From ab826041528a92a6e8b326bb4b4432cc00629505 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 21 Sep 2020 09:16:53 +0200 Subject: [PATCH 001/191] [fix] (template): Missing code in wrappers' doc. Error #187 --- docs/generate_docs.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/generate_docs.py b/docs/generate_docs.py index c471d06d2f9..446fe83a9e6 100644 --- a/docs/generate_docs.py +++ b/docs/generate_docs.py @@ -34,10 +34,10 @@ TOOL_TEMPLATE = Template(f.read()) with open(os.path.join(BASE_DIR, "_templates", "wrapper.rst")) as f: - TEMPLATE = Template(f.read()) + TEMPLATE_WRAPPER = Template(f.read()) with open(os.path.join(BASE_DIR, "_templates", "meta_wrapper.rst")) as f: - TEMPLATE = Template(f.read()) + TEMPLATE_META = Template(f.read()) def get_tool_dir(tool): @@ -88,7 +88,7 @@ def render_wrapper(path, target): name = meta["name"].replace(" ", "_") + ".rst" os.makedirs(os.path.dirname(target), exist_ok=True) with open(target, "w") as readme: - rst = TEMPLATE.render( + rst = TEMPLATE_WRAPPER.render( snakefile=snakefile, wrapper=wrapper, wrapper_lang=wrapper_lang, @@ -113,7 +113,7 @@ def render_meta(path, target): with open(os.path.join(path, "test", "Snakefile")) as snakefile: snakefile = textwrap.indent(snakefile.read(), " ").replace("master", TAG) - + wrappers = [] for uw in used_wrappers: wrapper = os.path.join(WRAPPER_DIR, uw, "wrapper.py") @@ -124,11 +124,11 @@ def render_meta(path, target): with open(wrapper) as wrapper: wrapper = textwrap.indent(wrapper.read(), " ") wrappers.append((wrapper, wrapper_lang, uw)) - + name = meta["name"].replace(" ", "_") + ".rst" os.makedirs(os.path.dirname(target), exist_ok=True) with open(target, "w") as readme: - rst = TEMPLATE.render( + rst = TEMPLATE_META.render( snakefile=snakefile, wrappers=wrappers, usedwrappers=used_wrappers, From 84147d6abff64e5b82f1dd9890b220dc3bf3e2eb Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 16 Jul 2021 09:09:37 +0200 Subject: [PATCH 002/191] [doc] (meta.yaml): adapterremoval and arriba pushed to current standard --- bio/adapterremoval/meta.yaml | 23 +++++++++++++---------- bio/arriba/meta.yaml | 14 ++++++++++++++ 2 files changed, 27 insertions(+), 10 deletions(-) diff --git a/bio/adapterremoval/meta.yaml b/bio/adapterremoval/meta.yaml index f3fb673fba8..efe64dd07b4 100644 --- a/bio/adapterremoval/meta.yaml +++ b/bio/adapterremoval/meta.yaml @@ -1,17 +1,20 @@ name: "AdapterRemoval" description: rapid adapter trimming, identification, and read merging. +url: https://adapterremoval.readthedocs.io/en/latest/ authors: - Filipe G. Vieira input: - - raw fastq file with R1 reads - - raw fastq file with R2 reads (PE only) + - sample: + - raw fastq file with R1 reads + - raw fastq file with R2 reads (PE only) output: - - trimmed fastq file with R1 reads - - trimmed fastq file with R2 reads (PE only) - - fastq file with singleton reads (PE only; PE reads for which the mate has been discarded) - - fastq file with collapsed reads (PE only; overlapping mate-pairs which have been merged into a single read) - - fastq file with collapsed truncated reads (PE only; collapsed reads that were quality trimmed) - - fastq file with discarded reads (reads that did not pass filters) - - settings and stats file + - fq: path to single fastq file (SE only) + - fq1: path to fastq R1 (PE only) + - fq2: path to fastq R2 (PE only) + - singleton: fastq file with singleton reads (PE only; PE reads for which the mate has been discarded) + - collapsed: fastq file with collapsed reads (PE only; overlapping mate-pairs which have been merged into a single read) + - collapsed_trunc: fastq file with collapsed truncated reads (PE only; collapsed reads that were quality trimmed) + - discarded: fastq file with discarded reads (reads that did not pass filters) + - settings: settings and stats file notes: | - * For more information see, https://adapterremoval.readthedocs.io/en/latest/ + * All output files, except for 'settings', must be compressed the same way (gz, or bz2). diff --git a/bio/arriba/meta.yaml b/bio/arriba/meta.yaml index 2e6357df4af..dc103d024c8 100644 --- a/bio/arriba/meta.yaml +++ b/bio/arriba/meta.yaml @@ -1,4 +1,18 @@ name: "arriba" +url: https://github.com/suhrig/arriba description: Detect gene fusions from chimeric STAR output authors: - Jan Forster +input: + - bam: Path to bam formatted alignment file from STAR + - genome: Path to fasta formatted genome sequence + - annotation: Path to GTF formatted genome annotation +output: + - fusions: Path to output fusion file +notes: | + Parameters: + + * known_fusions: Path to known fusions file, see `official documentation on known fusions `_ for more information. + * blacklist: Path to blacklist file, see `official documentation on blacklist `_ for more information. + * sv_file: Path to structural variations calls from WGS, see `official documentation on SV `_ for more information. + * extra: Other `optional parameters `_. From e31b39c7e69ea31a0a104f6785137192d900f4e5 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:25:25 +0200 Subject: [PATCH 003/191] [doc] (meta.yaml): bio/optitype/meta.yaml updated --- bio/optitype/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/optitype/meta.yaml b/bio/optitype/meta.yaml index 1d3cef745bc..448902db548 100644 --- a/bio/optitype/meta.yaml +++ b/bio/optitype/meta.yaml @@ -1,4 +1,13 @@ name: Optitype -description: Precision 4-digit HLA-I-typing from NGS data based on integer linear programming. Use razers3 beforehand to generate input fastq files only mapping to HLA-regions. Please see https://github.com/FRED-2/OptiType +url: https://github.com/FRED-2/OptiType +description: Precision 4-digit HLA-I-typing from NGS data based on integer linear programming. Use razers3 beforehand to generate input fastq files only mapping to HLA-regions. authors: - Jan Forster +input: + - reads: Path to input reads +output: + - Path to OptiType results. This must be the first output in the outptu file list. +params: + - extra: Optional parameters + - config: Alternative config.ini file + - sequencing_type: Either ``rna`` or ``dna`` From 7c9b3d55d84db660f281a6a9bc973b7e0d662dd1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:25:40 +0200 Subject: [PATCH 004/191] [doc] (meta.yaml): bio/arriba/meta.yaml updated --- bio/arriba/meta.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/bio/arriba/meta.yaml b/bio/arriba/meta.yaml index dc103d024c8..126a8f25ae2 100644 --- a/bio/arriba/meta.yaml +++ b/bio/arriba/meta.yaml @@ -9,10 +9,10 @@ input: - annotation: Path to GTF formatted genome annotation output: - fusions: Path to output fusion file +params: + - known_fusions: Path to known fusions file, see `official documentation on known fusions `_ for more information. + - blacklist: Path to blacklist file, see `official documentation on blacklist `_ for more information. + - sv_file: Path to structural variations calls from WGS, see `official documentation on SV `_ for more information. + - extra: Other `optional parameters `_ notes: | - Parameters: - - * known_fusions: Path to known fusions file, see `official documentation on known fusions `_ for more information. - * blacklist: Path to blacklist file, see `official documentation on blacklist `_ for more information. - * sv_file: Path to structural variations calls from WGS, see `official documentation on SV `_ for more information. - * extra: Other `optional parameters `_. + This tool/wrapper does not handle multi threading. From c055590e5d64c5e9fc8d29a4527f112972e33dc1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 005/191] [doc] (meta.yaml): bio/art/profiler_illumina/meta.yaml updated --- bio/art/profiler_illumina/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/art/profiler_illumina/meta.yaml b/bio/art/profiler_illumina/meta.yaml index e73e1984997..10c40198b2a 100644 --- a/bio/art/profiler_illumina/meta.yaml +++ b/bio/art/profiler_illumina/meta.yaml @@ -1,6 +1,15 @@ name: art_profiler_illumina +url: https://www.niehs.nih.gov/research/resources/software/biostatistics/art/index.cfm description: Use the art profiler to create a base quality score profile for Illumina read data from a fastq file. authors: - David Laehnemann - Victoria Sack +input: + - Path to fastq-formatted input file (first place in the input list of files) +output: + - Path to txt formatted profile (first place in the output list of files) +params: + - Extra parameters (no keyword mapped parameter) +notes: | + Your input file must have one of the following extensions: fastq, fastq.gz, fq or fq.gz From 6fd3c214d604546f3517db916e3f152db062f1a2 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 006/191] [doc] (meta.yaml): bio/assembly-stats/meta.yaml updated --- bio/assembly-stats/meta.yaml | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/bio/assembly-stats/meta.yaml b/bio/assembly-stats/meta.yaml index 4b121e1575c..15f223c0087 100644 --- a/bio/assembly-stats/meta.yaml +++ b/bio/assembly-stats/meta.yaml @@ -1,12 +1,14 @@ name: "assembly-stats" description: Generates report of summary statistics for a genome assembly +url: https://github.com/sanger-pathogens/assembly-stats authors: - Pathogen Informatics, Wellcome Sanger Institute (assembly-stats tool) - https://github.com/sanger-pathogens - Max Cummins (Snakemake wrapper [unaffiliated with Wellcome Sanger Institute]) input: - - Genomic assembly (fasta format) + - assembly: Genomic assembly (fasta format) output: - - Assembly statistics (format of your choosing, default = tab-delimited) + - assembly_stats: Assembly statistics (format of your choosing, default = tab-delimited) +params: + - extra: Optional parameters, see `assembly-stats official documentation `_ notes: | - * The `extra` param allows for additional program arguments. - * For more inforamtion see https://github.com/sanger-pathogens/assembly-stats \ No newline at end of file + This tool/wrapper does not handle multi threading From beb4b13e7c0e53a55c68e4085e5bc262355e71ea Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 007/191] [doc] (meta.yaml): bio/bamtools/filter/meta.yaml updated --- bio/bamtools/filter/meta.yaml | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/bio/bamtools/filter/meta.yaml b/bio/bamtools/filter/meta.yaml index f6080f143e8..86f559fc6b7 100644 --- a/bio/bamtools/filter/meta.yaml +++ b/bio/bamtools/filter/meta.yaml @@ -1,8 +1,20 @@ name: bamtools filter -description: Filters BAM files. For more information about bamtools see `bamtools documentation `_ and `bamtools source code `_. +url: https://github.com/pezmaster31/bamtools +description: Filters BAM files. For more information about bamtools see `bamtools documentation `_ authors: - Antonie Vietor input: - - bam files (.bam) + - bam files (.bam), must be in first position output: - - bam file (.bam) + - bam file (.bam), must be in first position +params: + - tags: filtering tags + - min_size: minimum insert size + - max_size: maximum insert size + - min_length: minimum read length + - max_length: maximum read length + - additional_params: Other filtering and optional parameters +notes: | + A complete usage documentation is available here: https://raw.githubusercontent.com/wiki/pezmaster31/bamtools/Tutorial_Toolkit_BamTools-1.0.pdf + + This tool/wrapper does not handle multi threading From 3357f1d2a65980a317c2adfd21bacd0494b12968 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 008/191] [doc] (meta.yaml): bio/bamtools/filter_json/meta.yaml updated --- bio/bamtools/filter_json/meta.yaml | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/bio/bamtools/filter_json/meta.yaml b/bio/bamtools/filter_json/meta.yaml index df4f57f2576..639adedbcf8 100644 --- a/bio/bamtools/filter_json/meta.yaml +++ b/bio/bamtools/filter_json/meta.yaml @@ -1,9 +1,16 @@ name: bamtools filter with json -description: Filters BAM files with JSON-script for filtering parameters and rules. For more information about bamtools see `bamtools documentation `_ and `bamtools source code `_. +url: https://github.com/pezmaster31/bamtools +description: Filters BAM files with JSON-script for filtering parameters and rules. For more information about bamtools see `bamtools documentation `_ authors: - Antonie Vietor input: - - bam files (.bam) - - json file (.json) + - bam files (.bam), must be in first position output: - - bam file (.bam) + - bam file (.bam), must be in first position +params: + - json: Path to filter file, json formatted. + - region: see documentation for more information about multiple formats. +notes: | + A complete usage documentation is available here: https://raw.githubusercontent.com/wiki/pezmaster31/bamtools/Tutorial_Toolkit_BamTools-1.0.pdf + + This tool/wrapper does not handle multi threading From 726cd582fa72d518ead6f67f315abe820bc729fe Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 009/191] [doc] (meta.yaml): bio/bamtools/split/meta.yaml updated --- bio/bamtools/split/meta.yaml | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/bio/bamtools/split/meta.yaml b/bio/bamtools/split/meta.yaml index 47cf5707d47..0eff5f931ca 100644 --- a/bio/bamtools/split/meta.yaml +++ b/bio/bamtools/split/meta.yaml @@ -1,8 +1,15 @@ name: bamtools split +url: https://github.com/pezmaster31/bamtools description: Split bam file into sub files, default by reference authors: - Patrik Smeds input: - - bam file + - bam file, this must be the only file in input. output: - - multiple bam file + - multiple bam file multiple formats. +params: + - extra: Optional parameters +notes: | + A complete usage documentation is available here: https://raw.githubusercontent.com/wiki/pezmaster31/bamtools/Tutorial_Toolkit_BamTools-1.0.pdf + + This tool/wrapper does not handle multi threading From 23569cf37f5d8cd90509cef2b87688a17c84e624 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 010/191] [doc] (meta.yaml): bio/bamtools/stats/meta.yaml updated --- bio/bamtools/stats/meta.yaml | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/bio/bamtools/stats/meta.yaml b/bio/bamtools/stats/meta.yaml index 3d13f25f142..7b6c0f4af9f 100644 --- a/bio/bamtools/stats/meta.yaml +++ b/bio/bamtools/stats/meta.yaml @@ -1,8 +1,15 @@ name: bamtools stats +url: https://github.com/pezmaster31/bamtools description: Use bamtools to collect statistics from a BAM file. For more information about bamtools see `bamtools documentation `_ and `bamtools source code `_. authors: - Antonie Vietor input: - - bam files (.bam) + - bam files (.bam), must be in first position output: - - bamstats file (.bamstats) + - bamstats file (.bamstats), must be in first position +params: + - Optional parameters as first and only value. +notes: | + A complete usage documentation is available here: https://raw.githubusercontent.com/wiki/pezmaster31/bamtools/Tutorial_Toolkit_BamTools-1.0.pdf + + This tool/wrapper does not handle multi threading From c8109396d49cc1b45763fb8d89396de6ea01ca10 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 011/191] [doc] (meta.yaml): bio/bbtools/bbduk/meta.yaml updated --- bio/bbtools/bbduk/meta.yaml | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/bio/bbtools/bbduk/meta.yaml b/bio/bbtools/bbduk/meta.yaml index 9d2b82e3410..77650a6db2b 100644 --- a/bio/bbtools/bbduk/meta.yaml +++ b/bio/bbtools/bbduk/meta.yaml @@ -1,17 +1,19 @@ name: BBDuk +url: https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/bbduk-guide/ description: | Run BBDuk. authors: - Filipe G. Vieira input: - - raw fastq file with R1 reads - - raw fastq file with R2 reads (optional) + - sample: list of paths. Raw fastq file with R1 reads, raw fastq file with R2 reads (PE only, optional) output: - - trimmed fastq file with R1 reads - - trimmed fastq file with R2 reads (optional) - - fastq file with singleton reads (optional) - - fastq file with discarded reads (optional) - - stats file (optonal) + - trimmed: trimmed fastq file with R1 reads, trimmed fastq file with R2 reads (PE only, optional) + - singleton: fastq file with singleton reads (optional) + - discarded: fastq file with discarded reads (optional) + - stats: stats file (optonal) +params: + - extra: Optional parameters + - adapters: Literal adapters sequences notes: | * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). * The `extra` param allows for additional program arguments. From ad804b0ff742c7a7c85392e48dbc1ea96af7c93d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 012/191] [doc] (meta.yaml): bio/bcftools/call/meta.yaml updated --- bio/bcftools/call/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/bcftools/call/meta.yaml b/bio/bcftools/call/meta.yaml index 61b0af2924e..304bbc64150 100644 --- a/bio/bcftools/call/meta.yaml +++ b/bio/bcftools/call/meta.yaml @@ -1,5 +1,13 @@ name: bcftools call +url: https://samtools.github.io/bcftools/bcftools.html#call description: Call variants with `bcftools call `_. authors: - Johannes Köster - Michael Hall +input: + - pileup: Path to input pileup file. +output: + - calls: Path to calling results. +params: + - caller: Either `--multiallelic-caller` or `--consensus-caller` + - options: Optional parameters From 880b242f3001cffc3536b6441fb4cd1ba2b79374 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 013/191] [doc] (meta.yaml): bio/bcftools/concat/meta.yaml updated --- bio/bcftools/concat/meta.yaml | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/bio/bcftools/concat/meta.yaml b/bio/bcftools/concat/meta.yaml index 56c543e6663..a725ba7afd2 100644 --- a/bio/bcftools/concat/meta.yaml +++ b/bio/bcftools/concat/meta.yaml @@ -1,13 +1,14 @@ name: bcftools concat +url: https://www.htslib.org/doc/bcftools.html#concat description: Concatenate vcf/bcf files with bcftools. For more information see `BCFtools documentation `_. authors: - Johannes Köster - Filipe G. Vieira input: - - vcf files + - calls: list of vcf files output: - - Concatenated VCF/BCF file -notes: | - * The `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). - * The `extra` param alllows for additional program arguments (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`). - * For more information see, https://samtools.github.io/bcftools/bcftools.html + - Concatenated VCF/BCF file, must be the first file in output +params: + - extra: Optional parameters (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`) + - uncompressed_bcf: The `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). + - bcftools_use_mem: The `bcftools_use_mem` param controls whether to pass the resources.mem_mb to bcftools From 6b58d68f245d1965f6b1255d397f47270b0bf73c Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 014/191] [doc] (meta.yaml): bio/bcftools/filter/meta.yaml updated --- bio/bcftools/filter/meta.yaml | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/bio/bcftools/filter/meta.yaml b/bio/bcftools/filter/meta.yaml index 91a1ec0c27e..cf92378ca38 100644 --- a/bio/bcftools/filter/meta.yaml +++ b/bio/bcftools/filter/meta.yaml @@ -1,14 +1,17 @@ name: bcftools filter +url: https://samtools.github.io/bcftools/bcftools.html#filter description: filter vcf/bcf file. authors: - Patrik Smeds - Nikos Tsardakas Renhuldt input: - - VCF/BCF file + - VCF/BCF file, must be the first in the input list output: - - Filtered VCF/BCF file + - Filtered VCF/BCF file, must be the only output +params: + - extra: Optional parameters (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`) + - filter: Filters, see `official bcftools expressions `_ for more information. + - uncompressed_bcf: The `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). + - bcftools_use_mem: The `bcftools_use_mem` param controls whether to pass the resources.mem_mb to bcftools notes: | - * The `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). - * The `bcftools_use_mem` param controls whether to pass the resources.mem_mb to bcftools - * The `extra` param allows for additional program arguments (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`). - * For more information see, https://samtools.github.io/bcftools/bcftools.html + * For more information see `tutorial `_ From 331c1984bcca957469be9e6d9d72b107e857bc89 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 015/191] [doc] (meta.yaml): bio/bcftools/index/meta.yaml updated --- bio/bcftools/index/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/bcftools/index/meta.yaml b/bio/bcftools/index/meta.yaml index aa428f2e9ec..c1f57d554d0 100644 --- a/bio/bcftools/index/meta.yaml +++ b/bio/bcftools/index/meta.yaml @@ -1,4 +1,13 @@ name: bcftools index -description: Index vcf/bcf file. For more information see `BCFtools documentation `_. +url: https://samtools.github.io/bcftools/bcftools.html#index +description: Index vcf/bcf file. authors: - Jan Forster +input: + - Path to a VCF/BCF file, must be the first element of the input list. +output: + - Path to the index. +params: + - extra: Optional parameters +notes: | + BCFTools indexes gzipped VCF files or BCF files. Raw, unzipped VCF files will raise an error. From 54e97e97715bb4cf807c3c7c36b4c1b482a6fe3d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 016/191] [doc] (meta.yaml): bio/bcftools/merge/meta.yaml updated --- bio/bcftools/merge/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/bcftools/merge/meta.yaml b/bio/bcftools/merge/meta.yaml index 49796646520..92c8c3baee0 100644 --- a/bio/bcftools/merge/meta.yaml +++ b/bio/bcftools/merge/meta.yaml @@ -1,4 +1,13 @@ name: bcftools merge -description: Merge vcf/bcf files with bcftools. For more information see `BCFtools documentation `_. +url: https://samtools.github.io/bcftools/bcftools.html#index +description: Merge vcf/bcf files with bcftools. authors: - Patrik Smeds +intpu: + - calls: List of paths to VCF/BCF files. +output: + - Merged VCF/BCF file, must be the first element in the output file list. +params: + - Optional parameters, must be the first and only value in snakemake's params. +notes: | + BCFTools will take longer to merge non-gzipped VCF files. From fc74165ebd897136fe48424dd934241244e4bdea Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 017/191] [doc] (meta.yaml): bio/bcftools/mpileup/meta.yaml updated --- bio/bcftools/mpileup/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/bcftools/mpileup/meta.yaml b/bio/bcftools/mpileup/meta.yaml index 5b2d39c1cb6..b4f77e02124 100644 --- a/bio/bcftools/mpileup/meta.yaml +++ b/bio/bcftools/mpileup/meta.yaml @@ -1,4 +1,13 @@ name: bcftools mpileup +url: https://samtools.github.io/bcftools/bcftools.html#mpileup description: Generate VCF or BCF containing genotype likelihoods for one or multiple alignment (BAM or CRAM) files with `bcftools mpileup `_. authors: - Michael Hall +input: + - alignments: List of paths to bam-formatted almignments +output: + - pileup: Path to pileup result file +params: + - options: Optional parameters +notes: | + Add --regions and --samples-files through params.options From 8a9184d4afa80a6788711a6ea0cfec080e6a2fa4 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 018/191] [doc] (meta.yaml): bio/bcftools/norm/meta.yaml updated --- bio/bcftools/norm/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/bcftools/norm/meta.yaml b/bio/bcftools/norm/meta.yaml index 2716ffd7bbb..73df61ebe7d 100644 --- a/bio/bcftools/norm/meta.yaml +++ b/bio/bcftools/norm/meta.yaml @@ -1,4 +1,11 @@ name: bcftools norm +url: https://samtools.github.io/bcftools/bcftools.html#mpileup description: Left-align and normalize indels, check if REF alleles match the reference, split multiallelic sites into multiple rows; recover multiallelics from multiple rows. For more information see `BCFtools documentation `_. authors: - Dayne Filer +input: + - Path to gzipped VCF or BCF, must be the first in the input file list +output: + - normalized VCF/BCF +params: + - Optional parameters, ust be the first and only value in snakemake's params. From 4503604d79e9140aeb1bcb6d5f642293565b7cc6 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 019/191] [doc] (meta.yaml): bio/bcftools/reheader/meta.yaml updated --- bio/bcftools/reheader/meta.yaml | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/bio/bcftools/reheader/meta.yaml b/bio/bcftools/reheader/meta.yaml index 2046866e53d..9f33766d952 100644 --- a/bio/bcftools/reheader/meta.yaml +++ b/bio/bcftools/reheader/meta.yaml @@ -1,4 +1,16 @@ name: bcftools reheader -description: Change header or sample names of vcf/bcf file. For more information see `BCFtools documentation `_. +url: https://samtools.github.io/bcftools/bcftools.html#mpileup +description: Change header or sample names of vcf/bcf file. authors: - Jan Forster +input: + - vcf: Path to vcf file + - header: Path to the new header (optional) + - samples: Path to the sample file (optional) +output: + - reheaded vcf, must be the only output file +params: + - extra: bcftools reheader optional parameters + - view_extra: bcftools view optional parameters +notes: | + This wrapper requires at least two threads: one for bcftools reheader, one for bcftools view. From 9c6b9359b9d671f5ecc2a209657664662c1a4f06 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 020/191] [doc] (meta.yaml): bio/bcftools/sort/meta.yaml updated --- bio/bcftools/sort/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/bcftools/sort/meta.yaml b/bio/bcftools/sort/meta.yaml index 0f9825352a8..615c95daf53 100644 --- a/bio/bcftools/sort/meta.yaml +++ b/bio/bcftools/sort/meta.yaml @@ -1,4 +1,12 @@ name: bcftools sort +url: https://www.htslib.org/doc/bcftools.html#sort description: Sort vcf/bcf file. For more information see `BCFtools documentation `_. authors: - Filipe G. Vieira +input: + - VCF/BCF file, must be the first element of the input list +output: + - VCF/BCF file, must be the first element of the output list +params: + - extra: Optional parameters + - uncompressed_bcf: Boolean. Return uncompressed BCF file. From 075c2171e46f73ee020b93d4d43a1d306048a9b2 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 021/191] [doc] (meta.yaml): bio/bcftools/view/meta.yaml updated --- bio/bcftools/view/meta.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/bio/bcftools/view/meta.yaml b/bio/bcftools/view/meta.yaml index 3215b65b12c..cf69c190939 100644 --- a/bio/bcftools/view/meta.yaml +++ b/bio/bcftools/view/meta.yaml @@ -1,14 +1,14 @@ name: bcftools view +url: https://samtools.github.io/bcftools/bcftools.html#view description: View vcf/bcf file in a different format. authors: - Johannes Köster - Nikos Tsardakas Renhuldt input: - - VCF/BCF file + - VCF/BCF file, must be the first in the input file list output: - - Filtered VCF/BCF file -notes: | - * The `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). - * The `bcftools_use_mem` param controls whether to pass the resources.mem_mb to bcftools - * The `extra` param allows for additional program arguments (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`). - * For more information see, https://samtools.github.io/bcftools/bcftools.html + - Filtered VCF/BCF file, must be the only element in the output file list +params: + extra: The `extra` param allows for additional program arguments (not `--threads, `-O/--output-type`, `-m/--max-mem`, or `-T/--temp-dir`). + uncompressed_bcf: he `uncompressed_bcf` param allows to specify that a BCF output should be uncompressed (ignored otherwise). + bcftools_use_mem: The `bcftools_use_mem` param controls whether to pass the resources.mem_mb to bcftools From 6d17c9e13ef2690e4ad76042394bc7b4054b167e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 022/191] [doc] (meta.yaml): bio/bedtools/complement/meta.yaml updated --- bio/bedtools/complement/meta.yaml | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/bio/bedtools/complement/meta.yaml b/bio/bedtools/complement/meta.yaml index 4a5c4907189..e8fc0ad9757 100644 --- a/bio/bedtools/complement/meta.yaml +++ b/bio/bedtools/complement/meta.yaml @@ -1,10 +1,13 @@ name: bedtools complement +url: https://bedtools.readthedocs.io/en/latest/content/tools/complement.html description: > `Bedtools complement `_ maps all regions of the genome which are not covered by the input. authors: - Antonie Vietor input: - - BED/GFF/VCF files - - genome file (`genome file format `_) + - in_file: BED/GFF/VCF files + - genome: genome file (`genome file format `_) output: - - complemented BED/GFF/VCF file + - complemented BED/GFF/VCF file, must be the first element in the output list +params: + - extra: Optional parameters From 643345543689ea52c092edef71ac12c8f8dc6895 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 023/191] [doc] (meta.yaml): bio/bedtools/coveragebed/meta.yaml updated --- bio/bedtools/coveragebed/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/bedtools/coveragebed/meta.yaml b/bio/bedtools/coveragebed/meta.yaml index ab4ee4ea95e..050e3b95e25 100644 --- a/bio/bedtools/coveragebed/meta.yaml +++ b/bio/bedtools/coveragebed/meta.yaml @@ -1,6 +1,14 @@ name: "coverageBed" +url: https://bedtools.readthedocs.io/en/latest/content/tools/coverage.html description: Returns the depth and breadth of coverage of features from B on the intervals in A. authors: - Patrik Smeds +input: + - a: BAM/BED/GFF/VCF file + - b: One or more BAM/BED/GFF/VCF file(s) +output: + - Output coverage file, this must be the first element of the output file list. +params: + - extra: Optional parameters, see `coverageBed official documentation `_ for more information. From 44d93359d6485c6dbb743a1be5cd88479374ec6a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 024/191] [doc] (meta.yaml): bio/bedtools/genomecov/meta.yaml updated --- bio/bedtools/genomecov/meta.yaml | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/bio/bedtools/genomecov/meta.yaml b/bio/bedtools/genomecov/meta.yaml index 42971ba84b0..c9b27792cf1 100644 --- a/bio/bedtools/genomecov/meta.yaml +++ b/bio/bedtools/genomecov/meta.yaml @@ -1,12 +1,15 @@ name: bedtools genomeCoverageBed +url: https://bedtools.readthedocs.io/en/latest/content/tools/genomecov.html description: > ``bedtools``'s genomeCoverageBed computes the coverage of a feature file as histograms, per-base reports or BEDGRAPH summaries among a given genome. - For usage information about genomeCoverageBed, please see ``bedtools``'s `documentation `_. - For more information about ``bedtools``, also see the `source code `_. authors: - Antonie Vietor input: - BED/GFF/VCF files grouped by chromosome and genome file (`genome file format `_) OR - - BAM files sorted by position. + - BAM files sorted by position, must be in first position in the input file list output: - - genomecov (.genomecov) + - genomecov (.genomecov), must be in first position in the output file list +params: + - Optional parameters, must be the only value in snakemake's params +notes: | + For more information about ``bedtools``, also see the `source code `_. From 25b721e5d671146d6d754c8c0200d2a6b3cd31c8 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 025/191] [doc] (meta.yaml): bio/bedtools/intersect/meta.yaml updated --- bio/bedtools/intersect/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/bedtools/intersect/meta.yaml b/bio/bedtools/intersect/meta.yaml index ced8a070265..98355302bc4 100644 --- a/bio/bedtools/intersect/meta.yaml +++ b/bio/bedtools/intersect/meta.yaml @@ -1,4 +1,12 @@ name: "bedtools intersect" +url: https://bedtools.readthedocs.io/en/latest/content/tools/intersect.html description: Intersect BED/BAM/VCF files with bedtools. authors: - Jan Forster +params: + - extra: Optional parameters, see `bedtools intersect official documentation `_ for more information. +input: + - left: BAM/BED/GFF/VCF file + - right: One or more BAM/BED/GFF/VCF file(s) +output: + - Path to output intersection. Must be the only element in the output file list From 3636f58469aeca10fa2e717515b49b1e6f717e61 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 026/191] [doc] (meta.yaml): bio/bedtools/merge/meta.yaml updated --- bio/bedtools/merge/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/bedtools/merge/meta.yaml b/bio/bedtools/merge/meta.yaml index 7f0cad8410b..f0c5cf177cd 100644 --- a/bio/bedtools/merge/meta.yaml +++ b/bio/bedtools/merge/meta.yaml @@ -1,4 +1,13 @@ name: "bedtools merge" +url: https://bedtools.readthedocs.io/en/latest/content/tools/merge.html description: Merge entries in one or multiple BED/BAM/VCF/GFF files with bedtools. authors: - Jan Forster +params: + - extra: Optional parameters, see `bedtools intersect official documentation `_ for more information. +input: + - One or more BED file. Input files must be all compressed or uncompressed. +output: + - One BED-formatted output file, this must be the only output. +notes: | + When more than one BED is provided, the three threads are used (cat/zcat + sort + bcftools merge). From e84d1c289610c05dd4f9600ecad8d5430487355b Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 027/191] [doc] (meta.yaml): bio/bedtools/slop/meta.yaml updated --- bio/bedtools/slop/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/bedtools/slop/meta.yaml b/bio/bedtools/slop/meta.yaml index d5f2ba49f2c..3ecb99ff89a 100644 --- a/bio/bedtools/slop/meta.yaml +++ b/bio/bedtools/slop/meta.yaml @@ -1,4 +1,12 @@ name: "bedtools slop" +url: https://bedtools.readthedocs.io/en/latest/content/tools/slop.html description: Increase the size of each feature in a BED/BAM/VCF by a specified factor. authors: - Jan Forster +input: + - BED/GFF/VCF file, must be the first in the list + - genome: Path to genome intervals +output: + - Path to output BED/GFF/VCF file, must be the only output element +params: + - extra: Optional parameters, see `bedtools slope official documentation `_ for more information. From fe352d34174e571ba5e0cac28a51bb2a00c32dfe Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 028/191] [doc] (meta.yaml): bio/bedtools/sort/meta.yaml updated --- bio/bedtools/sort/meta.yaml | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/bio/bedtools/sort/meta.yaml b/bio/bedtools/sort/meta.yaml index 7a546faf59e..7ea07e1a400 100644 --- a/bio/bedtools/sort/meta.yaml +++ b/bio/bedtools/sort/meta.yaml @@ -1,11 +1,14 @@ name: bedtools sort +url: https://bedtools.readthedocs.io/en/latest/content/tools/sort.html description: > Sorts bed, vcf or gff files by chromosome and other criteria, for more information please see `bedtools sort documentation `_. authors: - Antonie Vietor input: - - BED/GFF/VCF files - - optional a tab separating file that determines the sorting order and contains the chromosome names in the first column - - optional a fasta index file + - in_file: BED/GFF/VCF files + - genome: optional a tab separating file that determines the sorting order and contains the chromosome names in the first column + - faidx: optional a fasta index file output: - - complemented BED/GFF/VCF file + - complemented BED/GFF/VCF file, must be the first +params: + - extra: Optional parameters, see `bedtools sort official documentation `_ for more information. From 23d9a9bf109c37463f91817e4b5c2af8cb84ce21 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 029/191] [doc] (meta.yaml): bio/benchmark/chm-eval-kit/meta.yaml updated --- bio/benchmark/chm-eval-kit/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/benchmark/chm-eval-kit/meta.yaml b/bio/benchmark/chm-eval-kit/meta.yaml index 4055b6f4e5e..5ea1c14653d 100644 --- a/bio/benchmark/chm-eval-kit/meta.yaml +++ b/bio/benchmark/chm-eval-kit/meta.yaml @@ -1,4 +1,12 @@ name: chm-eval-kit -description: Download CHM-eval kit (https://github.com/lh3/CHM-eval) for benchmarking variant calling. +url: https://github.com/lh3/CHM-eval +description: Download CHM-eval kit for benchmarking variant calling. authors: - Johannes Köster +output: + - Downloaded kit +params: + - version: The kit version number + - tag: The kit tag number +notes: | + At least two threads are required (curl + tar) From 991cf2d0a3648e4f9abdaf9a46739a589b252ad7 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 030/191] [doc] (meta.yaml): bio/benchmark/chm-eval-sample/meta.yaml updated --- bio/benchmark/chm-eval-sample/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/benchmark/chm-eval-sample/meta.yaml b/bio/benchmark/chm-eval-sample/meta.yaml index ad911f6267e..3f6d7325a57 100644 --- a/bio/benchmark/chm-eval-sample/meta.yaml +++ b/bio/benchmark/chm-eval-sample/meta.yaml @@ -1,4 +1,12 @@ name: chm-eval-sample -description: Download CHM-eval sample (https://github.com/lh3/CHM-eval) for benchmarking variant calling. +url: https://github.com/lh3/CHM-eval +description: Download CHM-eval sample for benchmarking variant calling. authors: - Johannes Köster +input: + - +output: + - bam: Path to output bam file + - bai: Path to bam index +params: + - first_n: Work on the first n lines From cc0feb14a70fcbe0dc74f26c00adc5bf1089c6a0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 031/191] [doc] (meta.yaml): bio/benchmark/chm-eval/meta.yaml updated --- bio/benchmark/chm-eval/meta.yaml | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/bio/benchmark/chm-eval/meta.yaml b/bio/benchmark/chm-eval/meta.yaml index 1aad7b7e501..76447c787b5 100644 --- a/bio/benchmark/chm-eval/meta.yaml +++ b/bio/benchmark/chm-eval/meta.yaml @@ -1,4 +1,16 @@ name: chm-eval -description: Evaluate given VCF file with chm-eval (https://github.com/lh3/CHM-eval) for benchmarking variant calling. +url: https://github.com/lh3/CHM-eval +description: Evaluate given VCF file with chm-eval for benchmarking variant calling. authors: - Johannes Köster +input: + - kit: Path to downloaded chm-eval-kit + - vcf: Path to VCF formatted calls +output: + - Summary file + - bed files containing errors +params: + - build: Genome build + - extra: Other optional arguments +notes: | + Output file order and mapping do not matter within the Snakefile From c6ecbcd57051850dd33ef2ab7807d3b52196c545 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 032/191] [doc] (meta.yaml): bio/biobambam2/bamsormadup/meta.yaml updated --- bio/biobambam2/bamsormadup/meta.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/bio/biobambam2/bamsormadup/meta.yaml b/bio/biobambam2/bamsormadup/meta.yaml index 65bb3ef1278..8dfefbc51a9 100644 --- a/bio/biobambam2/bamsormadup/meta.yaml +++ b/bio/biobambam2/bamsormadup/meta.yaml @@ -1,15 +1,15 @@ name: BioBamBam2 BamSorMaDup +url: https://gitlab.com/german.tischler/biobambam2 description: | Mark PCR and optical duplicates, followed with sorting, with BioBamBam2 tools authors: - Filipe G. Vieira input: - - SAM/BAM/CRAM file + - SAM/BAM/CRAM file, must be the first element in the input file list - reference (for CRAM output) output: - - SAM/BAM/CRAM file with marked duplicates - - BAM index file (optional) - - metrics file (optional) -notes: | - * The `extra` param allows for additional program arguments (not `inputformat` or `outputformat`). - * For more information see, https://gitlab.com/german.tischler/biobambam2 + - bam: SAM/BAM/CRAM file with marked duplicates + - index: BAM index file (optional) + - metrics: metrics file (optional) +params: + - extra: The `extra` param allows for additional program arguments (not `inputformat` or `outputformat`). More information on the `official documentation `_ From 6297d705d46c16f11081066e85850036a50304a5 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 033/191] [doc] (meta.yaml): bio/bismark/bam2nuc/meta.yaml updated --- bio/bismark/bam2nuc/meta.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/bio/bismark/bam2nuc/meta.yaml b/bio/bismark/bam2nuc/meta.yaml index 06f9b365eef..4ce9f1f4681 100644 --- a/bio/bismark/bam2nuc/meta.yaml +++ b/bio/bismark/bam2nuc/meta.yaml @@ -1,7 +1,8 @@ name: bam2nuc +url: https://github.com/FelixKrueger/Bismark/blob/master/bam2nuc description: | Calculate mono- and di-nucleotide coverage of the reads and compares them with average genomic sequence - composition (see https://github.com/FelixKrueger/Bismark/blob/master/bam2nuc). + composition. authors: - Roman Cherniatchik input: From df34a225baa8bf5cb2da813315cee36296efd1f2 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 034/191] [doc] (meta.yaml): bio/bismark/bismark/meta.yaml updated --- bio/bismark/bismark/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/bismark/bismark/meta.yaml b/bio/bismark/bismark/meta.yaml index 8810037de1d..6aa21f41d0c 100644 --- a/bio/bismark/bismark/meta.yaml +++ b/bio/bismark/bismark/meta.yaml @@ -1,6 +1,7 @@ name: bismark +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark description: | - Align BS-Seq reads using Bismark (see https://github.com/FelixKrueger/Bismark/blob/master/bismark). + Align BS-Seq reads using Bismark. authors: - Roman Cherniatchik input: @@ -13,4 +14,4 @@ params: output: - bam: Bam file. Output file will be renamed if differs from default `NAME_pe.bam` or `NAME_se.bam` - report: Aligning report file. Output file will be renamed if differs from default `NAME_PE_report.txt` or `NAME_SE_report.txt` - - nucleotide_stats: Optional nucleotides report file. Output file will be renamed if differs from default `NAME_pe.nucleotide_stats.txt` or `NAME_se.nucleotide_stats.txt` \ No newline at end of file + - nucleotide_stats: Optional nucleotides report file. Output file will be renamed if differs from default `NAME_pe.nucleotide_stats.txt` or `NAME_se.nucleotide_stats.txt` From 07d5742558000defae276d2699f3ed4a2753f1ed Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 035/191] [doc] (meta.yaml): bio/bismark/bismark2bedGraph/meta.yaml updated --- bio/bismark/bismark2bedGraph/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/bismark/bismark2bedGraph/meta.yaml b/bio/bismark/bismark2bedGraph/meta.yaml index ece1c07df61..5807c79e9d1 100644 --- a/bio/bismark/bismark2bedGraph/meta.yaml +++ b/bio/bismark/bismark2bedGraph/meta.yaml @@ -1,6 +1,7 @@ name: bismark2bedGraph +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark2bedGraph description: | - Generate bedGraph and coverage files from positional methylation files created by bismark_methylation_extractor (see https://github.com/FelixKrueger/Bismark/blob/master/bismark2bedGraph). + Generate bedGraph and coverage files from positional methylation files created by bismark_methylation_extractor. authors: - Roman Cherniatchik input: @@ -9,4 +10,4 @@ params: - extra: Any additional args, e.g. '--CX', '--ample_memory', ' --buffer_size 10G', etc. output: - bedGraph: Bismark methylation level track, \*.bedGraph.gz (0-based start, 1-based end coordintates, i.e. end offset exclusive) - - cov: Optional bismark coverage file \*.bismark.cov.gz, file name is calculated by bedGraph name (1-based start and end, i.e. end offset inclusive) \ No newline at end of file + - cov: Optional bismark coverage file \*.bismark.cov.gz, file name is calculated by bedGraph name (1-based start and end, i.e. end offset inclusive) From c9ca4171d4abda04bb81098d03f6157648ab39fd Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 036/191] [doc] (meta.yaml): bio/bismark/bismark2report/meta.yaml updated --- bio/bismark/bismark2report/meta.yaml | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/bio/bismark/bismark2report/meta.yaml b/bio/bismark/bismark2report/meta.yaml index cd84e3a16bc..915ca0ee3c6 100644 --- a/bio/bismark/bismark2report/meta.yaml +++ b/bio/bismark/bismark2report/meta.yaml @@ -1,6 +1,7 @@ name: bismark2report +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark2report description: | - Generate graphical HTML report from Bismark reports (see https://github.com/FelixKrueger/Bismark/blob/master/bismark2report). + Generate graphical HTML report from Bismark reports. authors: - Roman Cherniatchik input: @@ -9,11 +10,9 @@ input: - dedup_report: Optional deduplication report (if not specified bismark will try to find it current directory) - splitting_report: Optional Bismark methylation extractor report (if not specified bismark will try to find it current directory) - mbias_report: Optional Bismark methylation extractor report (if not specified bismark will try to find it current directory) - params: - skip_optional_reports: Use 'true' of 'false' to not look for optional reports not mentioned in input section (passes 'none' to bismark2report) - extra: Any additional args - output: - html: Output HTML file path, if batch mode isn't used. - - html_dir: Output dir path for HTML reports if batch mode is used \ No newline at end of file + - html_dir: Output dir path for HTML reports if batch mode is used From 2824d8787cf709c7382f77b26d315a8c2f95dbed Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 037/191] [doc] (meta.yaml): bio/bismark/bismark2summary/meta.yaml updated --- bio/bismark/bismark2summary/meta.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/bio/bismark/bismark2summary/meta.yaml b/bio/bismark/bismark2summary/meta.yaml index f3182fbbc6f..1506a7e29d9 100644 --- a/bio/bismark/bismark2summary/meta.yaml +++ b/bio/bismark/bismark2summary/meta.yaml @@ -1,6 +1,7 @@ name: bismark2summary +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark2summary description: | - Generate summary graphical HTML report from several Bismark text report files reports (see https://github.com/FelixKrueger/Bismark/blob/master/bismark2summary). + Generate summary graphical HTML report from several Bismark text report files reports. authors: - Roman Cherniatchik input: @@ -8,7 +9,6 @@ input: params: - extra: Any additional args - title: Optional report custom title. - output: - html: Output HTML report path (e.g. 'bismark_summary_report.html'). - - txt: Output txt table path (e.g. 'bismark_summary_report.txt'). Should have same as 'html' report but with suffix '.txt'. \ No newline at end of file + - txt: Output txt table path (e.g. 'bismark_summary_report.txt'). Should have same as 'html' report but with suffix '.txt'. From 45a4dc58c658d83d3816f1bbc0fbf1abee2dff4d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 038/191] [doc] (meta.yaml): bio/bismark/bismark_genome_preparation/meta.yaml updated --- bio/bismark/bismark_genome_preparation/meta.yaml | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/bio/bismark/bismark_genome_preparation/meta.yaml b/bio/bismark/bismark_genome_preparation/meta.yaml index 37a52371d83..459d90cb8d8 100644 --- a/bio/bismark/bismark_genome_preparation/meta.yaml +++ b/bio/bismark/bismark_genome_preparation/meta.yaml @@ -1,9 +1,12 @@ name: bismark_genome_preparation +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark_genome_preparation description: | - Generate indexes for Bismark (see https://github.com/FelixKrueger/Bismark/blob/master/bismark_genome_preparation). + Generate indexes for Bismark. authors: - Roman Cherniatchik input: - - path to genome \*.fa (or \*.fasta, \*.fa.gz, \*.fasta.gz) file + - path to genome \*.fa (or \*.fasta, \*.fa.gz, \*.fasta.gz) file, must be the first element in the input file list output: - - No ouptut, generates bismark indexes in parent directory of input file \ No newline at end of file + - No ouptut, generates bismark indexes in parent directory of input file. Must be the first element in the output file list +params: + - extra: Optional parameters From 49e3c7dad86dcba72ee24e5abb83174944d81678 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 039/191] [doc] (meta.yaml): bio/bismark/bismark_methylation_extractor/meta.yaml updated --- bio/bismark/bismark_methylation_extractor/meta.yaml | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/bio/bismark/bismark_methylation_extractor/meta.yaml b/bio/bismark/bismark_methylation_extractor/meta.yaml index 06dda38e931..6d8d4bcb607 100644 --- a/bio/bismark/bismark_methylation_extractor/meta.yaml +++ b/bio/bismark/bismark_methylation_extractor/meta.yaml @@ -1,10 +1,11 @@ name: bismark_methylation_extractor +url: https://github.com/FelixKrueger/Bismark/blob/master/bismark_methylation_extractor description: | - Call methylation counts from Bismark alignment results (see https://github.com/FelixKrueger/Bismark/blob/master/bismark_methylation_extractor). + Call methylation counts from Bismark alignment results. authors: - Roman Cherniatchik input: - - Input BAM file aligned by Bismark + - Input BAM file aligned by Bismark, must be the only element in the input file list params: - output_dir: Output directory (current dir is used if not specified) - ignore: Number of bases to trim at 5' end in R1 (see bismark_methylation_extractor documentation), optional argument @@ -20,6 +21,6 @@ output: - splitting_report: Splitting report, \*_splitting_report.txt (if key is provided, the out file will be renamed to this name) - methylome_CpG_cov: Bismark coverage file for CpG context, \*.bismark.cov.gz (if key is provided, the out file will be renamed to this name) - methylome_CpG_mlevel_bedGraph: Bismark methylation level track, \*.bedGraph.gz - - read_base_meth_state_cpg: Per read CpG base methylation info, CpG_context_\*.txt.gz (if key is provided, the out file will be renamed to this name) - - read_base_meth_state_chg: Per read CpG base methylation info, CHG_context_\*.txt.gz (if key is provided, the out file will be renamed to this name) - - read_base_meth_state_chh: Per read CpG base methylation info, CHH_context_\*.txt.gz (if key is provided, the out file will be renamed to this name) + - read_base_meth_state_cpg: Per read CpG base methylation info, CpG_context\_\*.txt.gz (if key is provided, the out file will be renamed to this name) + - read_base_meth_state_chg: Per read CpG base methylation info, CHG_context\_\*.txt.gz (if key is provided, the out file will be renamed to this name) + - read_base_meth_state_chh: Per read CpG base methylation info, CHH_context\_\*.txt.gz (if key is provided, the out file will be renamed to this name) From 95acf8dc99fbefbdcc6389af1332d88d329ca550 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:34 +0200 Subject: [PATCH 040/191] [doc] (meta.yaml): bio/bismark/deduplicate_bismark/meta.yaml updated --- bio/bismark/deduplicate_bismark/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/bismark/deduplicate_bismark/meta.yaml b/bio/bismark/deduplicate_bismark/meta.yaml index 218286beefa..daf33774b55 100644 --- a/bio/bismark/deduplicate_bismark/meta.yaml +++ b/bio/bismark/deduplicate_bismark/meta.yaml @@ -1,6 +1,7 @@ name: deduplicate_bismark +url: https://github.com/FelixKrueger/Bismark/blob/master/deduplicate_bismark description: | - Deduplicate Bismark Bam Files and saves as \*.bam file (see https://github.com/FelixKrueger/Bismark/blob/master/deduplicate_bismark). + Deduplicate Bismark Bam Files and saves as \*.bam file. authors: - Roman Cherniatchik input: @@ -9,4 +10,4 @@ params: - extra: Additional deduplicate_bismark args output: - bam: Result bam file path. The file will be renamed if differs from `NAME.deduplicated.bam` for given 'NAME.bam' input. - - report: Result report path. The file will be renamed if differs from `NAME.deduplication_report.txt` for given 'NAME.bam' input. \ No newline at end of file + - report: Result report path. The file will be renamed if differs from `NAME.deduplication_report.txt` for given 'NAME.bam' input. From a3081aca3f997506008108c66a197f398533a064 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 041/191] [doc] (meta.yaml): bio/blast/blastn/meta.yaml updated --- bio/blast/blastn/meta.yaml | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/bio/blast/blastn/meta.yaml b/bio/blast/blastn/meta.yaml index 98ccbe4ade4..53067ef12ab 100644 --- a/bio/blast/blastn/meta.yaml +++ b/bio/blast/blastn/meta.yaml @@ -1,9 +1,8 @@ name: blast blastn +url: https://www.ncbi.nlm.nih.gov/books/NBK279690/ description: > ``Blastn`` performs a sequence similarity search of nucleotide query sequences against a nucleotide database. - For more information please see `BLAST documentation `_. - - +notes: | Different `formatting output options `_ and `formatting specifiers `_ (see tables below) can be selected via the 'format' parameter as shown in example Snakemake rule below. +----------------------------------------+---------------+------------+ @@ -162,8 +161,12 @@ description: > author: - Antonie Vietor input: - - FASTA file OR - - bare sequence file (`more information `_) OR - - identifiers (`more information `_) + - query: FASTA file OR + - query: bare sequence file (`more information `_) OR + - query: identifiers (`more information `_) + - blastdb: Path to local blast database output: - depending on the formatting option, different output files can be generated (see tables above) +params: + - extra: Optional parameters + - format: Optional output format, see notes below From 4fb45a6768570e16daf8f808db3d9d45b057a45f Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 042/191] [doc] (meta.yaml): bio/blast/makeblastdb/meta.yaml updated --- bio/blast/makeblastdb/meta.yaml | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/bio/blast/makeblastdb/meta.yaml b/bio/blast/makeblastdb/meta.yaml index 4651a11b70e..d5532b8b761 100644 --- a/bio/blast/makeblastdb/meta.yaml +++ b/bio/blast/makeblastdb/meta.yaml @@ -1,10 +1,14 @@ name: blast makeblastdb for FASTA files +url: https://www.ncbi.nlm.nih.gov/books/NBK279690/ description: > Makeblastdb produces local `BLAST `_ databases from nucleotide or protein FASTA files. - For more information please see `BLAST documentation `_. author: - Antonie Vietor input: - - FASTA file + - fasta: FASTA file output: - - multiple files with different extensions (e.g. .nin, .nsq, .nhr for nucleotides or .pin, .psq, .phr for proteins) + - multiple files with different extensions (e.g. .nin, .nsq, .nhr for nucleotides or .pin, .psq, .phr for proteins). Must be the first element in the output file list +params: + - Optional arguments, this must be the only element in snakemake's params +notes: | + This tool/wrapper does not handle multi threading From e9ee227fa5f94e676c9f21ce9f20ed50dd965ff4 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 043/191] [doc] (meta.yaml): bio/bowtie2/align/meta.yaml updated --- bio/bowtie2/align/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/bowtie2/align/meta.yaml b/bio/bowtie2/align/meta.yaml index ce33fe50b65..f3bfee43323 100644 --- a/bio/bowtie2/align/meta.yaml +++ b/bio/bowtie2/align/meta.yaml @@ -1,6 +1,14 @@ name: "bowtie2" +url: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml description: Map reads with bowtie2. authors: - Johannes Köster -note: +input: + - sample: List of input fastq files. R1 for Single End, R1 and R2 for Paired end. +output: + - BAM formatted aligned reads, this must be the first element of the output file list +params: + - index: Index prefix + - extra: Optional parameters, more information on the `bowtie2-build documentation `_ +notes: This wrapper uses an inner pipe. Make sure to use at least two threads in your Snakefile. From 1f17724820998364489e231dfb9a7ee265bed184 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 044/191] [doc] (meta.yaml): bio/bowtie2/build/meta.yaml updated --- bio/bowtie2/build/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/bowtie2/build/meta.yaml b/bio/bowtie2/build/meta.yaml index 1af7c14e3d4..a597030cb2f 100644 --- a/bio/bowtie2/build/meta.yaml +++ b/bio/bowtie2/build/meta.yaml @@ -1,4 +1,11 @@ name: "bowtie2_build" +url: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml description: Map reads with bowtie2. authors: - Daniel Standage +params: + - extra: Optional parameters, more information on the `bowtie2-build documentation `_ +output: + - Index files. The ".1.bt2" index must be the first of the output file list +input: + - reference: fasta-formatted sequence file From 0995c488546cb939ef74de4a8eb01e6023bfb0ef Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 045/191] [doc] (meta.yaml): bio/busco/meta.yaml updated --- bio/busco/meta.yaml | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/bio/busco/meta.yaml b/bio/busco/meta.yaml index 9ed4f431be9..2edc019a2d7 100644 --- a/bio/busco/meta.yaml +++ b/bio/busco/meta.yaml @@ -1,9 +1,15 @@ name: busco +url: https://busco-archive.ezlab.org/ description: | - Assess assembly and annotation completeness with BUSCO + Assess assembly and annotation completeness with BUSCO authors: - Tessa Pierce input: - - assembly fasta + - assembly fasta, this must be the only element of the input file list output: - - annotation quality files + - annotation quality files, must be the first files in the output file list +params: + - extra: Optional parameters, see `BUSCO official documentation `_ for more information. + - mode: Either genome, proteins, or transcriptome + - lineage: location of the BUSCO lineage data to use + - download_path: Path to downloaded BUSCO data for offline use From 8816eedba05c4dc061b5cbaa735d0fca56ec21b3 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 046/191] [doc] (meta.yaml): bio/bwa-mem2/index/meta.yaml updated --- bio/bwa-mem2/index/meta.yaml | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/bio/bwa-mem2/index/meta.yaml b/bio/bwa-mem2/index/meta.yaml index 4b2f7d6c13e..d644289febd 100644 --- a/bio/bwa-mem2/index/meta.yaml +++ b/bio/bwa-mem2/index/meta.yaml @@ -1,5 +1,12 @@ name: "bwa-mem2 index" +url: https://github.com/bwa-mem2/bwa-mem2 description: "Creates a bwa-mem2 index." authors: - Christopher Schröder - - Patrik Smeds \ No newline at end of file + - Patrik Smeds +input: + - Path to Fasta formatted genome sequence, must be the first and only element of the input file list. +output: + - Path to genome index +params: + prefix: Genome index prefix From a4417631c5a9925dd737baecd7cd56ebbbdce31f Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 047/191] [doc] (meta.yaml): bio/bwa-mem2/mem-samblaster/meta.yaml updated --- bio/bwa-mem2/mem-samblaster/meta.yaml | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/bio/bwa-mem2/mem-samblaster/meta.yaml b/bio/bwa-mem2/mem-samblaster/meta.yaml index 7127db91bee..c1f30c998f5 100644 --- a/bio/bwa-mem2/mem-samblaster/meta.yaml +++ b/bio/bwa-mem2/mem-samblaster/meta.yaml @@ -1,4 +1,22 @@ name: "bwa mem samblaster" +url: https://github.com/bwa-mem2/bwa-mem2 description: Map reads using bwa-mem2, mark duplicates by samblaster and sort and index by sambamba. authors: - - Christopher Schröder \ No newline at end of file + - Christopher Schröder +input: + - reads: List of paths to fastq files. R1 is mandatory, and an optional R2 is required for paired end +output: + - SAM/BAM file +params: + - index: Path to indexed genome + - extra: Optional parameters for bwa mem + - sort: Either "none", "samtools", or "picard". + - sort_order: Either "coordinate" or "queryname" + - sort_extra: Extra parameters for samtools or picard +notes: | + This wrapper uses more threads than the number reserved in the snakemake rule. For X reserved threads, 3X+1 threads are used: + + * X in BWA mem, + * X more in sambamba view, + * X more in sambamba sort. + * 1 more in samblaster From 0c69426ed95fbed7dd1a1ac78e6da7635cd02a3e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 048/191] [doc] (meta.yaml): bio/bwa-mem2/mem/meta.yaml updated --- bio/bwa-mem2/mem/meta.yaml | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/bio/bwa-mem2/mem/meta.yaml b/bio/bwa-mem2/mem/meta.yaml index c13a645f95a..34b37058a73 100644 --- a/bio/bwa-mem2/mem/meta.yaml +++ b/bio/bwa-mem2/mem/meta.yaml @@ -1,6 +1,19 @@ name: "bwa-mem2" +url: https://github.com/bwa-mem2/bwa-mem2 description: Bwa-mem2 is the next version of the bwa-mem algorithm in bwa. It produces alignment identical to bwa and is ~1.3-3.1x faster depending on the use-case, dataset and the running machine. Optional sorting using samtools or picard. authors: - Christopher Schröder - Johannes Köster - Julian de Ruiter +input: + - reads: List of paths to fastq files. R1 is mandatory, and an optional R2 is required for paired end +output: + - SAM/BAM file +params: + - index: Path to indexed genome + - extra: Optional parameters for bwa mem + - sort: Either "none", "samtools", or "picard". + - sort_order: Either "coordinate" or "queryname" + - sort_extra: Extra parameters for samtools or picard +notes: | + This wrapper uses an inner pipe. For X threads reserved in the snakemake rule, this wrapper uses X+1 threads when the `sort` parameter is not none. From 4ebe1918cf28af6443ab87634468b31e1a6795b8 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 049/191] [doc] (meta.yaml): bio/bwa/aln/meta.yaml updated --- bio/bwa/aln/meta.yaml | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/bio/bwa/aln/meta.yaml b/bio/bwa/aln/meta.yaml index 8b31e20d9df..d20ec873939 100644 --- a/bio/bwa/aln/meta.yaml +++ b/bio/bwa/aln/meta.yaml @@ -1,4 +1,11 @@ name: "bwa aln" -description: Map reads with bwa aln. For more information about BWA see `BWA documentation `_. +url: http://bio-bwa.sourceforge.net/bwa.shtml +description: Map reads with bwa aln. authors: - Julian de Ruiter +input: + - Fastq file. This must be the first element of the input list +output: + - sai file. This must be the first element of the output list +params: + - index: Path to the bwa index From eabb6b2ebdacc61a11b6b3ace5d3ca82c8d628e0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 050/191] [doc] (meta.yaml): bio/bwa/index/meta.yaml updated --- bio/bwa/index/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/bwa/index/meta.yaml b/bio/bwa/index/meta.yaml index 800299f6b2f..9c3a9710b86 100644 --- a/bio/bwa/index/meta.yaml +++ b/bio/bwa/index/meta.yaml @@ -1,4 +1,12 @@ name: "bwa index" -description: Creates a BWA index. For more information about BWA see `BWA documentation `_. +url: http://bio-bwa.sourceforge.net/bwa.shtml +description: Creates a BWA index. authors: - Patrik Smeds +input: + - One and only one fasta formatted reference genome +output: + - Indexed sequence genome +params: + - algorithm: Either "is" or "bwtsw", the algorithm for constructing BWT index. Optional + - prefix: Genome index prefix, optional From 77badeae7a75ba11babd65a625769c80abea61a8 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 051/191] [doc] (meta.yaml): bio/bwa/mem-samblaster/meta.yaml updated --- bio/bwa/mem-samblaster/meta.yaml | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/bio/bwa/mem-samblaster/meta.yaml b/bio/bwa/mem-samblaster/meta.yaml index 2e64347e00a..eea9a4c719c 100644 --- a/bio/bwa/mem-samblaster/meta.yaml +++ b/bio/bwa/mem-samblaster/meta.yaml @@ -1,4 +1,21 @@ name: "bwa mem samblaster" +url: http://bio-bwa.sourceforge.net/bwa.shtml description: Map reads using bwa mem, mark duplicates by samblaster and sort and index by sambamba. authors: - - Christopher Schröder \ No newline at end of file + - Christopher Schröder +input: + reads: List of fastq files paths, R1 only for single end, R2 for paired end only. +params: + index: Path to bwa index + extra: Optional arguments for bwa mem + sort_extra: Optional arguments for sambamba sort + samblaster_extra: +output: + bam: Path to output bam +notes: | + This wrapper uses more threads than the number reserved in the snakemake rule. For X reserved threads, 3X+1 threads are used: + + * X in BWA mem, + * X more in sambamba view, + * X more in sambamba sort. + * 1 more in samblaster From 72ecf51c358eb93ccc49210a68c55b64e975948d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 052/191] [doc] (meta.yaml): bio/bwa/mem/meta.yaml updated --- bio/bwa/mem/meta.yaml | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/bio/bwa/mem/meta.yaml b/bio/bwa/mem/meta.yaml index b102139acfe..264326d1b2d 100644 --- a/bio/bwa/mem/meta.yaml +++ b/bio/bwa/mem/meta.yaml @@ -1,4 +1,5 @@ name: "bwa mem" +url: http://bio-bwa.sourceforge.net/bwa.shtml description: Map reads using bwa mem, with optional sorting using samtools or picard. authors: @@ -6,13 +7,14 @@ authors: - Julian de Ruiter - Filipe G. Vieira input: - - FASTQ file(s) - - reference genome + - reads: FASTQ file(s) output: - SAM/BAM/CRAM file +params: + - index: Path to the bwa index + - extra: The `extra` param allows for additional arguments for bwa-mem. + - sorting: The `sorting` param allows to enable sorting, and can be either 'none', 'samtools' or 'picard'. + - sort_extra: The `sort_extra` allows for extra arguments for samtools/picard + - tmp_dir: The `tmp_dir` param allows to define path to the temp dir. One can use `tmpdir resources `_ instead. notes: | - * The `extra` param allows for additional arguments for bwa-mem. - * The `sorting` param allows to enable sorting, and can be either 'none', 'samtools' or 'picard'. - * The `sort_extra` allows for extra arguments for samtools/picard - * The `tmp_dir` param allows to define path to the temp dir. - * For more inforamtion see, http://bio-bwa.sourceforge.net/bwa.shtml + Warning, this wrapper uses a number of threads equal to one plus the number of threads written in the Snakefile: sort + bwa mem From 61a1a24f52d28d4571afcf05cefb80a31ffd571a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 053/191] [doc] (meta.yaml): bio/bwa/sampe/meta.yaml updated --- bio/bwa/sampe/meta.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/bio/bwa/sampe/meta.yaml b/bio/bwa/sampe/meta.yaml index d860177b265..23061d83da2 100644 --- a/bio/bwa/sampe/meta.yaml +++ b/bio/bwa/sampe/meta.yaml @@ -1,4 +1,18 @@ name: "bwa sampe" +url: http://bio-bwa.sourceforge.net/bwa.shtml description: Map paired-end reads with bwa sampe. For more information about BWA see `BWA documentation `_. authors: - Julian de Ruiter +input: + - sai: Path to sai file from bwa aln + - fastq: Path to fastq file +output: + - sam/bam file +params: + - index: Path to genome index + - extra: Optional parameters for bwa sampe + - sort: Either "none", "samtools", or "picard". + - sort_order: Either "coordinate" or "queryname" + - sort_extra: Extra parameters for samtools or picard +notes: | + This wrapper uses two threads if sort parameter is not None. From 1f8e8824ac9c75566d3cd8540c42b33cc8b9be4f Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 054/191] [doc] (meta.yaml): bio/bwa/samse/meta.yaml updated --- bio/bwa/samse/meta.yaml | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/bio/bwa/samse/meta.yaml b/bio/bwa/samse/meta.yaml index b206d23bff8..4858890d035 100644 --- a/bio/bwa/samse/meta.yaml +++ b/bio/bwa/samse/meta.yaml @@ -1,4 +1,18 @@ name: "bwa samse" -description: Map single-end reads with bwa samse. For more information about BWA see `BWA documentation `_. +url: http://bio-bwa.sourceforge.net/bwa.shtm +description: Map single-end reads with bwa samse. authors: - Julian de Ruiter +input: + - sai: Path to sai file from bwa aln + - fastq: Path to fastq file +output: + - SAM/BAM file +params: + - index: Path to indexed genome + - extra: Optional parameters for bwa samse + - sort: Either "none", "samtools", or "picard". + - sort_order: Either "coordinate" or "queryname" + - sort_extra: Extra parameters for samtools or picard +notes: | + This wrapper uses two threads if sort parameter is not None. From 3bf0329a4d0f96141096a8c453e6afcdfe939309 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 055/191] [doc] (meta.yaml): bio/bwa/samxe/meta.yaml updated --- bio/bwa/samxe/meta.yaml | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/bio/bwa/samxe/meta.yaml b/bio/bwa/samxe/meta.yaml index cde5fd94479..6b19fac5dba 100644 --- a/bio/bwa/samxe/meta.yaml +++ b/bio/bwa/samxe/meta.yaml @@ -1,4 +1,18 @@ name: "bwa sam(se/pe)" -description: Map paired-end reads with either bwa samse or sampe. For more information about BWA see `BWA documentation `_. +url: http://bio-bwa.sourceforge.net/bwa.shtml +description: Map paired-end reads with either bwa samse or sampe. authors: - Filipe G. Vieira +input: + - sai: Path to sai file from bwa aln + - fastq: List of path to fastq files +output: + - SAM/BAM file +params: + - index: Path to indexed genome sequence + - extra: Optional parameters for bwa samse/sampe + - sort: Either "none", "samtools", or "picard". + - sort_order: Either "coordinate" or "queryname" + - sort_extra: Extra parameters for samtools or picard +notes: | + This wrapper uses two threads if sort parameter is not None. From a2e8860a2529e20ddd48ee86e341fb3cc92cf228 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 056/191] [doc] (meta.yaml): bio/clustalo/meta.yaml updated --- bio/clustalo/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/clustalo/meta.yaml b/bio/clustalo/meta.yaml index 00dce2b45fe..68af0187d3a 100644 --- a/bio/clustalo/meta.yaml +++ b/bio/clustalo/meta.yaml @@ -1,4 +1,11 @@ name: clustalo +url: https://www.ebi.ac.uk/Tools/msa/clustalo/ description: Multiple alignment of nucleic acid and protein sequences. authors: - Michael Hall +input: + - Sequence in GCG, FASTA, EMBL (Nucleotide only), GenBank, PIR/NBRF, PHYLIP or UniProtKB/Swiss-Prot (Protein only) format. This must be the first element in the input file list. +output: + - Alignment file, this must be the first element in the output file list. +params: + - extra: Optional parameters, see `command line documentation `_ for more information. From 8c224da185d1ace6fb083b706e00e481cde29d93 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 057/191] [doc] (meta.yaml): bio/cutadapt/pe/meta.yaml updated --- bio/cutadapt/pe/meta.yaml | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/bio/cutadapt/pe/meta.yaml b/bio/cutadapt/pe/meta.yaml index d102b241729..db6d40a3cfe 100644 --- a/bio/cutadapt/pe/meta.yaml +++ b/bio/cutadapt/pe/meta.yaml @@ -5,7 +5,13 @@ authors: - Julian de Ruiter - David Laehnemann input: - - two (paired-end) fastq files + - Two (paired-end) fastq files. They must be the only elements in the input file list. output: - - two trimmed (paired-end) fastq files - - text file containing trimming statistics + - fastq1: trimmed R1 fastq file + - fastq2: trimmed R2 fastq file + - qc: text file containing trimming statistics +params: + - adapters: Adapters to remove + - extra: Optional parameters +note: | + This wrapper requires either `params.adapters` or `params.extra` to be non null and non empty. From 5e55d9fa31f1dd3dbbebf7d547fa0853e861c84b Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 058/191] [doc] (meta.yaml): bio/cutadapt/se/meta.yaml updated --- bio/cutadapt/se/meta.yaml | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/bio/cutadapt/se/meta.yaml b/bio/cutadapt/se/meta.yaml index 0df1fc3c008..7abd583fb31 100644 --- a/bio/cutadapt/se/meta.yaml +++ b/bio/cutadapt/se/meta.yaml @@ -1,10 +1,16 @@ name: cutadapt-se +url: https://cutadapt.readthedocs.io/en/stable/ description: | Trim single-end reads using cutadapt. authors: - Julian de Ruiter input: - - fastq file + - fastq file, this must be the first element of the input file list output: - - trimmed fastq file - - text file containing trimming statistics + - fastq: trimmed fastq file + - qc: text file containing trimming statistics +params: + - adapters: Adapters to remove + - extra: Optional parameters +note: | + This wrapper requires either `params.adapters` or `params.extra` to be non null and non empty. From 0d32c99e5f0802c7917e639bb894251721ae774d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 059/191] [doc] (meta.yaml): bio/dada2/add-species/meta.yaml updated --- bio/dada2/add-species/meta.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/bio/dada2/add-species/meta.yaml b/bio/dada2/add-species/meta.yaml index e8f24ebd9b5..5fd33dc960e 100644 --- a/bio/dada2/add-species/meta.yaml +++ b/bio/dada2/add-species/meta.yaml @@ -1,4 +1,5 @@ name: dada2_add_species +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Adding species-level annotation using dada2 ``addSpecies`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. @@ -10,4 +11,4 @@ input: params: - optional arguments for ``addSpecies()``, please provide them as python ``key=value`` pairs output: - - The input RDS file augmented by the species-level annotation + - The input RDS file augmented by the species-level annotation. It must be the first element in the output file. From 418404ddb0a170a5f8207cbe87be0e85e11616ba Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 060/191] [doc] (meta.yaml): bio/dada2/assign-species/meta.yaml updated --- bio/dada2/assign-species/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/assign-species/meta.yaml b/bio/dada2/assign-species/meta.yaml index 418b1597da6..c360433b770 100644 --- a/bio/dada2/assign-species/meta.yaml +++ b/bio/dada2/assign-species/meta.yaml @@ -1,4 +1,5 @@ name: dada2_assign_species +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Classifying sequences against a reference database using dada2 ``assignSpecies`` function. Optional parameters are documented in the `manual `_ and an example of the function can be found in the dedicated `section `_ of the DADA2 website. @@ -8,6 +9,6 @@ input: - seqs: RDS file with the chimera-free sequence table - refFasta: A string with the path to the genus-species FASTA reference database params: - - optional arguments for ``assignTaxonomy()``, please provide them as python ``key=value`` pairs + - optional arguments for ``assignTaxonomy()``, please provide them as python ``key=value`` pairs output: - - RDS file containing the genus and species taxonomic assignments + - RDS file containing the genus and species taxonomic assignments. It must be the first element in the output file. From b2ea8e5c5c87b2e16132451e3ab58e710b773f40 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 061/191] [doc] (meta.yaml): bio/dada2/assign-taxonomy/meta.yaml updated --- bio/dada2/assign-taxonomy/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/assign-taxonomy/meta.yaml b/bio/dada2/assign-taxonomy/meta.yaml index d60c7fc3ff1..ab228e4c2b6 100644 --- a/bio/dada2/assign-taxonomy/meta.yaml +++ b/bio/dada2/assign-taxonomy/meta.yaml @@ -1,4 +1,5 @@ name: dada2_assign_taxonomy +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Classifying sequences against a reference database using dada2 ``assignTaxonomy`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. @@ -8,6 +9,6 @@ input: - seqs: RDS file with the chimera-free sequence table - refFasta: A string with the path to the FASTA reference database params: - - optional arguments for ``assignTaxonomy()``, please provide them as python ``key=value`` pairs + - optional arguments for ``assignTaxonomy()``, please provide them as python ``key=value`` pairs output: - - RDS file containing the taxonomic assignments + - RDS file containing the taxonomic assignments. It must be the first element in the output file. From cdec7c7493eb19e01252ee5482e9524e2d9baa27 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 062/191] [doc] (meta.yaml): bio/dada2/collapse-nomismatch/meta.yaml updated --- bio/dada2/collapse-nomismatch/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/collapse-nomismatch/meta.yaml b/bio/dada2/collapse-nomismatch/meta.yaml index bab4ebb65ec..ed8b43f7c03 100644 --- a/bio/dada2/collapse-nomismatch/meta.yaml +++ b/bio/dada2/collapse-nomismatch/meta.yaml @@ -1,4 +1,5 @@ name: dada2_collapse_nomismatch +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Combine together sequences that are identical up to shifts and/or indels using dada2 ``collapseNoMismatch`` function. Optional parameters are documented in the `manual `_. While the function is not included in the `tutorial `_, feel free to browse the dada2 `issues `_ for showcases. @@ -7,6 +8,6 @@ authors: input: - RDS file with the chimera-free sequence table params: - - optional arguments for ``collapseNoMismatch()``, please provide them as python ``key=value`` pairs + - optional arguments for ``collapseNoMismatch()``, please provide them as python ``key=value`` pairs output: - - RDS file with the sequence table where the needed sequences were collapsed + - RDS file with the sequence table where the needed sequences were collapsed. It must be the first element in the output file. From ea7a9fe4e8aa3d5ec0c16e7e990f74ebda65fef8 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 063/191] [doc] (meta.yaml): bio/dada2/dereplicate-fastq/meta.yaml updated --- bio/dada2/dereplicate-fastq/meta.yaml | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/bio/dada2/dereplicate-fastq/meta.yaml b/bio/dada2/dereplicate-fastq/meta.yaml index 66af90eddbb..8ad61361092 100644 --- a/bio/dada2/dereplicate-fastq/meta.yaml +++ b/bio/dada2/dereplicate-fastq/meta.yaml @@ -1,13 +1,13 @@ name: dada2_dereplicate_fastq +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Dereplication of FASTQ files using dada2 ``derepFastq`` function. Optional parameters are documented in the `manual `_ and though the function is not introduced explicitly in the tutorial it is used in under the hood in the `learnErrors` `section `_. authors: - Charlie Pauvert -input: - - a FASTQ file +input: + - a FASTQ file. It must be the only element of the input file list. params: - optional arguments for ``derepFastq()``, please provide them as python ``key=value`` pairs -output: - - RDS file containing a ``derep-class`` object - +output: + - RDS file containing a ``derep-class`` object. It must be the first element in the output file. From 617a849abbc886ffea83d88d85034dc9d2405cd3 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 064/191] [doc] (meta.yaml): bio/dada2/filter-trim/meta.yaml updated --- bio/dada2/filter-trim/meta.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/bio/dada2/filter-trim/meta.yaml b/bio/dada2/filter-trim/meta.yaml index c0255eb119d..f0597123b6b 100644 --- a/bio/dada2/filter-trim/meta.yaml +++ b/bio/dada2/filter-trim/meta.yaml @@ -1,4 +1,5 @@ name: dada2_filter_trim +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Quality filtering of single or paired-end reads using dada2 ``filterAndTrim`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. From 754eb057eeabf862b9557a929ae5811ff3d642c5 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 065/191] [doc] (meta.yaml): bio/dada2/learn-errors/meta.yaml updated --- bio/dada2/learn-errors/meta.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/bio/dada2/learn-errors/meta.yaml b/bio/dada2/learn-errors/meta.yaml index 5189b07c093..76b803b8715 100644 --- a/bio/dada2/learn-errors/meta.yaml +++ b/bio/dada2/learn-errors/meta.yaml @@ -1,11 +1,12 @@ name: dada2_learn_errors +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Learning error rates separately on paired-end data using dada2 ``learnErrors`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. authors: - Charlie Pauvert input: - - A list of quality filtered and trimmed forward FASTQ files (potentially compressed) + - A list of quality filtered and trimmed forward FASTQ files (potentially compressed). It must be the only elements in the input file list. params: - optional arguments for ``learnErrors()``, please provide them as python ``key=value`` pairs output: From d673ba58dbd7153dba5ae00bd7b5375fed69e5f2 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 066/191] [doc] (meta.yaml): bio/dada2/make-table/meta.yaml updated --- bio/dada2/make-table/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/make-table/meta.yaml b/bio/dada2/make-table/meta.yaml index fb051f494af..41f2c7f3726 100644 --- a/bio/dada2/make-table/meta.yaml +++ b/bio/dada2/make-table/meta.yaml @@ -1,12 +1,13 @@ name: dada2_make_table +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Build a sequence - sample table from denoised samples using dada2 ``makeSequenceTable`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. authors: - Charlie Pauvert input: - - A list of RDS files with denoised samples (se), or denoised and merged samples (pe) -params: + - A list of RDS files with denoised samples (se), or denoised and merged samples (pe). It must be the only elements in the input file list. +params: - names: A list of sample names instead of paths - params: Any other optional arguments for ``makeSequenceTable()``, please provide them as python ``key=value`` pairs output: From 70d586c1ed392d96d86bd6b35f20e81722aa7a67 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 067/191] [doc] (meta.yaml): bio/dada2/merge-pairs/meta.yaml updated --- bio/dada2/merge-pairs/meta.yaml | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/bio/dada2/merge-pairs/meta.yaml b/bio/dada2/merge-pairs/meta.yaml index ca25c54afdd..fa11633e4a9 100644 --- a/bio/dada2/merge-pairs/meta.yaml +++ b/bio/dada2/merge-pairs/meta.yaml @@ -1,15 +1,16 @@ name: dada2_merge_pairs +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Merging denoised forward and reverse reads using dada2 ``mergePairs`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. authors: - Charlie Pauvert input: - - dadaF: RDS file with the inferred sample composition from forward reads - - dadaR: reverse + - dadaF: RDS file with the inferred sample composition from forward reads + - dadaR: reverse - derepF: RDS file with the dereplicated forward reads - - derepR: reverse + - derepR: reverse params: - optional arguments for ``mergePairs()``, please provide them as python ``key=value`` pairs output: - - RDS file with the merged pairs + - RDS file with the merged pairs. It must be the first element in the output file. From 5415f9c92bc002f8a86b470c3adcc41471fc3b47 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 068/191] [doc] (meta.yaml): bio/dada2/quality-profile/meta.yaml updated --- bio/dada2/quality-profile/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/quality-profile/meta.yaml b/bio/dada2/quality-profile/meta.yaml index f5acda6fe72..aab8986b53d 100644 --- a/bio/dada2/quality-profile/meta.yaml +++ b/bio/dada2/quality-profile/meta.yaml @@ -1,10 +1,11 @@ name: dada2_quality_profiles +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Plotting the quality profile of reads using dada2 ``plotQualityProfile`` function. The function is introduced in the dedicated tutorial `section `_. authors: - Charlie Pauvert input: - - a FASTQ file (potentially compressed) without primers sequences + - a FASTQ file (potentially compressed) without primers sequences. This must be the only elements in the input file list. output: - - A PNG file of the quality plot + - A PNG file of the quality plot. It must be the first element in the output file. From c50951bf2323b59d032c0bd764920933bf382b41 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 069/191] [doc] (meta.yaml): bio/dada2/remove-chimeras/meta.yaml updated --- bio/dada2/remove-chimeras/meta.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/bio/dada2/remove-chimeras/meta.yaml b/bio/dada2/remove-chimeras/meta.yaml index f1be9c21a2b..b67fe3666f1 100644 --- a/bio/dada2/remove-chimeras/meta.yaml +++ b/bio/dada2/remove-chimeras/meta.yaml @@ -1,12 +1,13 @@ name: dada2_remove_chimeras +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Remove chimera sequences from the sequence table data using dada2 ``removeBimeraDenovo`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. authors: - Charlie Pauvert input: - - RDS file with the sequence table + - RDS file with the sequence table. It must be the first element in the output file. params: - optional arguments for ``removeBimeraDenovo()``, please provide them as python ``key=value`` pairs output: - - RDS file with the chimera-free sequence table + - RDS file with the chimera-free sequence table. It must be the first element in the output file. From ebf2566f459c66bc32b79eaab9bb4aae5d96092c Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 070/191] [doc] (meta.yaml): bio/dada2/sample-inference/meta.yaml updated --- bio/dada2/sample-inference/meta.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/bio/dada2/sample-inference/meta.yaml b/bio/dada2/sample-inference/meta.yaml index 5201ed2b86a..1291f472293 100644 --- a/bio/dada2/sample-inference/meta.yaml +++ b/bio/dada2/sample-inference/meta.yaml @@ -1,4 +1,5 @@ name: dada2_sample_inference +url: https://benjjneb.github.io/dada2/index.html description: | `DADA2 `_ Inferring sample composition using dada2 ``dada`` function. Optional parameters are documented in the `manual `_ and the function is introduced in the dedicated tutorial `section `_. @@ -8,6 +9,6 @@ input: - derep: RDS file with the dereplicated sequences - err: RDS file with the error model output: - - RDS file with the stored inferred sample composition + - RDS file with the stored inferred sample composition. It must be the first element in the output file. params: - optional arguments for ``dada()``, please provide them as python ``key=value`` pairs From 79d7e15ea1224d647b0ac9b959ae7e2f02eca368 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 071/191] [doc] (meta.yaml): bio/deeptools/computematrix/meta.yaml updated --- bio/deeptools/computematrix/meta.yaml | 28 +++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/bio/deeptools/computematrix/meta.yaml b/bio/deeptools/computematrix/meta.yaml index db67533b477..18fbd70ad00 100644 --- a/bio/deeptools/computematrix/meta.yaml +++ b/bio/deeptools/computematrix/meta.yaml @@ -1,9 +1,23 @@ name: deepTools computeMatrix +url: https://deeptools.readthedocs.io/en/develop/content/tools/computeMatrix.html description: > ``deepTools computeMatrix`` calculates scores per genomic region. +authors: + - Antonie Vietor +input: + - bed: BED or GTF files (.bed or .gtf) AND + - bigwig: bigWig files (.bw) +output: + - matrix_gz: ipped matrix file (.gz) AND/OR + - matrix_tab: tab-separated table of matrix file (.tab) AND/OR + - matrix_bed: BED matrix file with sorted regions after skiping zeros or min/max threshold values (.bed) +params: + - command: Either `scale-regions` or `reference-point` + - extra: Optional parameters +notes: | + The matrix file can be used as input for other tools or for the generation of a ``deepTools plotHeatmap`` or ``deepTools plotProfiles``. - For usage information about ``deepTools computeMatrix``, please see the `documentation `_. - For more information about ``deepTools``, also see the `source code `_. + This tool/wrapper does not handle multithreading. +----------------------------+-----------------------------+---------------------+-------------+ | computeMatrix option | Output format | Name of output | Recommended | @@ -24,13 +38,3 @@ description: > | | | | | | | or min/max threshold values | | | +----------------------------+-----------------------------+---------------------+-------------+ - -authors: - - Antonie Vietor -input: - - BED or GTF files (.bed or .gtf) AND - - bigWig files (.bw) -output: - - gzipped matrix file (.gz) AND/OR - - tab-separated table of matrix file (.tab) AND/OR - - BED matrix file with sorted regions after skiping zeros or min/max threshold values (.bed) From e3ef2d3d669c454b4ff6bb3e36248cf16154750e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 072/191] [doc] (meta.yaml): bio/deeptools/plotfingerprint/meta.yaml updated --- bio/deeptools/plotfingerprint/meta.yaml | 30 +++++++++++++------------ 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/bio/deeptools/plotfingerprint/meta.yaml b/bio/deeptools/plotfingerprint/meta.yaml index 21af7f7a597..23369418222 100644 --- a/bio/deeptools/plotfingerprint/meta.yaml +++ b/bio/deeptools/plotfingerprint/meta.yaml @@ -1,13 +1,25 @@ name: deepTools plotFingerprint +url: https://deeptools.readthedocs.io/en/develop/content/tools/plotFingerprint.html description: > ``deepTools plotFingerprint`` plots a profile of cumulative read coverages from a list of indexed BAM files. - For usage information about ``deepTools plotFingerprint``, please see the `documentation `_. - For more information about ``deepTools``, also see the `source code `_. - - +authors: + - Antonie Vietor +input: + - jsd_sample: Reference sample against which to compute the Jensen-Shannon distance and the CHANCE statistics. + - bam_files: list of BAM files (.bam) AND + - list of their index files (.bam.bai) +output: + - fingerprint: plot file in image format (.png, .eps, .pdf or .svg) + - counts: tab-separated table of read counts per bin (.tab) (optional) + - qc_metrics: tab-separated table of metrics and JSD calculation (.txt) (optional) +params: + - optional parameters, this must be the only element in params. +notes: | In addition to required output, an optional output file of read counts can be generated by setting the output variable "counts" (see example Snakemake rule below). Also an optional output file of quality control metrics can be generated by setting the variable "qc_metrics". If the jsd_sample is specified in the input, the results of the Jensen-Shannon distance calculation are also written to this file. + This tool/wrapper does not handle multithreading. + +----------------------------+--------------------------------+---------------------+-------------+ | plotFingerprint option | Output | Name of output | Recommended | | | | | | @@ -33,13 +45,3 @@ description: > | | | | | | | distance calculation (optional)| | | +----------------------------+--------------------------------+---------------------+-------------+ - -authors: - - Antonie Vietor -input: - - list of BAM files (.bam) AND - - list of their index files (.bam.bai) -output: - - plot file in image format (.png, .eps, .pdf or .svg) - - tab-separated table of read counts per bin (.tab) (optional) - - tab-separated table of metrics and JSD calculation (.txt) (optional) From e2603b07e23c7c9b2a28ee6c242193450a36cbfb Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 073/191] [doc] (meta.yaml): bio/deeptools/plotheatmap/meta.yaml updated --- bio/deeptools/plotheatmap/meta.yaml | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/bio/deeptools/plotheatmap/meta.yaml b/bio/deeptools/plotheatmap/meta.yaml index 7fbf41d77f6..24b796402a7 100644 --- a/bio/deeptools/plotheatmap/meta.yaml +++ b/bio/deeptools/plotheatmap/meta.yaml @@ -1,13 +1,23 @@ name: deepTools plotHeatmap +url: https://deeptools.readthedocs.io/en/develop/content/tools/plotHeatmap.html description: > ``deepTools plotHeatmap`` creates a heatmap for scores associated with genomic regions. - As input, it requires a matrix file generated by ``deepTools computeMatrix``. - For usage information about ``deepTools plotHeatmap``, please see the `documentation `_. - For more information about ``deepTools``, also see the `source code `_. - - + As input, it requires a matrix file generated by ``deepTools computeMatrix`` +authors: + - Antonie Vietor +input: + - gzipped matrix file from ``deepTools computeMatrix`` (.gz). This must be the first file in the input file list. +output: + - heatmap_img: plot file in image format (.png, .eps, .pdf or .svg) AND/OR + - regions: file with sorted regions after skipping zeros or min/max threshold values (.bed) AND/OR + - heatmap_matrix: tab-separated table for average profile (.tab) +params: + - optional parameters, this must be the only element in params. +notes: | You can select which optional output files are generated by adding the respective output variable with the recommended extension(s) for them (see example Snakemake rule below). + This tool/wrapper does not handle multithreading. + +----------------------------+---------------------+---------------------+-------------+ | PlotHeatmap option | Output | Name of output | Recommended | | | | | | @@ -31,12 +41,3 @@ description: > | | | | | | | the heatmap | | | +----------------------------+---------------------+---------------------+-------------+ - -authors: - - Antonie Vietor -input: - - gzipped matrix file from ``deepTools computeMatrix`` (.gz) -output: - - plot file in image format (.png, .eps, .pdf or .svg) AND/OR - - file with sorted regions after skipping zeros or min/max threshold values (.bed) AND/OR - - tab-separated table for average profile (.tab) From 0a924ee7e45459c6c3fcdfb7af6521b535044419 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 074/191] [doc] (meta.yaml): bio/deeptools/plotprofile/meta.yaml updated --- bio/deeptools/plotprofile/meta.yaml | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/bio/deeptools/plotprofile/meta.yaml b/bio/deeptools/plotprofile/meta.yaml index f0b9d65ccd2..7a518774e8c 100644 --- a/bio/deeptools/plotprofile/meta.yaml +++ b/bio/deeptools/plotprofile/meta.yaml @@ -1,12 +1,25 @@ name: deepTools plotProfile +url: https://deeptools.readthedocs.io/en/develop/content/tools/plotProfile.html description: > ``deepTools plotProfile`` plots scores over sets of genomic regions. As input, it requires a matrix file generated by ``deepToolscomputeMatrix``. - For usage information about ``deepTools plotProfile``, please see the `documentation `_. - For more information about ``deepTools``, also see the `source code `_. You can select which optional output files are generated by adding the respective output variable with the recommended extension for them (see example Snakemake rule below). +authors: + - Antonie Vietor +input: + - gzipped matrix file from ``deepTools computeMatrix`` (.gz) This must be the first element in the input file. +output: + - plot_img: plot file in image format (.png, .eps, .pdf or .svg) AND/OR + - regions: file with sorted regions after skipping zeros or min/max threshold values (.bed) AND/OR + - data: tab-separated table for average profile (.tab) +params: + - optional parameters, this must be the only element in params. +notes: | + + + This tool/wrapper does not handle multithreading. +----------------------------+---------------------+---------------------+-------------+ | PlotProfile option | Output | Name of output | Recommended | @@ -29,12 +42,3 @@ description: > | | | | | | | for average profile | | | +----------------------------+---------------------+---------------------+-------------+ - -authors: - - Antonie Vietor -input: - - gzipped matrix file from ``deepTools computeMatrix`` (.gz) -output: - - plot file in image format (.png, .eps, .pdf or .svg) AND/OR - - file with sorted regions after skipping zeros or min/max threshold values (.bed) AND/OR - - tab-separated table for average profile (.tab) From c631c89f39413ec04ed9aa701da529b0ece5aa09 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 075/191] [doc] (meta.yaml): bio/deepvariant/meta.yaml updated --- bio/deepvariant/meta.yaml | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/bio/deepvariant/meta.yaml b/bio/deepvariant/meta.yaml index de548e3614d..47d3c0be219 100644 --- a/bio/deepvariant/meta.yaml +++ b/bio/deepvariant/meta.yaml @@ -1,15 +1,19 @@ name: deepvariant +url: https://github.com/google/deepvariant description: | - Call genetic variants using deep neural network. Copyright 2017 Google LLC. BSD 3-Clause "New" or "Revised" https://github.com/google/deepvariant + Call genetic variants using deep neural network. Copyright 2017 Google LLC. BSD 3-Clause "New" or "Revised" authors: - Tetsuro Hisayoshi - Nikos Tsardakas Renhuldt input: - - fasta - - bam + - ref: Path to genome sequence (fasta) + - bam: Path to bam file output: - - vcf - - visual report html + - visual report html + - vcf: vcf +params: + - extra: Optional parameters + - sample_name: Optional sample name + - model: One of ``WGS``, ``WES``, ``PACBIO``, or ``HYBRID_PACBIO_ILLUMINA`` notes: | - * The `extra` param alllows for additional program arguments. * This snakemake wrapper uses bioconda deepvariant package. Copyright 2018 Brad Chapman. From 6fd007beeb127d501d4cefa533e409ce18351682 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 076/191] [doc] (meta.yaml): bio/delly/meta.yaml updated --- bio/delly/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/delly/meta.yaml b/bio/delly/meta.yaml index 20506f31f47..f03c1df4b50 100644 --- a/bio/delly/meta.yaml +++ b/bio/delly/meta.yaml @@ -1,4 +1,13 @@ name: delly +url: https://github.com/dellytools/delly description: Call variants with delly. authors: - Johannes Köster +input: + ref: Fasta formatted genome sequence + exclude: BED4 formatted list of regions to exclude + samples: List of samples (bam) +output: + - VCF file, this must be the first element in the output file list. +params: + - extra: Optional parameters From 64107c6cf5df3375f806ff0b57ca7f0a6002af2b Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 077/191] [doc] (meta.yaml): bio/diamond/blastx/meta.yaml updated --- bio/diamond/blastx/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/diamond/blastx/meta.yaml b/bio/diamond/blastx/meta.yaml index fb778984593..8c9f7b7345e 100644 --- a/bio/diamond/blastx/meta.yaml +++ b/bio/diamond/blastx/meta.yaml @@ -1,4 +1,12 @@ name: "diamond blastx" +url: https://github.com/bbuchfink/diamond description: DIAMOND is a sequence aligner for protein and translated DNA searches, designed for high performance analysis of big sequence data. authors: - Kim Philipp Jablonski +input: + - fname_fastq: Path to fastq file + - fname_db: Path to diamond database +output: + - fname: Path to TSV output +params: + - extra: Optional parameters From 339b5f266486ba7630798c3dcaa7bb14bdae4b06 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 078/191] [doc] (meta.yaml): bio/diamond/makedb/meta.yaml updated --- bio/diamond/makedb/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/diamond/makedb/meta.yaml b/bio/diamond/makedb/meta.yaml index 0dd458edfc4..710d6855c58 100644 --- a/bio/diamond/makedb/meta.yaml +++ b/bio/diamond/makedb/meta.yaml @@ -1,4 +1,11 @@ name: "diamond makedb" +url: https://github.com/bbuchfink/diamond description: DIAMOND is a sequence aligner for protein and translated DNA searches, designed for high performance analysis of big sequence data. authors: - Kim Philipp Jablonski +input: + - fname: Path to the sequence genome, fasta formatted +output: + - fname: Path to diamond database +params: + - extra: Optional parameters From 7fe57d1e036f2ad7aa22db644c6feeebebce9cee Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 079/191] [doc] (meta.yaml): bio/epic/peaks/meta.yaml updated --- bio/epic/peaks/meta.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/bio/epic/peaks/meta.yaml b/bio/epic/peaks/meta.yaml index 177204c94df..90eb92fb863 100644 --- a/bio/epic/peaks/meta.yaml +++ b/bio/epic/peaks/meta.yaml @@ -1,4 +1,5 @@ name: epic +url: https://github.com/biocore-ntnu/epic authors: - Endre Bakken Stovner description: | From 4097926e685dbbe73b79a88add359823e23245cf Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 080/191] [doc] (meta.yaml): bio/fastp/meta.yaml updated --- bio/fastp/meta.yaml | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/bio/fastp/meta.yaml b/bio/fastp/meta.yaml index f330fc3d436..3bc2d70f7ea 100644 --- a/bio/fastp/meta.yaml +++ b/bio/fastp/meta.yaml @@ -1,18 +1,19 @@ name: "fastp" +url: https://github.com/OpenGene/fastp description: trim and QC fastq reads with fastp authors: - Sebastian Kurscheid (sebastian.kurscheid@unibas.ch) - Filipe G. Vieira input: - - fastq file(s) + - sample: List of fastq file(s) output: - - trimmed fastq file(s) - - unpaired reads (optional; eihter in a single file or separate) - - merged reads (optional) - - failed reads (optional) - - json file containing trimming statistics - - html file containing trimming statistics -notes: | - * The `adapters` param allows to specify adapter sequences - * The `extra` param allows for additional program arguments. - * For more inforamtion see, https://github.com/OpenGene/fastp + - trimmed: trimmed fastq file(s) + - unpaired1: unpaired reads (optional; eihter in a single file or separate) + - unpaired2: unpaired R2 reads in case of separate pairs + - merged: merged reads (optional) + - failed: failed reads (optional) + - json: json file containing trimming statistics + - html: html file containing trimming statistics +params: + - extra: The `extra` param allows for additional program arguments. + - adapters: The `adapters` param allows to specify adapter sequences From f0ef8c1573ba4b4444ddb4dd35b3ce5a47a5f6ba Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 081/191] [doc] (meta.yaml): bio/fastq_screen/meta.yaml updated --- bio/fastq_screen/meta.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/bio/fastq_screen/meta.yaml b/bio/fastq_screen/meta.yaml index 482671cc91f..e4d1afb34be 100644 --- a/bio/fastq_screen/meta.yaml +++ b/bio/fastq_screen/meta.yaml @@ -1,4 +1,5 @@ name: fastq_screen +url: http://www.bioinformatics.babraham.ac.uk/projects/fastq_screen authors: - Ryan Dale description: | @@ -39,10 +40,14 @@ description: | arguments verbatim to ``fastq_screen``, for example ``extra="--illumina1_3"`` or ``extra="--bowtie2 '--trim5=8'"``. input: - - A FASTQ file, gzipped or not. + - A FASTQ file, gzipped or not. This must be the first file in the input file list output: - txt: a text file containing the fraction of reads mapping to each provided index - png: a bar plot of the contents of ``txt``, saved as a PNG file +params: + - subset: The number of reads processed (default 100000) + - aligner: The aligner used with fastq_screen (default bowtie2) + - extra: optional parameters notes: | * ``fastq_screen`` hard-codes the output filenames. This wrapper moves the hard-coded output files to those specified by the rule. From 9071386285910fa2fc3df1083e0b8d284b656033 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 082/191] [doc] (meta.yaml): bio/fastqc/meta.yaml updated --- bio/fastqc/meta.yaml | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/bio/fastqc/meta.yaml b/bio/fastqc/meta.yaml index 5da8b492248..8c5f28a0f91 100644 --- a/bio/fastqc/meta.yaml +++ b/bio/fastqc/meta.yaml @@ -1,10 +1,13 @@ name: fastqc +url: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ description: | Generate fastq qc statistics using fastqc. authors: - Julian de Ruiter input: - - fastq file + - fastq file, this must be the first file in the input file list output: - - html file containing statistics - - zip file containing statistics + - html: html file containing statistics + - zip: zip file containing statistics +params: + - Optional arguments, this must be the only parameters From 1a1a7c2cfb1820f4540c8d5c8aa6a51582d5b354 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 083/191] [doc] (meta.yaml): bio/fgbio/annotatebamwithumis/meta.yaml updated --- bio/fgbio/annotatebamwithumis/meta.yaml | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/bio/fgbio/annotatebamwithumis/meta.yaml b/bio/fgbio/annotatebamwithumis/meta.yaml index acc45e3766c..d7c21dd175b 100644 --- a/bio/fgbio/annotatebamwithumis/meta.yaml +++ b/bio/fgbio/annotatebamwithumis/meta.yaml @@ -1,4 +1,14 @@ name: "fgbio AnnotateBamWithUmis" +url: https://fulcrumgenomics.github.io/fgbio/ description: Annotates existing BAM files with UMIs (Unique Molecular Indices, aka Molecular IDs, Molecular barcodes) from a separate FASTQ file. authors: - Patrik Smeds +input: + - bam: Path to bam file + - umi: Path to umi file +output: + - Path to annotated bam, this must be the only output file +params: + - extra: Optional parameters +notes: | + See source on `github `_. From c38bdebd2d1d3d8038ec7dde3777e7f22d7baa96 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 084/191] [doc] (meta.yaml): bio/fgbio/callmolecularconsensusreads/meta.yaml updated --- bio/fgbio/callmolecularconsensusreads/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/fgbio/callmolecularconsensusreads/meta.yaml b/bio/fgbio/callmolecularconsensusreads/meta.yaml index b1d6e32050b..523323aba76 100644 --- a/bio/fgbio/callmolecularconsensusreads/meta.yaml +++ b/bio/fgbio/callmolecularconsensusreads/meta.yaml @@ -1,4 +1,13 @@ name: "fgbio CallMolecularConsensusReads" +url: https://fulcrumgenomics.github.io/fgbio/ description: Calls consensus sequences from reads with the same unique molecular tag. authors: - Patrik Smeds +input: + - Path to bam file, this must be the first element in the input file list +output: + - Path to annotated bam file, this must be the first element in the output file list +params: + - extra: Optional parameters +notes: | + See source on `github `_. From 17a9ee17b54e736d5b2d89c24136fbed639ebe05 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 085/191] [doc] (meta.yaml): bio/fgbio/collectduplexseqmetrics/meta.yaml updated --- bio/fgbio/collectduplexseqmetrics/meta.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/bio/fgbio/collectduplexseqmetrics/meta.yaml b/bio/fgbio/collectduplexseqmetrics/meta.yaml index de4f720741e..57a2a13a403 100644 --- a/bio/fgbio/collectduplexseqmetrics/meta.yaml +++ b/bio/fgbio/collectduplexseqmetrics/meta.yaml @@ -1,4 +1,18 @@ name: "fgbio CollectDuplexSeqMetrics" +url: https://fulcrumgenomics.github.io/fgbio/ description: Collects a suite of metrics to QC duplex sequencing data.g. authors: - Patrik Smeds +input: + - Path to input bam file +output: + - family_sizes: metrics on the frequency of different types of families of different sizes + - duplex_family_sizes: metrics on the frequency of duplex tag families by the number of observations from each strand + - duplex_yield_metrics: summary QC metrics produced using 5%, 10%, 15%...100% of the data + - umi_counts: metrics on the frequency of observations of UMIs within reads and tag families + - duplex_qc: a series of plots generated from the preceding metrics files for visualization + - duplex_umi_counts: (optional) metrics on the frequency of observations of duplex UMIs within reads and tag families +params: + - extra: Optional parameters +notes: | + See source on `github `_. From b40753576735521f149a4321edcaf17900c692f9 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 086/191] [doc] (meta.yaml): bio/fgbio/filterconsensusreads/meta.yaml updated --- bio/fgbio/filterconsensusreads/meta.yaml | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/bio/fgbio/filterconsensusreads/meta.yaml b/bio/fgbio/filterconsensusreads/meta.yaml index a16be23d246..abdac7691d9 100644 --- a/bio/fgbio/filterconsensusreads/meta.yaml +++ b/bio/fgbio/filterconsensusreads/meta.yaml @@ -1,14 +1,14 @@ name: "fgbio FilterConsensusReads" +url: http://fulcrumgenomics.github.io/fgbio/tools/latest/FilterConsensusReads.html description: Filters consensus reads generated by CallMolecularConsensusReads or CallDuplexConsensusReads. authors: - Patrik Smeds input: - - bam file - - vcf files - - reference genome + - Path to bam file, this must be the first element in the input file list output: - - filtered bam file -notes: | - * min_base_quality: a single value (Int). Mask (make N) consensus bases with quality less than this threshold. (default: 5) - * min_reads: n array of Ints, max length 3, min length 1. Number of reads that need to support a UMI. For filtering bam files processed with CallMolecularConsensusReads one value is required. 3 values can be provided for bam files processed with CallDuplexConsensusReads, if fewer than 3 are provided the last value will be repeated, the first value is for the final consensus sequence and the two last for each strands consensus. - * For more information see, http://fulcrumgenomics.github.io/fgbio/tools/latest/FilterConsensusReads.html + - filtered bam file, this must be the first element in the output file list +params: + - ref: Path to reference genome sequence (fasta) + - extra: Optional parameters + - min_base_quality: a single value (Int). Mask (make N) consensus bases with quality less than this threshold. (default 5) + - min_reads: n array of Ints, max length 3, min length 1. Number of reads that need to support a UMI. For filtering bam files processed with CallMolecularConsensusReads one value is required. 3 values can be provided for bam files processed with CallDuplexConsensusReads, if fewer than 3 are provided the last value will be repeated, the first value is for the final consensus sequence and the two last for each strands consensus. From f38d8a63e4d729fa077b93c83d8682e020f43476 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 087/191] [doc] (meta.yaml): bio/fgbio/groupreadsbyumi/meta.yaml updated --- bio/fgbio/groupreadsbyumi/meta.yaml | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/bio/fgbio/groupreadsbyumi/meta.yaml b/bio/fgbio/groupreadsbyumi/meta.yaml index 5818e944006..30a036a525a 100644 --- a/bio/fgbio/groupreadsbyumi/meta.yaml +++ b/bio/fgbio/groupreadsbyumi/meta.yaml @@ -1,4 +1,14 @@ name: "fgbio GroupReadsByUmi" +url: https://fulcrumgenomics.github.io/fgbio/tools/latest/GroupReadsByUmi.html description: Groups reads together that appear to have come from the same original molecule. authors: - Patrik Smeds +input: + - Bam file. This must be the first input file in the input file list. +output: + - bam: path to grouped bam + - hist: Path to histogram +params: + - extra: Optional extra parameters +notes: | + See source on `github `_. From 525507f6a2a26a97a33267b3c6c701134da50c1e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 088/191] [doc] (meta.yaml): bio/fgbio/setmateinformation/meta.yaml updated --- bio/fgbio/setmateinformation/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/fgbio/setmateinformation/meta.yaml b/bio/fgbio/setmateinformation/meta.yaml index 6221bc8cc7a..212971b729d 100644 --- a/bio/fgbio/setmateinformation/meta.yaml +++ b/bio/fgbio/setmateinformation/meta.yaml @@ -1,4 +1,5 @@ name: "fgbio SetMateInformation" +url: https://fulcrumgenomics.github.io/fgbio/tools/latest/SetMateInformation.html description: Adds and/or fixes mate information on paired-end reads. Sets the MQ (mate mapping quality), MC (mate cigar string), ensures all mate-related @@ -6,3 +7,11 @@ description: position are correct. authors: - Patrik Smeds +input: + - Bam file. This must be the first input file in the input file list. +output: + - Bam file with mate information. This must be the first output file in the output file list. +params: + - extra: Optional extra parameters +notes: | + See source on `github `_. From 8d011ad1696fc777d09502b85b22aae11e77675f Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 089/191] [doc] (meta.yaml): bio/filtlong/meta.yaml updated --- bio/filtlong/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/filtlong/meta.yaml b/bio/filtlong/meta.yaml index 34b05c1f8c9..0c42be5d3ac 100644 --- a/bio/filtlong/meta.yaml +++ b/bio/filtlong/meta.yaml @@ -1,4 +1,12 @@ name: filtlong +url: https://github.com/rrwick/Filtlong description: Quality filtering tool for long reads. authors: - Michael Hall +input: + - reads: Path to input reads +output: + - Filtered reads, this must be the only file in the output file list +params: + - extra: Optional parameters + - target_bases: Remove the worst reads until only XXX Mbp remain From 6b82018485da9123c993e428ca97c7be83efdc02 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 090/191] [doc] (meta.yaml): bio/freebayes/meta.yaml updated --- bio/freebayes/meta.yaml | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/bio/freebayes/meta.yaml b/bio/freebayes/meta.yaml index a63a4ae0e77..574d977e377 100644 --- a/bio/freebayes/meta.yaml +++ b/bio/freebayes/meta.yaml @@ -1,17 +1,26 @@ name: "freebayes" +url: https://github.com/freebayes/freebayes description: Call small genomic variants with freebayes. authors: - Johannes Köster - Felix Mölder - Filipe G. Vieira input: - - SAM/BAM/CRAM file(s) - - reference genome + - samples: SAM/BAM/CRAM file(s) + - ref: reference genome + - regions: Optional BED regions output: - - VCF/VCF.gz/BCF file + - VCF/VCF.gz/BCF file, this must be the first file in the output file list +params: + - extra: Optional parameters + - chunkzise: The `chunkzise` param allows setting reference genome chunk size for parallelization (default 100000) + - uncompressed_bcf: The `uncompressed_bcf` param allows for uncompressed BCF output. + - normalize: The `normalize` param allows to use `bcftools norm` to normalize indels. notes: | - * The `extra` param allows for additional arguments for freebayes. - * The `uncompressed_bcf`param allows for uncompressed BCF output. - * The `normalize` param allows to use `bcftools norm` to normalize indels. - * The `chunkzise` param allows setting reference genome chunk size for parallelization (default: 100000) - * For more inforamtion see, https://github.com/freebayes/freebayes + If a region bed is provided in input, this wrapper uses more threads than the number of threads declared in the snakefile. + + For X threads expected: + + * X is used in freebayes + * 1 in bedtools intersect + * 2 in piped sed commands From d98c5b150a7598c4058097b60ba33d2aa6b3665e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 091/191] [doc] (meta.yaml): bio/gatk/applybqsr/meta.yaml updated --- bio/gatk/applybqsr/meta.yaml | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/bio/gatk/applybqsr/meta.yaml b/bio/gatk/applybqsr/meta.yaml index 48bc54cf381..996204cdee5 100644 --- a/bio/gatk/applybqsr/meta.yaml +++ b/bio/gatk/applybqsr/meta.yaml @@ -1,4 +1,5 @@ name: gatk ApplyBQSR +url: https://gatk.broadinstitute.org/hc/en-us/articles/360046222011-ApplyBQSR description: | Run gatk ApplyBQSR. authors: @@ -6,12 +7,11 @@ authors: - Johannes Köster - Jake VanCampen input: - - bam file - - fasta reference - - recalibration table for the bam + - bam: Path to bam file + - ref: Path to fasta-formatted reference genome + - recal_table: Path to recalibration table for the bam output: - - recalibrated bam file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments for ApplyBSQR. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360037055712-ApplyBQSR + - bam: recalibrated bam file +params: + - extra: The `extra` param allows for additional program arguments for ApplyBSQR. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). From c77b7a1e6b45af022c55af1c2f261e559bac871b Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:35 +0200 Subject: [PATCH 092/191] [doc] (meta.yaml): bio/gatk/applybqsrspark/meta.yaml updated --- bio/gatk/applybqsrspark/meta.yaml | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/bio/gatk/applybqsrspark/meta.yaml b/bio/gatk/applybqsrspark/meta.yaml index 01b3f4af0ca..d7e445eddd3 100644 --- a/bio/gatk/applybqsrspark/meta.yaml +++ b/bio/gatk/applybqsrspark/meta.yaml @@ -1,18 +1,18 @@ name: gatk ApplyBQSRSpark +url: https://gatk.broadinstitute.org/hc/en-us/articles/360057440431-ApplyBQSRSpark-BETA- description: | ApplyBQSRSpark: Apply base quality score recalibration on Spark; uses output of the BaseRecalibrator tool. authors: - Filipe G. Vieira input: - - bam file - - fasta reference - - recalibration table for the bam + - bam: Path to bam file + - ref: Path to fasta-formatted reference genome + - recal_table: Path to recalibration table for the bam output: - - recalibrated bam file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments for `applybqsrspark`. - * The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. - * The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. - * The `spark_extra` param allows for additional spark arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360057440431-ApplyBQSRSpark-BETA- + - bam: recalibrated bam file +params: + - extra: The `extra` param allows for additional program arguments for `applybqsrspark`. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - spark_runner: The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. + - spark_master: The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. + - spark_extra: The `spark_extra` param allows for additional spark arguments. From 95074c9fdac112a7926946735b726887ea4c7d57 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 093/191] [doc] (meta.yaml): bio/gatk/applyvqsr/meta.yaml updated --- bio/gatk/applyvqsr/meta.yaml | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/bio/gatk/applyvqsr/meta.yaml b/bio/gatk/applyvqsr/meta.yaml index c7f1837ab9a..dc7be606cb0 100644 --- a/bio/gatk/applyvqsr/meta.yaml +++ b/bio/gatk/applyvqsr/meta.yaml @@ -1,15 +1,15 @@ name: gatk ApplyVQSR +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037226332-ApplyVQSR description: | Run gatk ApplyVQSR. authors: - Brett Copeland input: - - VCF file - - Recalibration file - - Tranches file + - vcf: Path to VCF file + - recal: Path to recalibration file generated by the VariantRecalibrator tool. + - tranches: Tranches file, produced by the VariantRecalibrator tool. output: - - Variant QualityScore-Recalibrated VCF -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information, see https://gatk.broadinstitute.org/hc/en-us/articles/360037226332-ApplyVQSR + - vcf: Variant QualityScore-Recalibrated VCF +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From 86f88748deda087dfbb0cb239258c848aff5a5c4 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 094/191] [doc] (meta.yaml): bio/gatk/baserecalibrator/meta.yaml updated --- bio/gatk/baserecalibrator/meta.yaml | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/bio/gatk/baserecalibrator/meta.yaml b/bio/gatk/baserecalibrator/meta.yaml index 0014456df15..cafe3ec0db5 100644 --- a/bio/gatk/baserecalibrator/meta.yaml +++ b/bio/gatk/baserecalibrator/meta.yaml @@ -1,4 +1,5 @@ name: gatk BaseRecalibrator +url: https://software.broadinstitute.org/gatk/documentation/article?id=11050 description: | Run gatk BaseRecalibrator. authors: @@ -6,13 +7,11 @@ authors: - Johannes Köster - Jake VanCampen input: - - bam file - - fasta reference - - vcf.gz of known variants + - bam: Path to bam file + - ref: Path to fasta reference + - known: vcf.gz of known variants output: - - recalibration table for the bam -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 - + - recal_table: Path to recalibration table for the bam +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. + - extra: The `extra` param allows for additional program arguments. From 80fead7318fbb296badba2a0ef2a3f1c2bd5118a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 095/191] [doc] (meta.yaml): bio/gatk/baserecalibratorspark/meta.yaml updated --- bio/gatk/baserecalibratorspark/meta.yaml | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/bio/gatk/baserecalibratorspark/meta.yaml b/bio/gatk/baserecalibratorspark/meta.yaml index 96aa3e6e87e..eb5698c44fe 100644 --- a/bio/gatk/baserecalibratorspark/meta.yaml +++ b/bio/gatk/baserecalibratorspark/meta.yaml @@ -1,4 +1,5 @@ name: gatk BaseRecalibratorSpark +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036897372-BaseRecalibratorSpark-BETA- description: | Run gatk BaseRecalibratorSpark. authors: @@ -6,15 +7,14 @@ authors: - Johannes Köster - Jake VanCampen input: - - bam file - - fasta reference - - vcf.gz of known variants + - bam: Path to bam file + - ref: Path to fasta reference + - known: Path to vcf.gz of known variants output: - - recalibration table for the bam -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments for `baserecalibratorspark`. - * The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. - * The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. - * The `spark_extra` param allows for additional spark arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360036897372-BaseRecalibratorSpark-BETA- + - recal_table: Path to recalibration table for the bam +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments for `baserecalibratorspark`. + - spark_runner: The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. + - spark_master: The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. + - spark_extra: The `spark_extra` param allows for additional spark arguments. From cf28cad7e6811929016d6539682c20286c90a4e1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 096/191] [doc] (meta.yaml): bio/gatk/cleansam/meta.yaml updated --- bio/gatk/cleansam/meta.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/bio/gatk/cleansam/meta.yaml b/bio/gatk/cleansam/meta.yaml index 39f31d1d9e8..32ab3eb8fa6 100644 --- a/bio/gatk/cleansam/meta.yaml +++ b/bio/gatk/cleansam/meta.yaml @@ -1,13 +1,13 @@ name: gatk CleanSam +url: https://gatk.broadinstitute.org/hc/en-us/articles/360056970832-CleanSam-Picard- description: | Run gatk CleanSam authors: - Filipe G. Vieira input: - - SAM/BAM/CRAM file + - bam: SAM/BAM/CRAM file output: - - clean and validates SAM/BAM/CRAM file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360056970832-CleanSam-Picard- + - clean: clean and validates SAM/BAM/CRAM file +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments. From 6d2741bbe60d290e407d5e387db734b5803cfc84 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 097/191] [doc] (meta.yaml): bio/gatk/combinegvcfs/meta.yaml updated --- bio/gatk/combinegvcfs/meta.yaml | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/bio/gatk/combinegvcfs/meta.yaml b/bio/gatk/combinegvcfs/meta.yaml index 7efda34eff0..5713c5a8241 100644 --- a/bio/gatk/combinegvcfs/meta.yaml +++ b/bio/gatk/combinegvcfs/meta.yaml @@ -1,14 +1,15 @@ name: gatk CombineGVCFs +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037593911-CombineGVCFs description: | Run gatk CombineGVCFs. authors: - Johannes Köster - Jake VanCampen input: - - GVCF files of multiple samples + - gvcfs: GVCF files of multiple samples + - ref: Path to fasta formatted reference genome output: - - Combined GVCF -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 + - gvcf: Combined GVCF +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From 6833fcd7b2777e24f3ef47cc72d76b5d5936fede Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 098/191] [doc] (meta.yaml): bio/gatk/estimatelibrarycomplexity/meta.yaml updated --- bio/gatk/estimatelibrarycomplexity/meta.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/bio/gatk/estimatelibrarycomplexity/meta.yaml b/bio/gatk/estimatelibrarycomplexity/meta.yaml index 9aca33b2e53..f21276c924a 100644 --- a/bio/gatk/estimatelibrarycomplexity/meta.yaml +++ b/bio/gatk/estimatelibrarycomplexity/meta.yaml @@ -1,13 +1,13 @@ name: gatk EstimateLibraryComplexity +url: https://gatk.broadinstitute.org/hc/en-us/articles/360057438451-EstimateLibraryComplexity-Picard- description: | Run gatk EstimateLibraryComplexity authors: - Filipe G. Vieira input: - - SAM/BAM/CRAM file + - SAM/BAM/CRAM file. This must be the only input file provided. output: - - metrics file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360057438451-EstimateLibraryComplexity-Picard- + - metrics: Path to metrics file +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments. From 1a0b420cb1052b0b603ed37eeb3729e0d25bd760 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 099/191] [doc] (meta.yaml): bio/gatk/filtermutectcalls/meta.yaml updated --- bio/gatk/filtermutectcalls/meta.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/bio/gatk/filtermutectcalls/meta.yaml b/bio/gatk/filtermutectcalls/meta.yaml index b564c195992..4f836d9f73e 100644 --- a/bio/gatk/filtermutectcalls/meta.yaml +++ b/bio/gatk/filtermutectcalls/meta.yaml @@ -1,14 +1,14 @@ name: gatk FilterMutectCalls +url: https://gatk.broadinstitute.org/hc/en-us/articles/360042476952-FilterMutectCalls description: | Run gatk FilterMutectCalls. authors: - Patrik Smeds input: - - vcf file - - reference genome + - vcf: Path to vcf file + - ref: Path to reference genome output: - - filtered vcf file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 + - vcf: filtered vcf file +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments. From d6e1e5281aedd2ec9f0c43f60b1122f843c556c0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 100/191] [doc] (meta.yaml): bio/gatk/genomicsdbimport/meta.yaml updated --- bio/gatk/genomicsdbimport/meta.yaml | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/bio/gatk/genomicsdbimport/meta.yaml b/bio/gatk/genomicsdbimport/meta.yaml index 21be9dd1f56..e9b90e7ef83 100644 --- a/bio/gatk/genomicsdbimport/meta.yaml +++ b/bio/gatk/genomicsdbimport/meta.yaml @@ -1,15 +1,18 @@ name: gatk GenomicsDBImport +url: https://gatk.broadinstitute.org/hc/en-us/articles/360051305591-GenomicsDBImport description: | Run gatk GenomicsDBImport. authors: - Filipe G. Vieira input: - - GVCF files of multiple samples + - gvcf: Path to GVCF files of multiple samples output: - - A GenomicsDB workspace + - db: A GenomicsDB workspace +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments. + - db_action: Either ``create`` or ``update`` + - intervals: One or more genomic intervals over which to operate notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `intervals` param is mandatory + * At least one interval must be provided. * By default, the wrapper will create a new database (output directory must be empty or non-existent). If you want to update an existing DB, set `db_action` param to `update`. - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360051305591-GenomicsDBImport From a15e94eebfa4ed2fad5b5426cbc57f376aeeec32 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 101/191] [doc] (meta.yaml): bio/gatk/genotypegvcfs/meta.yaml updated --- bio/gatk/genotypegvcfs/meta.yaml | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/bio/gatk/genotypegvcfs/meta.yaml b/bio/gatk/genotypegvcfs/meta.yaml index 5ae8b8d4ef2..8536ae69c06 100644 --- a/bio/gatk/genotypegvcfs/meta.yaml +++ b/bio/gatk/genotypegvcfs/meta.yaml @@ -1,14 +1,18 @@ name: gatk GenotypeGVCFs +url: https://gatk.broadinstitute.org/hc/en-us/articles/360041417092-GenotypeGVCFs description: | Run gatk GenotypeGVCFs. authors: - Johannes Köster - Jake VanCampen input: - - GVCF files + - gvcf: Path to GVCF files (ignore if ``genomicsdb`` is provided) + - known: Path to known variants (vcf.gz) + - interval_file: List of intervals over which to operate + - genomicsdb: Path/url to genomics database (ignore if ``gvcf`` is provided) + - ref: Path to fasta formatted genome sequence output: - - VCF file with genotypes -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 + - vcf: VCF file with genotypes +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From 7cc0c902ea2e0fa6bb8873951bfec768bc73b57a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 102/191] [doc] (meta.yaml): bio/gatk/haplotypecaller/meta.yaml updated --- bio/gatk/haplotypecaller/meta.yaml | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/bio/gatk/haplotypecaller/meta.yaml b/bio/gatk/haplotypecaller/meta.yaml index b550dde6544..569a9864332 100644 --- a/bio/gatk/haplotypecaller/meta.yaml +++ b/bio/gatk/haplotypecaller/meta.yaml @@ -1,15 +1,17 @@ name: gatk HaplotypeCaller +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037225632-HaplotypeCaller description: | Run gatk HaplotypeCaller. authors: - Johannes Köster - Jake VanCampen input: - - bam file + - bam: Path to bam file(s) + - ref: Path to fasta-formatted reference genome + - known: Path to known variants output: - - GVCF file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 - + - gvcf: Path to GVCF file + - bam: Path to output bam(s) +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. + - extra: The `extra` param allows for additional program arguments. From b8ae7ac68e5c8e9986e7e636fbb29eadabcb10b1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 103/191] [doc] (meta.yaml): bio/gatk/intervallisttobed/meta.yaml updated --- bio/gatk/intervallisttobed/meta.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/bio/gatk/intervallisttobed/meta.yaml b/bio/gatk/intervallisttobed/meta.yaml index 6b476a541dd..c9113dbd0d6 100644 --- a/bio/gatk/intervallisttobed/meta.yaml +++ b/bio/gatk/intervallisttobed/meta.yaml @@ -1,13 +1,13 @@ name: gatk IntervalListToBed +url: https://gatk.broadinstitute.org/hc/en-us/articles/360050815192-IntervalListToBed-Picard- description: | Run gatk IntervalListToBed. authors: - Filipe G. Vieira input: - - interval list + - intervals: Path to interval list output: - - bed file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360050815192-IntervalListToBed-Picard- + - bed: Path to interval file +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). From b6fa5168c5c83adddcfdb4996c8874c497d3e927 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 104/191] [doc] (meta.yaml): bio/gatk/markduplicatesspark/meta.yaml updated --- bio/gatk/markduplicatesspark/meta.yaml | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/bio/gatk/markduplicatesspark/meta.yaml b/bio/gatk/markduplicatesspark/meta.yaml index 09ba292fa43..b14fc8925aa 100644 --- a/bio/gatk/markduplicatesspark/meta.yaml +++ b/bio/gatk/markduplicatesspark/meta.yaml @@ -1,17 +1,17 @@ name: GATK MarkDuplicatesSpark +url: https://gatk.broadinstitute.org/hc/en-us/articles/360050814112-MarkDuplicatesSpark description: | Spark implementation of Picard MarkDuplicates that allows the tool to be run in parallel on multiple cores on a local machine or multiple machines on a Spark cluster while still matching the output of the non-Spark Picard version of the tool. Since the tool requires holding all of the readnames in memory while it groups read information, machine configuration and starting sort-order impact tool performance. authors: - Filipe G. Vieira input: - - bam file - - reference file + - Path to bam file, this must be the only input element in the input file list output: - - bam file with marked or removed duplicates -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments for markduplicatesspark. - * The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. - * The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. - * The `spark_extra` param allows for additional spark arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360050814112-MarkDuplicatesSpark + - bam: Path to bam file with marked or removed duplicates + - metrics: Optional metrics file +params: + - extra: The `extra` param allows for additional program arguments for markduplicatesspark. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. + - spark_runner: The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. + - spark_master: The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. + - spark_extra: The `spark_extra` param allows for additional spark arguments. From 9a30eeef04514987c1e15c27d8036a3866de375e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 105/191] [doc] (meta.yaml): bio/gatk/mutect/meta.yaml updated --- bio/gatk/mutect/meta.yaml | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/bio/gatk/mutect/meta.yaml b/bio/gatk/mutect/meta.yaml index 3b3655e884a..96dfcb338bb 100644 --- a/bio/gatk/mutect/meta.yaml +++ b/bio/gatk/mutect/meta.yaml @@ -1,9 +1,14 @@ name: GATK Mutect2 +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037593851-Mutect2 description: Call somatic SNVs and indels via local assembly of haplotypes authors: - Thibault Dayris input: - - Mapped reads (SAM/BAM/CRAM) - - Reference Fasta file + - map: Mapped reads (SAM/BAM/CRAM) + - fasta: Reference Fasta file output: - - Variant file + - vcf: Variant file + - bam: Optional output bam file +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). From 84aad6a718a9d5800f160aba7267e9076268ed64 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 106/191] [doc] (meta.yaml): bio/gatk/printreadsspark/meta.yaml updated --- bio/gatk/printreadsspark/meta.yaml | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/bio/gatk/printreadsspark/meta.yaml b/bio/gatk/printreadsspark/meta.yaml index 0e09b3b2c07..10e281a2a98 100644 --- a/bio/gatk/printreadsspark/meta.yaml +++ b/bio/gatk/printreadsspark/meta.yaml @@ -1,18 +1,17 @@ name: gatk PrintReadsSpark +url: https://gatk.broadinstitute.org/hc/en-us/articles/360057441531-PrintReadsSpark description: | Write reads from SAM format file (SAM/BAM/CRAM) that pass specified criteria to a new file. This is the version that can be run on Spark. authors: - Filipe G. Vieira input: - - bam file - - reference file - - reference dict + - bam: Path to bam file + - ref: Path to reference file (fasta) output: - - filtered bam file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments for `printreadsspark`. - * The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. - * The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. - * The `spark_extra` param allows for additional spark arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360057441531-PrintReadsSpark + - bam: filtered bam file +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). + - extra: The `extra` param allows for additional program arguments for `printreadsspark`. + - spark_runner: The `spark_runner` param = "LOCAL"|"SPARK"|"GCS" allows to set the spark_runner. Set the parameter to "LOCAL" or don't set it at all to run on local machine. + - spark_master: The `spark_master` param allows to set the URL of the Spark Master to submit the job. Set to "local[number_of_cores]" for local execution. Don't set it at all for local execution with number of cores determined by snakemake. + - spark_extra: The `spark_extra` param allows for additional spark arguments. From 9071cfbe277ce1a1f6cf0d3a322db5b0fa06683e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 107/191] [doc] (meta.yaml): bio/gatk/scatterintervalsbyns/meta.yaml updated --- bio/gatk/scatterintervalsbyns/meta.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/bio/gatk/scatterintervalsbyns/meta.yaml b/bio/gatk/scatterintervalsbyns/meta.yaml index 4d6eaabffbb..f07e392f68e 100644 --- a/bio/gatk/scatterintervalsbyns/meta.yaml +++ b/bio/gatk/scatterintervalsbyns/meta.yaml @@ -1,13 +1,13 @@ name: gatk ScatterIntervalsByNs +url: https://gatk.broadinstitute.org/hc/en-us/articles/360057440251-ScatterIntervalsByNs-Picard- description: | Run gatk ScatterIntervalsByNs. authors: - Filipe G. Vieira input: - - reference genome + - ref: Path to reference genome output: - - interval list -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360057440251-ScatterIntervalsByNs-Picard- + - intervals: Output interval list +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). From 5cd8dbb37cee0f04729b0ffd3159e5b3965a9f98 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 108/191] [doc] (meta.yaml): bio/gatk/selectvariants/meta.yaml updated --- bio/gatk/selectvariants/meta.yaml | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/bio/gatk/selectvariants/meta.yaml b/bio/gatk/selectvariants/meta.yaml index 6732f401328..171fd813a30 100644 --- a/bio/gatk/selectvariants/meta.yaml +++ b/bio/gatk/selectvariants/meta.yaml @@ -1,16 +1,15 @@ name: gatk SelectVariants +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036362532-SelectVariants description: | Run gatk SelectVariants. authors: - Johannes Köster - Jake VanCampen input: - - vcf file - - reference genome + - vcf: Path to vcf file + - ref: Path to reference genome output: - - filtered vcf file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 - + - vcf: Path to filtered vcf file +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From e0881b247806755d1c02aa2c9040ba63ebda2d0a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 109/191] [doc] (meta.yaml): bio/gatk/splitncigarreads/meta.yaml updated --- bio/gatk/splitncigarreads/meta.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/bio/gatk/splitncigarreads/meta.yaml b/bio/gatk/splitncigarreads/meta.yaml index 2e0dc736a9c..7ffeec7f579 100644 --- a/bio/gatk/splitncigarreads/meta.yaml +++ b/bio/gatk/splitncigarreads/meta.yaml @@ -1,14 +1,14 @@ name: gatk SplitNCigarReads +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036858811-SplitNCigarReads description: | Run gatk SplitNCigarReads. authors: - Jan Forster input: - - bam file + - bam: Path to in bam file + - ref: Path to reference genome output: - - split bam file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 - + - split bam file. This must be the only output file path +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. + - extra: The `extra` param allows for additional program arguments. From b738e8a269c44dcac9c84b4333f158ac9a3ba6cd Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 110/191] [doc] (meta.yaml): bio/gatk/varianteval/meta.yaml updated --- bio/gatk/varianteval/meta.yaml | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/bio/gatk/varianteval/meta.yaml b/bio/gatk/varianteval/meta.yaml index 3ec4e1c116f..45441b652e1 100644 --- a/bio/gatk/varianteval/meta.yaml +++ b/bio/gatk/varianteval/meta.yaml @@ -1,18 +1,19 @@ name: gatk VariantEval +url: https://gatk.broadinstitute.org/hc/en-us/articles/360056967892-VariantEval-BETA- description: | Run gatk VariantEval. authors: - Filipe G. Vieira input: - - vcf files - - BAM/CRAM files (optional) - - reference genome (optional) - - reference dictionary (optional) - - vcf.gz of known variants (optional) - - PED (pedigree) file (optional) + - vcf: Path to input vcf files + - bam: Path to BAM/CRAM files (optional) + - ref: Path to reference genome (optional) + - dict: Path to reference dictionary (optional) + - known: Path to vcf.gz of known variants (optional) + - ped: Path to PED (pedigree) file (optional) + - comp: Path to comparison file (optional) output: - - Evaluation tables detailing the results of the eval modules on VCF file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://gatk.broadinstitute.org/hc/en-us/articles/360056967892-VariantEval-BETA- + - Evaluation tables detailing the results of the eval modules on VCF file. This must be the first element of the output file list. +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). From fd4bdbe977db083597c020b7b1f47ac4949ee30f Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 111/191] [doc] (meta.yaml): bio/gatk/variantfiltration/meta.yaml updated --- bio/gatk/variantfiltration/meta.yaml | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/bio/gatk/variantfiltration/meta.yaml b/bio/gatk/variantfiltration/meta.yaml index 490b1eff3de..fc957560c47 100644 --- a/bio/gatk/variantfiltration/meta.yaml +++ b/bio/gatk/variantfiltration/meta.yaml @@ -1,15 +1,15 @@ name: gatk VariantFiltration +url: https://gatk.broadinstitute.org/hc/en-us/articles/360041850471-VariantFiltration description: | Run gatk VariantFiltration. authors: - Johannes Köster - Jake VanCampen input: - - vcf file - - reference genome + - vcf: Path to vcf file + - ref: Path to reference genome output: - - filtered vcf file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 + - vcf: Path to the filtered vcf file +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From e5b15fcc4790734b94b0404aeaaec0143363d754 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 112/191] [doc] (meta.yaml): bio/gatk/variantrecalibrator/meta.yaml updated --- bio/gatk/variantrecalibrator/meta.yaml | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/bio/gatk/variantrecalibrator/meta.yaml b/bio/gatk/variantrecalibrator/meta.yaml index 4a423d14960..4fd53f7b81e 100644 --- a/bio/gatk/variantrecalibrator/meta.yaml +++ b/bio/gatk/variantrecalibrator/meta.yaml @@ -1,15 +1,19 @@ name: gatk VariantRecalibrator +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036351392-VariantRecalibrator description: | Run gatk VariantRecalibrator. authors: - Johannes Köster - - Jake VanCampen + - Jake VanCampen input: - - VCF file + - vcf: Path to VCF file + - ref: Path to reference genome output: - - .recal file - - .tranches file -notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 + - vcf: Path to .recal file + - tranches: Path to .tranches file +params: + - annotation: The names of the annotations in INFO fields which should used for calculations + - mode: Recalibration mode to employ. One of ``SNP``, ``INDEL``, or ``BOTH``. + - resources: A list of sites for which to apply a prior probability of being correct + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. From a2edad1b4b3142fda5cbd2bef02542908930303d Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 113/191] [doc] (meta.yaml): bio/gatk3/baserecalibrator/meta.yaml updated --- bio/gatk3/baserecalibrator/meta.yaml | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/bio/gatk3/baserecalibrator/meta.yaml b/bio/gatk3/baserecalibrator/meta.yaml index 9e3f5926c7d..57dec061984 100644 --- a/bio/gatk3/baserecalibrator/meta.yaml +++ b/bio/gatk3/baserecalibrator/meta.yaml @@ -1,16 +1,17 @@ name: gatk3 BaseRecalibrator +url: https://gatk.broadinstitute.org/hc/en-us/articles/360035890531-Base-Quality-Score-Recalibration-BQSR- description: | Run gatk3 BaseRecalibrator. authors: - Patrik Smeds input: - - bam file - - vcf files - - reference genome + - bam: Path to bam file + - known: Path to vcf.gz known variants + - ref: Path to reference genome output: - - recalibration table + - Recalibration table. This must be the only output. +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. + - extra: The `extra` param allows for additional program arguments. notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 * Gatk3.jar is not included in the bioconda package, i.e it need to be added to the conda environment manually. From 65ca83e463c3581ddbd117de485e3774d9d35800 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 114/191] [doc] (meta.yaml): bio/gatk3/indelrealigner/meta.yaml updated --- bio/gatk3/indelrealigner/meta.yaml | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/bio/gatk3/indelrealigner/meta.yaml b/bio/gatk3/indelrealigner/meta.yaml index 678730262f6..e3ab10eeb46 100644 --- a/bio/gatk3/indelrealigner/meta.yaml +++ b/bio/gatk3/indelrealigner/meta.yaml @@ -1,21 +1,21 @@ name: gatk3 IndelRealigner +url: https://github.com/broadinstitute/gatk-docs/blob/master/gatk3-tutorials/(howto)_Perform_local_realignment_around_indels.md description: | Run gatk3 IndelRealigner authors: - Patrik Smeds - Filipe G. Vieira input: - - bam file - - reference genome - - target intervals to realign - - bed file (optional) - - vcf files known variation (optional) + - bam: Path to bam file + - ref: Path to reference genome + - target_intervals: target intervals to realign + - bed: Path to Bed intervals (optional) + - known: vcf files known variation (optional) output: - - indel realigned bam file - - indel realigned bai file (optional) - - temp dir (optional) + - bam: indel realigned bam file + - bai: indel realigned bai file (optional) +params: + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (memory is automatically inferred from `resources` and temp dir from `output.java_temp`. + - extra: The `extra` param allows for additional program arguments. notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (memory is automatically inferred from `resources` and temp dir from `output.java_temp`. - * The `extra` param allows for additional program arguments. - * For more information see, https://github.com/broadinstitute/gatk-docs/blob/master/gatk3-tutorials/(howto)_Perform_local_realignment_around_indels.md * Gatk3.jar is not included in the bioconda package, i.e it need to be added to the conda environment manually. From a31f728d4d3fff658e83d2f07711795c3369b015 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 115/191] [doc] (meta.yaml): bio/gatk3/printreads/meta.yaml updated --- bio/gatk3/printreads/meta.yaml | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/bio/gatk3/printreads/meta.yaml b/bio/gatk3/printreads/meta.yaml index fc72d2587c3..50e69b3539c 100644 --- a/bio/gatk3/printreads/meta.yaml +++ b/bio/gatk3/printreads/meta.yaml @@ -1,16 +1,17 @@ name: gatk3 PrintReads +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036897512-PrintReads description: | Run gatk3 PrintReads authors: - Patrik Smeds input: - - bam file - - recalibration table - - reference genome + - bam: Path to bam file + - recal_data: Path to BQSR recalibration table + - ref: Path to reference genome output: - - bam file + - Path to bam file, this must be the only output file. +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-Xmx4G" for one, and "-Xmx4G -XX:ParallelGCThreads=10" for two options. - * The `extra` param allows for additional program arguments. - * For more information see, https://software.broadinstitute.org/gatk/documentation/article?id=11050 * Gatk3.jar is not included in the bioconda package, i.e it need to be added to the conda environment manually. From ddf6fe1be4d07365f253f877bbae8e94415a7c9e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 116/191] [doc] (meta.yaml): bio/gatk3/realignertargetcreator/meta.yaml updated --- bio/gatk3/realignertargetcreator/meta.yaml | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/bio/gatk3/realignertargetcreator/meta.yaml b/bio/gatk3/realignertargetcreator/meta.yaml index 7a42a823706..b6b004f709a 100644 --- a/bio/gatk3/realignertargetcreator/meta.yaml +++ b/bio/gatk3/realignertargetcreator/meta.yaml @@ -1,19 +1,19 @@ name: gatk3 RealignerTargetCreator +url: https://github.com/broadinstitute/gatk-docs/blob/master/gatk3-tutorials/(howto)_Perform_local_realignment_around_indels.md description: | Run gatk3 RealignerTargetCreator authors: - Patrik Smeds - Filipe G. Vieira input: - - bam file - - reference genome - - bed file (optional) - - vcf files known variation (optional) + - bam: Path to bam file + - ref: Path to reference genome + - bed: Path to bed intervals (optional) + - known: Path to vcf.gz files known variation (optional) output: - - target intervals - - temp dir (optional) + - intervals: Path to output target intervals +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (memory is automatically inferred from `resources` and temp dir from `output.java_temp`. notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (memory is automatically inferred from `resources` and temp dir from `output.java_temp`. - * The `extra` param allows for additional program arguments. - * For more information see, https://github.com/broadinstitute/gatk-docs/blob/master/gatk3-tutorials/(howto)_Perform_local_realignment_around_indels.md * Gatk3.jar is not included in the bioconda package, i.e it need to be added to the conda environment manually. From a058667437fe49b6dcfb80e72c0f31e0b4d28798 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 117/191] [doc] (meta.yaml): bio/gdc-api/bam-slicing/meta.yaml updated --- bio/gdc-api/bam-slicing/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/gdc-api/bam-slicing/meta.yaml b/bio/gdc-api/bam-slicing/meta.yaml index 3a4ae65d9d8..8cb1f21d2fb 100644 --- a/bio/gdc-api/bam-slicing/meta.yaml +++ b/bio/gdc-api/bam-slicing/meta.yaml @@ -1,7 +1,15 @@ name: "GDC API-based data download of BAM slices" +url: https://docs.gdc.cancer.gov/API/Users_Guide/BAM_Slicing/ description: Download slices of GDC BAM files using `curl `_ and the `GDC API for BAM Slicing `_. authors: - David Lähnemann +output: + - bam: Path to output bam file +params: + - uuid: provide a GDC UUID + - gdc_token: GDC data access token + - slices: Region slice, see notes below for more information + - extra: Optional parameters notes: | - BAM file UUIDs can be found via the `GDC repository query `_, either by clicking on individual files or systematically by creating a cart and downloading a manifest file. - Slicing can be performed using `region syntax like 'region=chr20:3000-4000' `_, `gene name syntax like 'gencode=BRCA2' `_ (this uses `Gene symbols of GENCODE v22 `_) or `'region=unmapped' to get unmapped reads `_. Multiple such entries can be joined with ampersands (e.g. ``region=chr5:200-300®ion=unmapped&gencode=BRCA1``). From 4f645f294255c4fb93634044badf25426a8acc82 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 118/191] [doc] (meta.yaml): bio/gdc-client/download/meta.yaml updated --- bio/gdc-client/download/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/gdc-client/download/meta.yaml b/bio/gdc-client/download/meta.yaml index 1cdb03fae4d..d9830fb2d4f 100644 --- a/bio/gdc-client/download/meta.yaml +++ b/bio/gdc-client/download/meta.yaml @@ -1,4 +1,11 @@ name: "GDC Data Transfer Tool data download" +url: https://docs.gdc.cancer.gov/Data_Transfer_Tool/Users_Guide/Data_Download_and_Upload/ description: Download GDC data files with the gdc-client. authors: - David Lähnemann +output: + - Downloaded file +params: + - extra: Optional parameters + - gdc_token: GDC data access token + - uuid: GDC UUID From 7a2b9f392c6ab9ad8acc40cf5c597fa0005726c0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 119/191] [doc] (meta.yaml): bio/genomepy/meta.yaml updated --- bio/genomepy/meta.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/bio/genomepy/meta.yaml b/bio/genomepy/meta.yaml index 1a26750cd5b..4b17b94577d 100644 --- a/bio/genomepy/meta.yaml +++ b/bio/genomepy/meta.yaml @@ -1,12 +1,12 @@ name: genomepy +url: https://github.com/vanheeringen-lab/genomepy authors: - Maarten van der Sande description: | - Download genomes the easy way: - https://github.com/vanheeringen-lab/genomepy + Download genomes the easy way output: | Always outputs {assembly}/{assembly}.fa, {assembly}/{assembly}.fa.fai, {assembly}/{assembly}.gaps.bed and {assembly}/{assembly}.fa.sizes. - Can output annotation: {assembly}/{assembly}.annotation.gtf or blacklist: {assembly}/{assembly}.blacklist.bed, depending on the assembly, + Can output ``annotation``: {assembly}/{assembly}.annotation.gtf or ``blacklist``: {assembly}/{assembly}.blacklist.bed, depending on the assembly, and whether or not it is specified as output. params: - provider: which provider to download from, defaults to UCSC (choose from UCSC, Ensembl, NCBI). From 8419572eba383d9de3672492fa8e629af88f5cb0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 120/191] [doc] (meta.yaml): bio/gridss/assemble/meta.yaml updated --- bio/gridss/assemble/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/gridss/assemble/meta.yaml b/bio/gridss/assemble/meta.yaml index 6c88e93ea86..0c7f42d3c6f 100644 --- a/bio/gridss/assemble/meta.yaml +++ b/bio/gridss/assemble/meta.yaml @@ -1,8 +1,16 @@ name: "gridss assemble" +url: https://github.com/PapenfussLab/gridss description: > GRIDSS is a module software suite containing tools useful for the detection of genomic rearrangements. It includes a genome-wide break-end assembler, as well as a structural variation caller for Illumina sequencing data. ``assemble`` performs GRIDSS breakend assembly. - Documentation at: https://github.com/PapenfussLab/gridss authors: - Christopher Schröder +input: + - bams: path to mapped bam files + - reference: Path to indexed reference genome all "``.amb``", "``.ann``", "``.bwt``", "``.pac``", "``.sa``", "``.dict``" files are expected +output: + - assembly: Path to output assembly +params: + - workingdir: Path to working directory + - extra: Optional parameters From 15707677a0ca9fe2a29c55a6dba493f377c0fdb3 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 121/191] [doc] (meta.yaml): bio/gridss/call/meta.yaml updated --- bio/gridss/call/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/gridss/call/meta.yaml b/bio/gridss/call/meta.yaml index 624c4fbe499..b616e4d3745 100644 --- a/bio/gridss/call/meta.yaml +++ b/bio/gridss/call/meta.yaml @@ -1,8 +1,17 @@ name: "gridss call" +url: https://github.com/PapenfussLab/gridss description: > GRIDSS is a module software suite containing tools useful for the detection of genomic rearrangements. It includes a genome-wide break-end assembler, as well as a structural variation caller for Illumina sequencing data. ``call`` performs variant calling. - Documentation at: https://github.com/PapenfussLab/gridss authors: - Christopher Schröder +input: + - assembly: Path to output assembly + - reference: Path to indexed reference genome all "``.amb``", "``.ann``", "``.bwt``", "``.pac``", "``.sa``" files are expected + - dictionary: Path to sequence disctionnary +output: + - vcf: Assembly VCF +params: + - workingdir: Path to working directory + - extra: Optional parameters From 8d2916c0b381619c81b3494ecd36698322a7a5a7 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 122/191] [doc] (meta.yaml): bio/gridss/preprocess/meta.yaml updated --- bio/gridss/preprocess/meta.yaml | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/bio/gridss/preprocess/meta.yaml b/bio/gridss/preprocess/meta.yaml index 4b79f50ee7f..8fcccc62c60 100644 --- a/bio/gridss/preprocess/meta.yaml +++ b/bio/gridss/preprocess/meta.yaml @@ -1,9 +1,20 @@ name: "gridss preprocess" +url: https://github.com/PapenfussLab/gridss description: > GRIDSS is a module software suite containing tools useful for the detection of genomic rearrangements. It includes a genome-wide break-end assembler, as well as a structural variation caller for Illumina sequencing data. ``preprocess`` pre-processes input BAM files. Can be run per input file. - Documentation at: https://github.com/PapenfussLab/gridss authors: - Christopher Schröder +input: + - reference: Path to indexed reference genome all "``.amb``", "``.ann``", "``.bwt``", "``.pac``", "``.sa``" files are expected + - dictionary: Path to sequence disctionnary + - bam: Path to bam file +output: + - Multiple metrics files + - Bam file, with its bai index + - Insert size histogram +params: + - workingdir: Path to working directory + - extra: Optional parameters From 2dd6bcc9d716590e959a8f13215805901e7d7343 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 123/191] [doc] (meta.yaml): bio/gridss/setupreference/meta.yaml updated --- bio/gridss/setupreference/meta.yaml | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/bio/gridss/setupreference/meta.yaml b/bio/gridss/setupreference/meta.yaml index 116ec9816a5..c128b3b78a0 100644 --- a/bio/gridss/setupreference/meta.yaml +++ b/bio/gridss/setupreference/meta.yaml @@ -1,10 +1,18 @@ name: "gridss setupreference" +url: https://github.com/PapenfussLab/gridss description: > GRIDSS is a module software suite containing tools useful for the detection of genomic rearrangements. It includes a genome-wide break-end assembler, as well as a structural variation caller for Illumina sequencing data. ``setupreference`` is a once-off setup generating additional files in the same directory as the reference. - WARNING multiple instances of GRIDSS attempting to perform setupreference at the same time will result in file corruption. - Make sure these files are generated before running parallel GRIDSS jobs. - Documentation at: https://github.com/PapenfussLab/gridss authors: - Christopher Schröder +input: + - reference: Path to indexed reference genome all "``.amb``", "``.ann``", "``.bwt``", "``.pac``", "``.sa``" files are expected +ouptut: + - reference image and cache +params: + - extra: Optional parameters +notes: | + WARNING multiple instances of GRIDSS attempting to perform setupreference at the same time will result in file corruption. + + Make sure these files are generated before running parallel GRIDSS jobs. From 00f131938335da69bbffddbcdc147db0fe291c6c Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 124/191] [doc] (meta.yaml): bio/hap.py/hap.py/meta.yaml updated --- bio/hap.py/hap.py/meta.yaml | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/bio/hap.py/hap.py/meta.yaml b/bio/hap.py/hap.py/meta.yaml index f937f7b667c..f0224c4002a 100644 --- a/bio/hap.py/hap.py/meta.yaml +++ b/bio/hap.py/hap.py/meta.yaml @@ -1,4 +1,20 @@ name: "hap.py" -description: Comparison of vcf files and calculating performance metrics following GA4GH defined best practices for benchmarking small variant call sets (Krusche, P. et al. 2019, https://doi.org/10.1038/s41587-019-0054-x). Part of the hap.py suite by Illumina (see https://github.com/Illumina/hap.py/blob/master/doc/normalisation.md). +url: https://github.com/Illumina/hap.py/ +description: Comparison of vcf files and calculating performance metrics following GA4GH defined best practices for benchmarking small variant call sets authors: - Nathan D. Olson +params: + - extra: Optional parameters + - engine: One of ``xcmp`` (default), ``Rtgtools vcfeval``, ``scmp-distancebased``, or ``scmp-somatic``. + - prefix: Output prefix +input: + - truth_regions: Path to VCF containing high confidence variants + - strats: Path to BED stratification file, see `official documentation on stratification `_ for more information. + - genome: Path to reference genome + - query: Path to the VCF that is to be compared and annotated. +output: + - Multiple filtered files. See `the output file list `_ on the official documentation. +notes: | + Krusche, P. et al. 2019, https://doi.org/10.1038/s41587-019-0054-x. + + Part of the `hap.py suite by Illumina `_. From d7eb239c686e7f7f2c76c6c0f29f226bd96de1eb Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 125/191] [doc] (meta.yaml): bio/hap.py/pre.py/meta.yaml updated --- bio/hap.py/pre.py/meta.yaml | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/bio/hap.py/pre.py/meta.yaml b/bio/hap.py/pre.py/meta.yaml index 2986214067d..083be004b3f 100644 --- a/bio/hap.py/pre.py/meta.yaml +++ b/bio/hap.py/pre.py/meta.yaml @@ -1,4 +1,14 @@ name: "pre.py" -description: Preprocessing/normalisation of vcf/bcf files. Part of the hap.py suite by Illumina (see https://github.com/Illumina/hap.py/blob/master/doc/normalisation.md). +url: https://github.com/Illumina/hap.py/ +description: Preprocessing/normalisation of vcf/bcf files. authors: - Jan Forster +input: + - variants: Path to VCF file +output: + - Path to normalized VCF file, this must be the only output file in the output file list +params: + - genome: path to reference genome (fasta) + - extra: Optional parameters +notes: | + Part of the `hap.py suite by Illumina `_. From eb611395e61ab136c2a9740d290528d4f6abc890 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 126/191] [doc] (meta.yaml): bio/hisat2/align/meta.yaml updated --- bio/hisat2/align/meta.yaml | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/bio/hisat2/align/meta.yaml b/bio/hisat2/align/meta.yaml index 7cd1033df57..85d06f76ba4 100644 --- a/bio/hisat2/align/meta.yaml +++ b/bio/hisat2/align/meta.yaml @@ -1,4 +1,5 @@ name: hisat2 align +url: https://daehwankimlab.github.io/hisat2/ authors: - Wibowo Arindrarto description: | @@ -6,7 +7,7 @@ description: | input: - reads: either 1 or 2 FASTQ files with reads output: - - bam file with mapped reads + - bam file with mapped reads. This must be the first output element in the output file list. params: - idx: prefix of index file path (required) - extra: additional parameters @@ -20,3 +21,5 @@ notes: | may differ depending on the reference sequence size. This is also why the index is supplied in the `params` directive instead of the `input` directive. + + Warning, this pipeline uses more threads than the number set in the snakemake rule. For X threads written, X+1 are used: X for hisat2, 1 for samtools view. From 38cf586c91f98f4e8204e7c7920f859eec267526 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 127/191] [doc] (meta.yaml): bio/hisat2/index/meta.yaml updated --- bio/hisat2/index/meta.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/bio/hisat2/index/meta.yaml b/bio/hisat2/index/meta.yaml index 16e0dfc21c1..0102780c287 100644 --- a/bio/hisat2/index/meta.yaml +++ b/bio/hisat2/index/meta.yaml @@ -1,4 +1,5 @@ name: hisat2 index +url: https://daehwankimlab.github.io/hisat2/ authors: - Joël Simoneau description: | From cdf6691abedf13bbdf5eff28ebaacc9f21a3b06a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 128/191] [doc] (meta.yaml): bio/hmmer/hmmbuild/meta.yaml updated --- bio/hmmer/hmmbuild/meta.yaml | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/bio/hmmer/hmmbuild/meta.yaml b/bio/hmmer/hmmbuild/meta.yaml index 377d4057c91..fcfc8115995 100644 --- a/bio/hmmer/hmmbuild/meta.yaml +++ b/bio/hmmer/hmmbuild/meta.yaml @@ -1,10 +1,13 @@ name: hmmbuild -description: "hmmbuild: construct profile HMM(s) from multiple sequence alignment(s)" +url: http://hmmer.org/ +description: "hmmbuild: construct profile HMM(s) from multiple sequence alignment(s)" authors: - N Tessa Pierce input: - - sequence alignment file + - sequence alignment file. This must be the only element of the input file list. output: - - profile hmm -citations: - - "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" + - profile hmm. This must be the only element of the output file list +params: + - extra: Optional parameters +notes: | + "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" From 14ea957a0ca19e7678d0f91bf4d702e8a8d417dc Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 129/191] [doc] (meta.yaml): bio/hmmer/hmmpress/meta.yaml updated --- bio/hmmer/hmmpress/meta.yaml | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/bio/hmmer/hmmpress/meta.yaml b/bio/hmmer/hmmpress/meta.yaml index 0904cc154d6..fec5de6bcf9 100644 --- a/bio/hmmer/hmmpress/meta.yaml +++ b/bio/hmmer/hmmpress/meta.yaml @@ -1,10 +1,15 @@ name: hmmpress +url: http://hmmer.org/ description: "Format an HMM database into a binary format for hmmscan." authors: - N Tessa Pierce input: - - hmm database + - hmm database. This must be the only element of the input file list. output: - binary format hmm database (for hmmscan) -citations: - - "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" +notes: | + "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" + + This wrapper does not accept parameters. + + This tool/wrapper does not handle multi-threading. From b507eb973ec1598fd2e5703d383d5aaf303d8636 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 130/191] [doc] (meta.yaml): bio/hmmer/hmmscan/meta.yaml updated --- bio/hmmer/hmmscan/meta.yaml | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/bio/hmmer/hmmscan/meta.yaml b/bio/hmmer/hmmscan/meta.yaml index f45bbe24cc9..1f01dc65841 100644 --- a/bio/hmmer/hmmscan/meta.yaml +++ b/bio/hmmer/hmmscan/meta.yaml @@ -1,11 +1,18 @@ name: hmmscan +url: http://hmmer.org/ description: "search protein sequence(s) against a protein profile database" authors: - N Tessa Pierce input: - - protein sequence file (fasta) - - database hmm files + - fasta: protein sequence file (fasta) + - profile: Path to database hmm files output: - - matches to hmm files -citations: - - "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" + - tblout: save parseable table of per-sequence hits to file + - domtblout: save parseable table of per-sequence hits to file + - pfamtblout: save table of hits and domains to file, in Pfam format + - outfile: Direct the main human-readable output to a file +params: + - evalue_threshold: default is 0.00001 + - score_threshold: if bitscore threshold provided, hmmsearch will use that instead +notes: | + "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" From 253ff0689da2952f5c150ccac6b46fc4e5f91781 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 131/191] [doc] (meta.yaml): bio/hmmer/hmmsearch/meta.yaml updated --- bio/hmmer/hmmsearch/meta.yaml | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/bio/hmmer/hmmsearch/meta.yaml b/bio/hmmer/hmmsearch/meta.yaml index dbeb70e69ca..e03f883b7c7 100644 --- a/bio/hmmer/hmmsearch/meta.yaml +++ b/bio/hmmer/hmmsearch/meta.yaml @@ -1,11 +1,18 @@ name: hmmsearch +url: http://hmmer.org/ description: "search profile(s) against a sequence database" authors: - N Tessa Pierce input: - - hmm profile(s) - - sequence database + - profile: hmm profile(s) + - fasta: sequence database output: - - matches between sequences and hmm profiles -citations: - - "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" + - tblout: save parseable table of per-sequence hits to file + - domtblout: save parseable table of per-sequence hits to file + - pfamtblout: save table of hits and domains to file, in Pfam format + - outfile: Direct the main human-readable output to a file +params: + - evalue_threshold: default is 0.00001 + - score_threshold: if bitscore threshold provided, hmmsearch will use that instead +notes: | + "`Challenges in Homology Search: HMMER3 and Convergent Evolution of Coiled-Coil Regions. J. Mistry, R. D. Finn, S. R. Eddy, A. Bateman, M. Punta. Nucleic Acids Research, 41:e121, 2013 `_" From a385a99c54ba795d743398c6a9e8f04effa57b21 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 132/191] [doc] (meta.yaml): bio/homer/annotatePeaks/meta.yaml updated --- bio/homer/annotatePeaks/meta.yaml | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/bio/homer/annotatePeaks/meta.yaml b/bio/homer/annotatePeaks/meta.yaml index a5926911994..cad955c1dc1 100644 --- a/bio/homer/annotatePeaks/meta.yaml +++ b/bio/homer/annotatePeaks/meta.yaml @@ -1,11 +1,30 @@ name: "Homer annotatePeaks" +url: http://homer.ucsd.edu/homer/ngs/annotation.html description: > - Performing peak annotation to associate peaks with nearby genes. For more information, please see the `documentation `_. + Performing peak annotation to associate peaks with nearby genes. authors: - Antonie Vietor input: - - peak or BED file - - various optional input files, i.e. gtf, bedGraph, wiggle + - peaks: peak or BED file + - genome: Path to a reference genome (fasta) + - gtf: Optional path to a GTF file + - gene: Optional path to a gene expression file + - motif_files: Optional path to motives file + - filter_motiv: Optional path to filter motives + - center: Optional path to motives file + - nearest_peak: Optional path to a set of peaks + - tag: Optional list of experiment directories to show tag counts for + - vcf: Optional path to a vcf file to annotate peaks with genetic variation infomation + - bed_graph: (Optional) read coverage counts from bedGraph files + - wig: (Optional) read coverage counts from wiggle files + - map: (Optional) mapping between peak IDs and promoter IDs, overrides closest assignment + - advanced_annotation: see `advanced annotation `_ output: - - annotation file (.txt) - - various optional output files + - annotations: annotation file (.txt) + - matrix: requires motif_files as input + - mfasta: requires motif_files as input + - mbed: requires motif_files as input + - mlogic: requires motif_files as input +params: + - mode: One of ``tss``, ``tts`` or ``rna`` + - extra: Optional parameters From fd86e6f1f960da63073ed3189fba4ac5783b4b94 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 133/191] [doc] (meta.yaml): bio/homer/findPeaks/meta.yaml updated --- bio/homer/findPeaks/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/homer/findPeaks/meta.yaml b/bio/homer/findPeaks/meta.yaml index 9365153e045..b2846ecb0e1 100644 --- a/bio/homer/findPeaks/meta.yaml +++ b/bio/homer/findPeaks/meta.yaml @@ -1,5 +1,14 @@ name: "Homer findPeaks" +url: http://homer.ucsd.edu/homer/ngs/peaks.html description: > - Find ChIP- or ATAC-Seq peaks with the HOMER suite. For more information, please see the `documentation `_. + Find ChIP- or ATAC-Seq peaks with the HOMER suite. authors: - Jan Forster +input: + - tag: Sample tag directory + - control: Control sample tag directory +output: + - Path to peaks file. This must be the only element of the output file list. +params: + - extra: Optional parameters + - style: One of ``factor``, ``histone``, ``super``, ``groseq``, ``tss``, ``dnase``, or ``mC``. Required From ea0fcd9bc05e4098f550e1eb0f07efbf85b66f48 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 134/191] [doc] (meta.yaml): bio/homer/getDifferentialPeaks/meta.yaml updated --- bio/homer/getDifferentialPeaks/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/homer/getDifferentialPeaks/meta.yaml b/bio/homer/getDifferentialPeaks/meta.yaml index 323903b5bf9..d77235252a1 100644 --- a/bio/homer/getDifferentialPeaks/meta.yaml +++ b/bio/homer/getDifferentialPeaks/meta.yaml @@ -1,5 +1,14 @@ name: "Homer getDifferentialPeaks" +url: http://homer.ucsd.edu/homer/ngs/mergePeaks.html description: > Detect differentially bound ChIP peaks between samples. For more information, please see the `documentation `_. authors: - Jan Forster +input: + - peaks: Path to input peaks + - first: Path to fist + - second: Path to second +output: + - Differential peaks. This must be the only element of the output file list. +params: + - extra: Optional parameters From 7193d04babd806e6ad14e42ffac442ea071fb5c0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 135/191] [doc] (meta.yaml): bio/homer/makeTagDirectory/meta.yaml updated --- bio/homer/makeTagDirectory/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/homer/makeTagDirectory/meta.yaml b/bio/homer/makeTagDirectory/meta.yaml index ac2a7277540..5c47ecf0636 100644 --- a/bio/homer/makeTagDirectory/meta.yaml +++ b/bio/homer/makeTagDirectory/meta.yaml @@ -1,5 +1,12 @@ name: "Homer makeTagDirectory" +url: http://homer.ucsd.edu/homer/ngs/tagDir.html description: > Create a tag directory with the HOMER suite. For more information, please see the `documentation `_. authors: - Jan Forster +input: + - Paths to tag directories. This must be the only elements in the input file list +output: + - Path to merged tag directories. This must be the only element in the output file list. +params: + - extra: Optional parameters From a92426ad8d930ff6886b50ddece25cd09ff545a1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 136/191] [doc] (meta.yaml): bio/homer/mergePeaks/meta.yaml updated --- bio/homer/mergePeaks/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/homer/mergePeaks/meta.yaml b/bio/homer/mergePeaks/meta.yaml index 488ba17e76a..1cbb955cc2a 100644 --- a/bio/homer/mergePeaks/meta.yaml +++ b/bio/homer/mergePeaks/meta.yaml @@ -1,5 +1,12 @@ name: "Homer mergePeaks" +url: http://homer.ucsd.edu/homer/ngs/mergePeaks.html description: > Merge ChIP-Seq peaks from multiple peak files. For more information, please see the `documentation `_. Please be aware that this wrapper does not yet support use of the ``-prefix`` parameter. authors: - Jan Forster +input: + - Paths to peak files. This must be the only elements of the input file list. +output: + - Path to merged peaks. This must be the only element in the output file list. +params: + - extra: Optional parameters From f146f11398988e8e5ec272a93f20dfbf842fe74e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 137/191] [doc] (meta.yaml): bio/igv-reports/meta.yaml updated --- bio/igv-reports/meta.yaml | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/bio/igv-reports/meta.yaml b/bio/igv-reports/meta.yaml index 427eade4258..478ac91aaae 100644 --- a/bio/igv-reports/meta.yaml +++ b/bio/igv-reports/meta.yaml @@ -1,8 +1,13 @@ -name: igv-reports +name: igv-reports +url: https://github.com/igvteam/igv-reports description: Create self-contained igv.js HTML pages. authors: - Johannes Köster input: - - BAM, VCF, ... + - tracks: Path to BAM/BED/... files to be displayed in IGV-report + - vcf: Path to VCF files to be displayed in IGV-report + - fasta: Path to reference genome output: - - HTML + - Path to HTML. This must be the first element of the output file list +params: + - extra: Optional parameters From 615491161543e348c4e44581a37ac48f722b6a82 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 138/191] [doc] (meta.yaml): bio/infernal/cmpress/meta.yaml updated --- bio/infernal/cmpress/meta.yaml | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/bio/infernal/cmpress/meta.yaml b/bio/infernal/cmpress/meta.yaml index 0a0e4544725..51812fe4eb1 100644 --- a/bio/infernal/cmpress/meta.yaml +++ b/bio/infernal/cmpress/meta.yaml @@ -1,10 +1,13 @@ name: infernal cmpress -description: "Starting from a CM database in standard Infernal-1.1 format, construct binary compressed datafiles for cmscan. Infernal ('INFERence of RNA ALignment') is for searching DNA sequence databases for RNA structure and sequence similarities. It is an implementation of a special case of profile stochastic context-free grammars called covariance models (CMs). A CM is like a sequence profile, but it scores a combination of sequence consensus and RNA secondary structure consensus, so in many cases, it is more capable of identifying RNA homologs that conserve their secondary structure more than their primary sequence." -authors: +url: http://eddylab.org/software/infernal/ +description: "Starting from a CM database in standard Infernal-1.1 format, construct binary compressed datafiles for cmscan. Infernal ('INFERence of RNA ALignment') is for searching DNA sequence databases for RNA structure and sequence similarities." +authors: - N. Tessa Pierce input: - - RNA covariance models (CMs) + - RNA covariance models (CMs). This must be the only input element of the input file list. output: - CMs prepared for use with cmscan -citations: - - "`E. P. Nawrocki and S. R. Eddy, Infernal 1.1 100-fold faster RNA homology searches, Bioinformatics 29:2933-2935 (2013) `_" +notes: | + It is an implementation of a special case of profile stochastic context-free grammars called covariance models (CMs). A CM is like a sequence profile, but it scores a combination of sequence consensus and RNA secondary structure consensus, so in many cases, it is more capable of identifying RNA homologs that conserve their secondary structure more than their primary sequence. + + "`E. P. Nawrocki and S. R. Eddy, Infernal 1.1 100-fold faster RNA homology searches, Bioinformatics 29:2933-2935 (2013) `_" From c6bb11c973e1a3e606503005bdb0248d022833d6 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 139/191] [doc] (meta.yaml): bio/infernal/cmscan/meta.yaml updated --- bio/infernal/cmscan/meta.yaml | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/bio/infernal/cmscan/meta.yaml b/bio/infernal/cmscan/meta.yaml index dbe8abffe1b..28fb3b7ebce 100644 --- a/bio/infernal/cmscan/meta.yaml +++ b/bio/infernal/cmscan/meta.yaml @@ -1,11 +1,19 @@ name: infernal cmscan -description: "cmscan is used to search sequences against collections of covariance models that have been prepared with cmpress. The output format is designed to be human- readable, but is often so voluminous that reading it is impractical, and parsing it is a pain. The --tblout option saves output in a simple tabular format that is concise and easier to parse. The -o option allows redirecting the main output, including throwing it away in /dev/null. Infernal ('INFERence of RNA ALignment') is for searching DNA sequence databases for RNA structure and sequence similarities. It is an implementation of a special case of profile stochastic context-free grammars called covariance models (CMs). A CM is like a sequence profile, but it scores a combination of sequence consensus and RNA secondary structure consensus, so in many cases, it is more capable of identifying RNA homologs that conserve their secondary structure more than their primary sequence." -authors: +url: http://eddylab.org/software/infernal/ +description: "cmscan is used to search sequences against collections of covariance models that have been prepared with cmpress." +authors: - N. Tessa Pierce input: - - sequence file - - RNA covariance models (CMs) + - fasta: Path to sequence file + - profile: RNA covariance models (CMs) output: - - rna alignments -citations: - - "`E. P. Nawrocki and S. R. Eddy, Infernal 1.1 100-fold faster RNA homology searches, Bioinformatics 29:2933-2935 (2013) `_" + - outfile: Path to output rna alignments + - tblout: Path to parseable table of hits to file +params: + - evalue_threshold: report <= this evalue threshold in output + - score_threshold: report >= this score threshold in output + - extra: Optional parameters +notes: | + The output format is designed to be human- readable, but is often so voluminous that reading it is impractical, and parsing it is a pain. The --tblout option saves output in a simple tabular format that is concise and easier to parse. The -o option allows redirecting the main output, including throwing it away in /dev/null. Infernal ('INFERence of RNA ALignment') is for searching DNA sequence databases for RNA structure and sequence similarities. It is an implementation of a special case of profile stochastic context-free grammars called covariance models (CMs). A CM is like a sequence profile, but it scores a combination of sequence consensus and RNA secondary structure consensus, so in many cases, it is more capable of identifying RNA homologs that conserve their secondary structure more than their primary sequence. + + "`E. P. Nawrocki and S. R. Eddy, Infernal 1.1 100-fold faster RNA homology searches, Bioinformatics 29:2933-2935 (2013) `_" From 1f9481197d74630a4a5336542fc705a48fd05eb7 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 140/191] [doc] (meta.yaml): bio/jannovar/meta.yaml updated --- bio/jannovar/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/jannovar/meta.yaml b/bio/jannovar/meta.yaml index 5cf5ecf06d2..6c9fcd9c84a 100644 --- a/bio/jannovar/meta.yaml +++ b/bio/jannovar/meta.yaml @@ -1,4 +1,13 @@ name: "jannovar" -description: Annotate predicted effect of nucleotide changes with `Jannovar`_ +url: https://doc-openbio.readthedocs.io/projects/jannovar/en/master/ +description: Annotate predicted effect of nucleotide changes with `Jannovar `_ authors: - Bradford Powell +input: + - vcf: Path to input VCF file + - pedigree: Path to pedigree file (optional) +output: + - Path to VCF output file, this must be he only output file +params: + - extra: Optional extra parameters + - database: Path to jannovar database From 8dae119b6502fd4a834c9d2fee7f1bb4e3d03247 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 141/191] [doc] (meta.yaml): bio/kallisto/index/meta.yaml updated --- bio/kallisto/index/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/kallisto/index/meta.yaml b/bio/kallisto/index/meta.yaml index 6cd1e98d579..749b7247982 100644 --- a/bio/kallisto/index/meta.yaml +++ b/bio/kallisto/index/meta.yaml @@ -1,4 +1,11 @@ name: "kallisto index" +url: https://bioinformatics.readthedocs.io/en/latest/kallisto/ description: Index a transcriptome using kallisto. authors: - Joël Simoneau +input: + - fasta: Path to transcriptome fasta file +output: + - index: Path to index directory +params: + - extra: Optional parameters From f07c7d9966a8104eb92b207528331802e2642eae Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 142/191] [doc] (meta.yaml): bio/kallisto/quant/meta.yaml updated --- bio/kallisto/quant/meta.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/bio/kallisto/quant/meta.yaml b/bio/kallisto/quant/meta.yaml index 4088f95a167..3a5ca5dd75a 100644 --- a/bio/kallisto/quant/meta.yaml +++ b/bio/kallisto/quant/meta.yaml @@ -1,4 +1,12 @@ name: "kallisto quant" +url: https://bioinformatics.readthedocs.io/en/latest/kallisto/ description: Pseudoalign reads and quantify transcripts using kallisto. authors: - Joël Simoneau +input: + - index: Path to index directory + - fastq: List of paths to fastq files +output: + - Quantification output directory. This must be the only element in the output file list +params: + - extra: Optional parameters From 0bd83a66c4a8cdc2dce6207c87f25c8493c7db80 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 143/191] [doc] (meta.yaml): bio/last/lastal/meta.yaml updated --- bio/last/lastal/meta.yaml | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/bio/last/lastal/meta.yaml b/bio/last/lastal/meta.yaml index fbc4259ade7..188ab7b9a86 100644 --- a/bio/last/lastal/meta.yaml +++ b/bio/last/lastal/meta.yaml @@ -1,11 +1,22 @@ name: lastal +url: http://last.cbrc.jp/doc/last-evalues.html description: "LAST finds similar regions between sequences, and aligns them. It is designed for comparing large datasets to each other (e.g. vertebrate genomes and/or large numbers of DNA reads)" authors: - N. Tessa Pierce inputs: - - indexed db for mapping with last - - sequences to align + - lastdb: indexed db for mapping with last + - data: sequences to align outputs: + - maf: Path to mad alignments result (default) + - tab: Path to TSV alignments result + - blasttab: Path to blasttab alignments result + - blasttabplus: Path to blasttabplus alignments result - sequence alignments -citations: - - "`Adaptive seeds tame genomic sequence comparison. Kiełbasa SM, Wan R, Sato K, Horton P, Frith MC. Genome Res. 2011 21(3):487-93. `_" +params: + - extra: Optional parameters + - D_length: Evaluated D length (default 1000000) + - frameshift_cost: Frameshift penality for alignment +notes: | + Only one of ``maf``, ``tab``, ``blasttab``, or ``blasttabplus`` result should be set in the output file list. + + "`Adaptive seeds tame genomic sequence comparison. Kiełbasa SM, Wan R, Sato K, Horton P, Frith MC. Genome Res. 2011 21(3):487-93. `_" From 4250d93d507c4050c673518f29eb87a8227baaad Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 144/191] [doc] (meta.yaml): bio/last/lastdb/meta.yaml updated --- bio/last/lastdb/meta.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/bio/last/lastdb/meta.yaml b/bio/last/lastdb/meta.yaml index 9a3dc238883..16480b4528d 100644 --- a/bio/last/lastdb/meta.yaml +++ b/bio/last/lastdb/meta.yaml @@ -3,8 +3,11 @@ description: "LAST finds similar regions between sequences, and aligns them. It authors: - N. Tessa Pierce inputs: - - fasta reference + - Path to fasta reference. This must be the only element in the input file list outputs: - indexed db for mapping with last +params: + - extra: Optional parameters + - protein_input: Boolean, set the ``-p`` parameters. citations: - - "`Adaptive seeds tame genomic sequence comparison. Kiełbasa SM, Wan R, Sato K, Horton P, Frith MC. Genome Res. 2011 21(3):487-93. `_" + - "`Adaptive seeds tame genomic sequence comparison. Kiełbasa SM, Wan R, Sato K, Horton P, Frith MC. Genome Res. 2011 21(3):487-93. `_" From d6a7ecf1afcb50bd16386ebacab7375e63a587fe Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 145/191] [doc] (meta.yaml): bio/liftoff/meta.yaml updated --- bio/liftoff/meta.yaml | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/bio/liftoff/meta.yaml b/bio/liftoff/meta.yaml index 9e4996fda7d..b4a5eb261e6 100644 --- a/bio/liftoff/meta.yaml +++ b/bio/liftoff/meta.yaml @@ -1,11 +1,14 @@ name: "liftoff" -description: Lift features from one genome assembly to another (https://github.com/agshumate/Liftoff) +url: https://github.com/agshumate/Liftoff +description: Lift features from one genome assembly to another authors: - Tomás Di Domenico input: - - A fasta formatted reference genome file - - A fasta formatted target genome file - - A GFF/GTF formatted annotations file + - ref: A fasta formatted reference genome file + - tgt: A fasta formatted target genome file + - ann: A GFF/GTF formatted annotations file output: - - A GFF formatted file containing the mapped annotations - - A GFF formatted file containing the unmapped annotations + - main: A GFF formatted file containing the mapped annotations + - unmapped: A GFF formatted file containing the unmapped annotations +params: + - extra: Optional parameters From ae1301b127d9dcaa4ba91be853ff898ab4944722 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 146/191] [doc] (meta.yaml): bio/lofreq/call/meta.yaml updated --- bio/lofreq/call/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/lofreq/call/meta.yaml b/bio/lofreq/call/meta.yaml index 743184626cf..191012f4080 100644 --- a/bio/lofreq/call/meta.yaml +++ b/bio/lofreq/call/meta.yaml @@ -1,4 +1,13 @@ name: lofreq call -description: simply call variants +url: https://csb5.github.io/lofreq/ +description: simply call variants authors: - Patrik Smeds +input: + - bam: Path to bam file + - bai: Path to bam index file +output: + - Path to lofreq calls. This must be the only element in the output file list. +params: + - extra: Optional parameters + - ref: Path to reference genome sequence (fasta) From b69f53376928c2349560459cf133aa953933cd5a Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 147/191] [doc] (meta.yaml): bio/macs2/callpeak/meta.yaml updated --- bio/macs2/callpeak/meta.yaml | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/bio/macs2/callpeak/meta.yaml b/bio/macs2/callpeak/meta.yaml index 562b83f2f1a..51eff3aa743 100644 --- a/bio/macs2/callpeak/meta.yaml +++ b/bio/macs2/callpeak/meta.yaml @@ -1,7 +1,19 @@ name: macs2 callpeak +url: https://github.com/macs3-project/MACS/blob/master/README.md description: > ``MACS2 callpeak`` model-based analysis tool for ChIP-sequencing that calls peaks from alignment results. +authors: + - Antonie Vietor +input: + - control: Path to input peaks (Optional) + - treatment: SAM, BAM, BED, ELAND, ELANDMULTI, ELANDEXPORT, BOWTIE, BAMPE or BEDPE files +output: + - tabular file in excel format (.xls) AND + - different optional metrics in bedGraph or BED formats +params: + - Optional parameters. This must b the only element in the param section of the snakemake rule +notes: | For usage information about ``MACS2 callpeak``, please see the `documentation `_ and the command line help. For more information about ``MACS2``, also see the `source code `_ and `published article `_. Depending on the selected extension(s), the option(s) will be set automatically (please see table below). @@ -39,11 +51,3 @@ description: > +--------------------------------+----------------------------------------+----------+--------------------+ | NAME_summits.bed | peak summits locations for every peak | BED | if not set -\-broad| +--------------------------------+----------------------------------------+----------+--------------------+ - -authors: - - Antonie Vietor -input: - - SAM, BAM, BED, ELAND, ELANDMULTI, ELANDEXPORT, BOWTIE, BAMPE or BEDPE files -output: - - tabular file in excel format (.xls) AND - - different optional metrics in bedGraph or BED formats From a6da000ee33ebb89d1cceebd49923c68458f21d1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 148/191] [doc] (meta.yaml): bio/mapdamage2/meta.yaml updated --- bio/mapdamage2/meta.yaml | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/bio/mapdamage2/meta.yaml b/bio/mapdamage2/meta.yaml index d7bfdb40dc5..dee0c2512d4 100644 --- a/bio/mapdamage2/meta.yaml +++ b/bio/mapdamage2/meta.yaml @@ -1,4 +1,13 @@ name: mapDamage2 -description: tracking and quantifying damage patterns in ancient DNA sequences. For more information about MapDamage2 see `MapDamage2 documentation `_. +url: https://ginolhac.github.io/mapDamage/ +description: tracking and quantifying damage patterns in ancient DNA sequences. authors: - Filipe G. Vieira +input: + - ref: Path to fasta genome sequence + - bam: Path to mapped dna sequences +output: + - rescaled_bam: Path to rescaled bam (Optional) + - log: Path to output directory +params: + - extra: Optional parameters From ef050a9cd67839c97a6a10801afde35322b39ba6 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 149/191] [doc] (meta.yaml): bio/minimap2/aligner/meta.yaml updated --- bio/minimap2/aligner/meta.yaml | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/bio/minimap2/aligner/meta.yaml b/bio/minimap2/aligner/meta.yaml index ffb70ec3a7b..d67a26081bc 100644 --- a/bio/minimap2/aligner/meta.yaml +++ b/bio/minimap2/aligner/meta.yaml @@ -1,16 +1,18 @@ name: minimap2 +url: https://lh3.github.io/minimap2 description: A versatile pairwise aligner for genomic and spliced nucleotide sequences. authors: - Tom Poorten - Michael Hall - Filipe G. Vieira input: - - FASTQ file(s) - - reference genome + - query: FASTQ file(s) + - targt: reference genome output: - - SAM/BAM/CRAM file + - SAM/BAM/CRAM file. This must be the first output element in the output file list +params: + - extra: The `extra` param allows for additional arguments for minimap2. + - sort: The `sort` param allows to enable sorting (if output not PAF), and can be either 'none', 'queryname' or 'coordinate'. + - sort_extra: The `sort_extra` allows for extra arguments for samtools/picard notes: | - * The `extra` param allows for additional arguments for minimap2. - * The `sort` param allows to enable sorting (if output not PAF), and can be either 'none', 'queryname' or 'coordinate'. - * The `sort_extra` allows for extra arguments for samtools/picard - * For more inforamtion see, https://lh3.github.io/minimap2 + Warning, this threads will use more threads than the number reserved in the Snakefile as soon as ``sort`` parameter is not none. In that case, for X reserved threads, X+1 will be used. From 03b91ec2d9923549826f10ce7539680e0dbf4947 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 150/191] [doc] (meta.yaml): bio/minimap2/index/meta.yaml updated --- bio/minimap2/index/meta.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/bio/minimap2/index/meta.yaml b/bio/minimap2/index/meta.yaml index 9c14d48e6f9..d4e15e7a854 100644 --- a/bio/minimap2/index/meta.yaml +++ b/bio/minimap2/index/meta.yaml @@ -1,4 +1,11 @@ name: minimap2 index +url: https://github.com/lh3/minimap2 description: creates a minimap2 index authors: - Tom Poorten +input: + - target: Path to reference genome (fasta) +output: + - Path to index. This must be the first input in the input file list +params: + - extra: optional parameters From 31a71a399734b6e2be3dad6ad77d86180f714f4c Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 151/191] [doc] (meta.yaml): bio/mlst/meta.yaml updated --- bio/mlst/meta.yaml | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/bio/mlst/meta.yaml b/bio/mlst/meta.yaml index 2f6b1e705f8..215e1c390d3 100644 --- a/bio/mlst/meta.yaml +++ b/bio/mlst/meta.yaml @@ -1,12 +1,12 @@ name: "mlst" +url: https://github.com/tseemann/mlst description: Scan contig files against traditional PubMLST typing schemes authors: - Torsten Seeman (mlst tool) - https://github.com/tseemann/mlst - Max Cummins (Snakemake wrapper [unaffiliated with Torsten Seeman]) input: - - Genomic assembly (fasta format) + - assembly: Genomic assembly (fasta format) output: - - Returns a tab-separated line containing the filename, matching PubMLST scheme name, ST (sequence type) and the allele IDs. Other output formats are also available (eg. CSV, JSON) -notes: | - * The `extra` param allows for additional program arguments. - * For more inforamtion see https://github.com/tseemann/mlst \ No newline at end of file + - mlst: Returns a tab-separated line containing the filename, matching PubMLST scheme name, ST (sequence type) and the allele IDs. Other output formats are also available (eg. CSV, JSON) +params: + - extra: The `extra` param allows for additional program arguments. From cdfee6fd0c88a6e1d0e886eb1194c299a660370e Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 152/191] [doc] (meta.yaml): bio/mosdepth/meta.yaml updated --- bio/mosdepth/meta.yaml | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/bio/mosdepth/meta.yaml b/bio/mosdepth/meta.yaml index 55c53e92f66..1db4d0cf633 100644 --- a/bio/mosdepth/meta.yaml +++ b/bio/mosdepth/meta.yaml @@ -1,18 +1,19 @@ name: mosdepth +url: https://github.com/brentp/mosdepth description: fast BAM/CRAM depth calculation authors: - William Rowell - David Lähnemann - Filipe Vieira input: - - BAM/CRAM files - - reference genome (optional) - - BED file (optional) + - bam: BAM/CRAM files + - fasta: reference genome (optional) + - bed: BED file (optional) output: - - Several coverage summary files. -notes: | - * The `by` param allows to specify (integer) window-sizes (incompatible with input BED). - * The `threshold` param allows to, for or each interval in `--by`, write number of bases covered by at least threshold bases. Specify multiple integer values separated by ','. - * The `precision` param allows to specify output floating point precision. - * The `extra` param allows for additional program arguments. - * For more information see, https://github.com/brentp/mosdepth + - Several coverage summary files. Order does not matter. +params: + - by: The `by` param allows to specify (integer) window-sizes (incompatible with input BED). + - threshold: The `threshold` param allows to, for or each interval in `--by`, write number of bases covered by at least threshold bases. Specify multiple integer values separated by ','. + - precision: The `precision` param allows to specify output floating point precision. + - extra: The `extra` param allows for additional program arguments. + - quantize: write quantized output From 8bc9b22f009ce1990dc2fe398535d94662c64234 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 153/191] [doc] (meta.yaml): bio/msisensor/msi/meta.yaml updated --- bio/msisensor/msi/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/msisensor/msi/meta.yaml b/bio/msisensor/msi/meta.yaml index 1e950114d78..244e757e31c 100644 --- a/bio/msisensor/msi/meta.yaml +++ b/bio/msisensor/msi/meta.yaml @@ -3,10 +3,15 @@ description: "Score your MSI with MSIsensor" author: - Thibault Dayris input: - - A microsatellite and homopolymer list from MSIsensor Scan - - A pair of normal/tumoral bams + - microsat: A microsatellite and homopolymer list from MSIsensor Scan + - normal: Path to normal bam + - tumor: Path to tumor bam output: - A text file containing MSI scores - A TSV formatted file containing read count distribution - A TSV formatted file containing somatic sites - A TSV formatted file containing germline sites +params: + - extra: Optional parameters +notes: | + Warning, the official repository has been archived by its owner. See msisensor-pro. From da75a20de9a44a6f4571629d36e008482e28fc97 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 154/191] [doc] (meta.yaml): bio/msisensor/scan/meta.yaml updated --- bio/msisensor/scan/meta.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/bio/msisensor/scan/meta.yaml b/bio/msisensor/scan/meta.yaml index 0f64c2f5b34..e352795e6a7 100644 --- a/bio/msisensor/scan/meta.yaml +++ b/bio/msisensor/scan/meta.yaml @@ -1,8 +1,11 @@ name: "MSIsensor Scan" +url: https://github.com/ding-lab/msisensor description: "Scan homopolymers and microsatelites with MSIsensor" authors: - Thibault Dayris input: - - A (multi)fasta formatted file + - A (multi)fasta formatted file. This must be the only input file output: - - A text file containing homopolymers and microsatelites + - A text file containing homopolymers and microsatelites. This must be the only output file +notes: | + Warning, the official repository has been archived by its owner. See msisensor-pro. From 853192afae2c4115fbbeea0f4bc3a7e0dee8bf2c Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 155/191] [doc] (meta.yaml): bio/multiqc/meta.yaml updated --- bio/multiqc/meta.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/bio/multiqc/meta.yaml b/bio/multiqc/meta.yaml index e2c6315cc37..36b8dabbe72 100644 --- a/bio/multiqc/meta.yaml +++ b/bio/multiqc/meta.yaml @@ -1,9 +1,12 @@ name: multiqc +url: https://multiqc.info/ description: | Generate qc report using multiqc. authors: - Julian de Ruiter input: - - input directory containing qc files + - input directories containing qc files output: - - qc report (html) + - qc report (html) This must be the first output in the output file list +params: + - Optional parameters From 6228edb35b42e33fdfcafa4d3ae75654d4eae6ef Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 156/191] [doc] (meta.yaml): bio/nanosim-h/meta.yaml updated --- bio/nanosim-h/meta.yaml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/bio/nanosim-h/meta.yaml b/bio/nanosim-h/meta.yaml index 7bae3a6836e..9c15abe0a4f 100644 --- a/bio/nanosim-h/meta.yaml +++ b/bio/nanosim-h/meta.yaml @@ -1,4 +1,16 @@ name: nanosim-h +url: https://github.com/karel-brinda/NanoSim-H description: NanoSim-H is a simulator of Oxford Nanopore reads that captures the technology-specific features of ONT data, and allows for adjustments upon improvement of Nanopore sequencing technology. authors: - Michael Hall +input: + - Genome sequence (fasta). This must be the first input element in the input file list +output: + - simulated reads, logs and errors with a common prefix +params: + - extra: Optional parameters + - num_reads: number of generated reads + - profile: error profile, see `precomputed profiles `_ + - perfect_reads: output perfect reads, no mutations + - min_read_len: minimum read length + - max_read_len: maximum read length From 90ad5f9b9a86462dccffc50f3237f819cabd197b Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 157/191] [doc] (meta.yaml): bio/ngs-disambiguate/meta.yaml updated --- bio/ngs-disambiguate/meta.yaml | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/bio/ngs-disambiguate/meta.yaml b/bio/ngs-disambiguate/meta.yaml index d99f93ad5cf..09f7dd5a58f 100644 --- a/bio/ngs-disambiguate/meta.yaml +++ b/bio/ngs-disambiguate/meta.yaml @@ -1,14 +1,19 @@ name: ngs-disambiguate +url: https://github.com/AstraZeneca-NGS/disambiguate description: | Disambiguation algorithm for reads aligned to two species (e.g. human and mouse genomes) from Tophat, Hisat2, STAR or BWA mem. authors: - Julian de Ruiter input: - - species a bam file (name sorted) - - species b bam file (name sorted) + - a: species a bam file (name sorted) + - b: species b bam file (name sorted) output: - - bam file with ambiguous alignments for species a - - bam file with ambiguous alignments for species b - - bam file with unambiguous alignments for species a - - bam file with unambiguous alignments for species b + - a_ambiguous: bam file with ambiguous alignments for species a + - b_ambiguous: bam file with ambiguous alignments for species b + - a_disambiguated: bam file with unambiguous alignments for species a + - b_disambiguated: bam file with unambiguous alignments for species b + - summary: Result summary +params: + - prefix: the prefix is used as the sample name in the summary file. + - extra: Optional parameters From eea4f04f5fe80fb890072cdb55647d310c4846d0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 158/191] [doc] (meta.yaml): bio/open-cravat/module/meta.yaml updated --- bio/open-cravat/module/meta.yaml | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/bio/open-cravat/module/meta.yaml b/bio/open-cravat/module/meta.yaml index f2b0e020e21..927c6c10914 100644 --- a/bio/open-cravat/module/meta.yaml +++ b/bio/open-cravat/module/meta.yaml @@ -1,4 +1,7 @@ name: OpenCRAVAT module -description: Install OpenCRAVAT modules. Annotate variant calls with OpenCRAVAT. For more details, see https://github.com/KarchinLab/open-cravat/wiki. +url: https://github.com/KarchinLab/open-cravat/wiki +description: Install OpenCRAVAT modules. Annotate variant calls with OpenCRAVAT authors: - Rick Kim +output: + - Cravat modules From 23d4cdaab22319190355b90f1da49b83a12665f3 Mon Sep 17 00:00:00 2001 From: tdayris Date: Thu, 22 Jul 2021 11:26:36 +0200 Subject: [PATCH 159/191] [doc] (meta.yaml): bio/open-cravat/run/meta.yaml updated --- bio/open-cravat/run/meta.yaml | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/bio/open-cravat/run/meta.yaml b/bio/open-cravat/run/meta.yaml index c7968f72e68..be3f500ee9f 100644 --- a/bio/open-cravat/run/meta.yaml +++ b/bio/open-cravat/run/meta.yaml @@ -1,4 +1,13 @@ name: OpenCRAVAT Run -description: Runs OpenCRAVAT. Annotate variant calls with OpenCRAVAT. For more details, see https://github.com/KarchinLab/open-cravat/wiki. +url: https://github.com/KarchinLab/open-cravat/wiki +description: Runs OpenCRAVAT. Annotate variant calls with OpenCRAVAT. authors: - - Rick Kim + - Rick Kim +params: + - genome: Reference genome identifier (default hg38) + - extra: Optional parameters +input: + - OpenCRAVAT modules + - TSV input +output: + - Output file depending on modules From d714809da635e827b76956e74c71b7f26f26864f Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 23 Jul 2021 11:27:18 +0200 Subject: [PATCH 160/191] [doc] (meta.yaml): bio/paladin/index/meta.yaml updated --- bio/paladin/index/meta.yaml | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/bio/paladin/index/meta.yaml b/bio/paladin/index/meta.yaml index f2384d67c94..6379c81db77 100644 --- a/bio/paladin/index/meta.yaml +++ b/bio/paladin/index/meta.yaml @@ -1,10 +1,14 @@ name: paladin index +url: http://genomebio.org/paladin/ description: "Index a protein fasta file for mapping with paladin. PALADIN is a protein sequence alignment tool designed for the accurate functional characterization of metagenomes." authors: - N. Tessa Pierce input: - - protein fasta file + - protein fasta file (this must be the first input) + - gff file (this may be the second and last input, do not use key-word ``gff``, the annotation entry vouls be duplicated) output: - file indexed for paladin mapping +params: + - extra: Optional parameters citations: - "`Westbrook, Anthony et al. 'PALADIN: protein alignment for functional profiling whole metagenome shotgun data' Bioinformatics (Oxford, England) vol. 33,10 (2017): 1473-1478 `_" From 063a696d7b7a5c6df9588031f97fa3478c5710db Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 161/191] [doc] (meta.yaml): bio/pandora/index/meta.yaml updated --- bio/pandora/index/meta.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bio/pandora/index/meta.yaml b/bio/pandora/index/meta.yaml index ef526a81e2e..9598d9a6297 100644 --- a/bio/pandora/index/meta.yaml +++ b/bio/pandora/index/meta.yaml @@ -9,4 +9,4 @@ output: - index: A pandora index file - kmer_prgs: A directory of the index kmer PRGs in GFA format params: - options: Any options other than threads (see docs) + - options: Any options other than threads (see docs) From 72036edfe26f31ad5ccf77e2129fb2cbdd13b280 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 162/191] [doc] (meta.yaml): bio/pbmm2/align/meta.yaml updated --- bio/pbmm2/align/meta.yaml | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/bio/pbmm2/align/meta.yaml b/bio/pbmm2/align/meta.yaml index 005a9dfd40b..63c6b6bcd99 100644 --- a/bio/pbmm2/align/meta.yaml +++ b/bio/pbmm2/align/meta.yaml @@ -1,4 +1,16 @@ name: pbmm2 align -description: Align reads using pbmm2, a minimap2 SMRT wrapper for PacBio data https://github.com/PacificBiosciences/pbmm2/ +url: https://github.com/PacificBiosciences/pbmm2/ +description: Align reads using pbmm2, a minimap2 SMRT wrapper for PacBio data authors: - William Rowell +input: + - reference: Genome index or genome fasta sequence + - query: Path to unaligned bam (ubam), or sequences (fasta, fastq) +- output: + - bam: Aligned bam + - index: Bam index +params: + - sample: Sample name for @RG + - extra: Optional parameters + - loglevel: Logging level + - preset: One of ``SUBREAD``, ``CCS``, ``HIFI``, ``ISOSEQ``, ``UNROLLED`` From 5a6e029b7aa6bd348c7faa89d8b55b1d87bc0428 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 163/191] [doc] (meta.yaml): bio/pbmm2/index/meta.yaml updated --- bio/pbmm2/index/meta.yaml | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/bio/pbmm2/index/meta.yaml b/bio/pbmm2/index/meta.yaml index 905e01f841f..b2fc735c7a7 100644 --- a/bio/pbmm2/index/meta.yaml +++ b/bio/pbmm2/index/meta.yaml @@ -1,4 +1,12 @@ name: pbmm2 index -description: Indexes a reference using pbmm2, a minimap2 SMRT wrapper for PacBio data https://github.com/PacificBiosciences/pbmm2/ +url: https://github.com/PacificBiosciences/pbmm2/ +description: Indexes a reference using pbmm2, a minimap2 SMRT wrapper for PacBio data authors: - William Rowell +params: + - preset: One of ``SUBREAD``, ``CCS``, ``HIFI``, ``ISOSEQ``, ``UNROLLED`` + - extra: Optional parameters +input: + - reference: Path to input reference genome (fasta) +output: + - Path to output index. This must be the only element in the output file list. From b14d346c1e136a9368ba2a92a0576b5e4ee0e9cd Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 164/191] [doc] (meta.yaml): bio/pear/meta.yaml updated --- bio/pear/meta.yaml | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/bio/pear/meta.yaml b/bio/pear/meta.yaml index 36c056e2c1b..92d57804422 100644 --- a/bio/pear/meta.yaml +++ b/bio/pear/meta.yaml @@ -1,10 +1,18 @@ name: pear +url: https://cme.h-its.org/exelixis/web/software/pear/doc.html description: PEAR is an ultrafast, memory-efficient and highly accurate pair-end read merger authors: - N. Tessa Pierce input: - - paired fastq files + - read1: Path to fastq R1 file (both fastq required) + - read2: Path to fastq R2 file (both fastq required) output: - - merged fastq -citations: - - "`Jiajie Zhang, Kassian Kobert, Tomáš Flouri, Alexandros Stamatakis; PEAR: a fast and accurate Illumina Paired-End reAd mergeR, Bioinformatics, Volume 30, Issue 5, 1 March 2014, Pages 614–620 `_" + - assembled: Assembled reads + - discarded: Discarded reads + - unassembled_r1: Reads from R1 which were not assembled + - unassembled_r2: Reads from R1 which were not assembled +params: + - pval: P-Value threshold + - extra: Optional parameters +notes: | + "`Jiajie Zhang, Kassian Kobert, Tomáš Flouri, Alexandros Stamatakis; PEAR: a fast and accurate Illumina Paired-End reAd mergeR, Bioinformatics, Volume 30, Issue 5, 1 March 2014, Pages 614–620 `_" From 8012e7560841d571bb6097b7ec4f3c527e771c85 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 165/191] [doc] (meta.yaml): bio/picard/addorreplacereadgroups/meta.yaml updated --- bio/picard/addorreplacereadgroups/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/picard/addorreplacereadgroups/meta.yaml b/bio/picard/addorreplacereadgroups/meta.yaml index 3c511d44df9..d5424d96fa1 100644 --- a/bio/picard/addorreplacereadgroups/meta.yaml +++ b/bio/picard/addorreplacereadgroups/meta.yaml @@ -1,8 +1,13 @@ name: picard AddOrReplaceReadGroups +url: https://gatk.broadinstitute.org/hc/en-us/articles/360046223331-AddOrReplaceReadGroups-Picard- description: Add or replace read groups with picard tools. authors: - Johannes Köster input: - - bam file + - bam file. This is the only element in the input file list output: - - bam file with added or replaced read groups + - bam file with added or replaced read groups. This must be the only element in the output file list +params: + - Optional parameters. +notes: | + This tool/wrapper does not handle multithreading From e1f65c607e101abb41c97ffb124d377e1e731e83 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 166/191] [doc] (meta.yaml): bio/picard/bedtointervallist/meta.yaml updated --- bio/picard/bedtointervallist/meta.yaml | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/bio/picard/bedtointervallist/meta.yaml b/bio/picard/bedtointervallist/meta.yaml index d19b3164aee..b3808c21f1c 100644 --- a/bio/picard/bedtointervallist/meta.yaml +++ b/bio/picard/bedtointervallist/meta.yaml @@ -1,4 +1,5 @@ name: picard BedToIntervalList +url: https://broadinstitute.github.io/picard/command-line-overview.html#BedToIntervalList description: | `picard BedToIntervalList `_ converts a BED file to Picard Interval List format. authors: @@ -7,5 +8,8 @@ input: - bed: region file - dict: genome dictionary file (from samtools dict or `picard CreateSequenceDictionary `_ ) output: - - interval_list Picard format - + - interval_list Picard format. This must be th only element in the output file list. +params: + - Optional arguments +notes: | + This tool/wrapper does not handle multithreading From ec8f81a7c301b8e0081314e325aa0232ef96eaf1 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 167/191] [doc] (meta.yaml): bio/picard/collectalignmentsummarymetrics/meta.yaml updated --- bio/picard/collectalignmentsummarymetrics/meta.yaml | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/bio/picard/collectalignmentsummarymetrics/meta.yaml b/bio/picard/collectalignmentsummarymetrics/meta.yaml index e6f196ee6d3..14d6c6fa6f2 100644 --- a/bio/picard/collectalignmentsummarymetrics/meta.yaml +++ b/bio/picard/collectalignmentsummarymetrics/meta.yaml @@ -1,5 +1,15 @@ name: picard CollectAlignmentSummaryMetrics +url: https://gatk.broadinstitute.org/hc/en-us/articles/360042476752-CollectAlignmentSummaryMetrics-Picard- description: | Collect metrics on aligned reads with picard tools. authors: - Johannes Köster +input: + - bam: Path to bam in which to collect metrics + - ref: Path to genome sequence (fasta). +output: + - Metrics. This must be the first element of the output file list +params: + - Optional arguments +notes: | + This tool/wrapper does not handle multithreading From c3aa21cac6dbeeedbd60c4a6f8258643a75f2b88 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 168/191] [doc] (meta.yaml): bio/picard/collectgcbiasmetrics/meta.yaml updated --- bio/picard/collectgcbiasmetrics/meta.yaml | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/bio/picard/collectgcbiasmetrics/meta.yaml b/bio/picard/collectgcbiasmetrics/meta.yaml index 39911bdd79b..90f06f5840d 100644 --- a/bio/picard/collectgcbiasmetrics/meta.yaml +++ b/bio/picard/collectgcbiasmetrics/meta.yaml @@ -1,14 +1,17 @@ name: picard CollectGcBiasMetrics +url: https://broadinstitute.github.io/picard/command-line-overview.html#CollectGcBiasMetrics description: | - Run picard CollectGcBiasMetrics to generate QC metrics pertaining to GC bias. + Run picard CollectGcBiasMetrics to generate QC metrics pertaining to GC bias. authors: - Brett Copeland input: - - BAM file of RNA-seq data aligned to genome - - REF_FLAT formatted file of transcriptome annotations + - bam: BAM file of RNA-seq data aligned to genome + - ref: REF_FLAT formatted file of transcriptome annotations output: - - GC metrics text file - - GC metrics PDF figure - - GC summary metrics text file + - metrics: GC metrics text file + - chart: GC metrics PDF figure + - summary: GC summary metrics text file +params: + - extra: Optional arguments notes: | - * For more information, see https://broadinstitute.github.io/picard/command-line-overview.html#CollectGcBiasMetrics. + This tool/wrapper does not handle multithreading From 192be2bc32a51389be31ce50820e424201ff77a0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 169/191] [doc] (meta.yaml): bio/picard/collecthsmetrics/meta.yaml updated --- bio/picard/collecthsmetrics/meta.yaml | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/bio/picard/collecthsmetrics/meta.yaml b/bio/picard/collecthsmetrics/meta.yaml index 185c35ad6f6..448688592a5 100644 --- a/bio/picard/collecthsmetrics/meta.yaml +++ b/bio/picard/collecthsmetrics/meta.yaml @@ -1,9 +1,17 @@ name: picard CollectHSMetrics +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037591891-CollectHsMetrics-Picard- description: | Collects hybrid-selection (HS) metrics for a SAM or BAM file using picard. authors: - Julian de Ruiter input: - - bam file + - bam: bam file + - reference: Path to reference genome (fasta) + - bait_intervals: Interval list which may be generated by Picard BedToIntervalList. + - target_intervals: Interval list which may be generated by Picard BedToIntervalList. output: - - metrics file + - metrics file. This must be the first element in the output file list +params: + - extra: Optional arguments +notes: | + This tool/wrapper does not handle multithreading From 3bcb8deeba242db3ecdc8d2960314bdb8c2e8a5e Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 170/191] [doc] (meta.yaml): bio/picard/collectinsertsizemetrics/meta.yaml updated --- bio/picard/collectinsertsizemetrics/meta.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/bio/picard/collectinsertsizemetrics/meta.yaml b/bio/picard/collectinsertsizemetrics/meta.yaml index 7999c0a9c77..e58827037c6 100644 --- a/bio/picard/collectinsertsizemetrics/meta.yaml +++ b/bio/picard/collectinsertsizemetrics/meta.yaml @@ -1,10 +1,15 @@ name: picard CollectInsertSizeMetrics +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037225252-CollectInsertSizeMetrics-Picard- description: | Collect metrics on insert size of paired end reads with picard tools. authors: - Johannes Köster input: - - bam file + - bam file. This must be the only element of the input file list output: - txt: textual representation of metrics - pdf: insert size histogram +params: + - Optional arguments +notes: | + This tool/wrapper does not handle multithreading From 19f4068890020b55bf50bef1daf6d9ff5e725d70 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 171/191] [doc] (meta.yaml): bio/picard/collectmultiplemetrics/meta.yaml updated --- bio/picard/collectmultiplemetrics/meta.yaml | 25 ++++++++++++--------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/bio/picard/collectmultiplemetrics/meta.yaml b/bio/picard/collectmultiplemetrics/meta.yaml index e0537ed4e95..d23d27a3cf0 100644 --- a/bio/picard/collectmultiplemetrics/meta.yaml +++ b/bio/picard/collectmultiplemetrics/meta.yaml @@ -1,6 +1,20 @@ name: picard CollectMultipleMetrics +url: https://broadinstitute.github.io/picard/command-line-overview.html#CollectMultipleMetrics description: > A ``picard`` meta-metrics tool that collects multiple classes of metrics. +authors: + - David Laehnemann + - Antonie Vietor +input: + - bam: BAM file (.bam) + - ref: FASTA reference sequence file (.fasta or .fa) +output: + - multiple metrics text files (_metrics) AND + - multiple metrics pdf files (.pdf) + - the appropriate extensions for the output files must be used depending on the desired tools +notes: | + This wrapper/tool does not handle multithreading + For usage information about CollectMultipleMetrics, please see ``picard``'s `documentation `_. For more information about ``picard``, also see the `source code `_. @@ -48,14 +62,3 @@ description: > +-----------------------------------+-----------------------------------------+ | CollectQualityYieldMetrics | ".quality_yield_metrics" | +-----------------------------------+-----------------------------------------+ - -authors: - - David Laehnemann - - Antonie Vietor -input: - - BAM file (.bam) - - FASTA reference sequence file (.fasta or .fa) -output: - - multiple metrics text files (_metrics) AND - - multiple metrics pdf files (.pdf) - - the appropriate extensions for the output files must be used depending on the desired tools From 0920fd74b5299e21af35dfcfa27f4657dcb3df63 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 172/191] [doc] (meta.yaml): bio/picard/collectrnaseqmetrics/meta.yaml updated --- bio/picard/collectrnaseqmetrics/meta.yaml | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/bio/picard/collectrnaseqmetrics/meta.yaml b/bio/picard/collectrnaseqmetrics/meta.yaml index 5ac3054c871..c6c4f1b1fea 100644 --- a/bio/picard/collectrnaseqmetrics/meta.yaml +++ b/bio/picard/collectrnaseqmetrics/meta.yaml @@ -1,12 +1,16 @@ name: picard CollectRnaSeqMetrics +url: https://broadinstitute.github.io/picard/command-line-overview.html#CollectRnaSeqMetrics description: | Run picard CollectRnaSeqMetrics to generate QC metrics for RNA-seq data. authors: - Brett Copeland input: - - BAM file of RNA-seq data aligned to genome - - REF_FLAT formatted file of transcriptome annotations + - bam: BAM file of RNA-seq data aligned to genome + - ref: REF_FLAT formatted file of transcriptome annotations output: - - RNA-Seq metrics text file + - RNA-Seq metrics text file. This must be the first element in the output file list +params: + - extra: Optional parameters + - strand: Strand specificity (default "NONE") notes: | - * For more information, see https://broadinstitute.github.io/picard/command-line-overview.html#CollectRnaSeqMetrics. + This tool/wrapper does not handle multithreading. From 5f1404c52ee3e1070e12d1d9d8ea1cba1a715cbd Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 173/191] [doc] (meta.yaml): bio/picard/collecttargetedpcrmetrics/meta.yaml updated --- bio/picard/collecttargetedpcrmetrics/meta.yaml | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/bio/picard/collecttargetedpcrmetrics/meta.yaml b/bio/picard/collecttargetedpcrmetrics/meta.yaml index 487702f15ce..276ec66e6d9 100644 --- a/bio/picard/collecttargetedpcrmetrics/meta.yaml +++ b/bio/picard/collecttargetedpcrmetrics/meta.yaml @@ -1,5 +1,16 @@ name: picard CollectTargetedPcrMetrics +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037225812-CollectTargetedPcrMetrics-Picard- description: | Collect metric information for target pcr metrics runs, with picard tools. authors: - Patrik Smeds +input: + - bam: Path to input bam file + - amplicon_intervals: Path to amplicon interval file + - target_intervals: Path to target interval file +output: + - Path to metrics file. This must be the first element of the output file list +params: + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From a0622ec7974abf306bd14cca3f51b730d92402f0 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 174/191] [doc] (meta.yaml): bio/picard/createsequencedictionary/meta.yaml updated --- bio/picard/createsequencedictionary/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/picard/createsequencedictionary/meta.yaml b/bio/picard/createsequencedictionary/meta.yaml index cd25a739d66..568df326336 100644 --- a/bio/picard/createsequencedictionary/meta.yaml +++ b/bio/picard/createsequencedictionary/meta.yaml @@ -1,9 +1,14 @@ name: picard CreateSequenceDictionary +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036712531-CreateSequenceDictionary-Picard- description: | Create a .dict file for a given FASTA file authors: - Johannes Köster input: - - FASTA file + - FASTA file. This must be the first element of the input file list output: - - .dict file + - Path to ``.dict`` file. This must be the first element of the output file list +params: + - extra: Optional arguments +notes: | + This tool/wrapper does not handle multithreading From 0a5477620002084a46cf54937258e88a498ed211 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 175/191] [doc] (meta.yaml): bio/picard/markduplicates/meta.yaml updated --- bio/picard/markduplicates/meta.yaml | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/bio/picard/markduplicates/meta.yaml b/bio/picard/markduplicates/meta.yaml index a2c331ac008..1be00cef44d 100644 --- a/bio/picard/markduplicates/meta.yaml +++ b/bio/picard/markduplicates/meta.yaml @@ -1,9 +1,15 @@ name: picard MarkDuplicates +url: https://broadinstitute.github.io/picard/command-line-overview.html#MarkDuplicates description: | - Mark PCR and optical duplicates with picard tools. For more information about MarkDuplicates see `picard documentation `_. + Mark PCR and optical duplicates with picard tools. authors: - Johannes Köster input: - - bam file(s) + - bam file(s). These must be the only input files output: - - bam file with marked or removed duplicates + - bam: bam file with marked or removed duplicates + - metrics: Path to metrics file +params: + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 13e531afcab07473ffb6f5b267b9c70745c98007 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 176/191] [doc] (meta.yaml): bio/picard/markduplicateswithmatecigar/meta.yaml updated --- bio/picard/markduplicateswithmatecigar/meta.yaml | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/bio/picard/markduplicateswithmatecigar/meta.yaml b/bio/picard/markduplicateswithmatecigar/meta.yaml index 8e504c1e4c9..f3de9349881 100644 --- a/bio/picard/markduplicateswithmatecigar/meta.yaml +++ b/bio/picard/markduplicateswithmatecigar/meta.yaml @@ -1,14 +1,17 @@ name: picard MarkDuplicatesWithMateCigar +url: https://broadinstitute.github.io/picard/command-line-overview.html#MarkDuplicatesWithMateCigar description: | Mark PCR and optical duplicates with picard tools, taking into account the CIGAR of the mate. authors: - Johannes Köster - Filipe G. Vieira input: - - bam file + - bam file. This must be the only element of the input file list output: - - bam file with marked or removed duplicates + - bam: bam file with marked or removed duplicates + - metrics: Path to metrics file +params: + - extra: The `extra` param allows for additional program arguments. + - java_opts: The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). notes: | - * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically). - * The `extra` param allows for additional program arguments. - * For more information see, https://broadinstitute.github.io/picard/command-line-overview.html#MarkDuplicatesWithMateCigar + This tool/wrapper does not handle multithreading From d6348927020455665e3b0e7d022c13dc8ca444a5 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 177/191] [doc] (meta.yaml): bio/picard/mergesamfiles/meta.yaml updated --- bio/picard/mergesamfiles/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/picard/mergesamfiles/meta.yaml b/bio/picard/mergesamfiles/meta.yaml index 05c985bc066..ecca705a282 100644 --- a/bio/picard/mergesamfiles/meta.yaml +++ b/bio/picard/mergesamfiles/meta.yaml @@ -1,9 +1,14 @@ name: picard MergeSamFiles +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036884711-MergeSamFiles-Picard- description: | Merge sam/bam files using picard tools. authors: - Julian de Ruiter input: - - sam/bam files + - sam/bam files. These must be the only input elements output: - - merged sam/bam file + - merged sam/bam file. This must be the first element of the output file list +params: + - Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 448c07e518fe5474f2a20d4babf53a599e4b89de Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 178/191] [doc] (meta.yaml): bio/picard/mergevcfs/meta.yaml updated --- bio/picard/mergevcfs/meta.yaml | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/bio/picard/mergevcfs/meta.yaml b/bio/picard/mergevcfs/meta.yaml index 7468be53dfe..64b3721aed2 100644 --- a/bio/picard/mergevcfs/meta.yaml +++ b/bio/picard/mergevcfs/meta.yaml @@ -4,6 +4,10 @@ description: | authors: - Johannes Köster input: - - vcf files + - vcfs: vcf files. These must be the only input elements output: - - merged vcf file + - merged vcf file. This must be the first element of the output file list +params: + - extra: Optional elements +notes: | + This tool/wrapper does not handle multithreading From 9e32c6dfb9933e2088907b8bc086e4dda4d76b28 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 179/191] [doc] (meta.yaml): bio/picard/revertsam/meta.yaml updated --- bio/picard/revertsam/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/picard/revertsam/meta.yaml b/bio/picard/revertsam/meta.yaml index 254b3bc1a2e..423d8fe0b2e 100644 --- a/bio/picard/revertsam/meta.yaml +++ b/bio/picard/revertsam/meta.yaml @@ -1,9 +1,14 @@ name: picard RevertSam +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036734291-RevertSam-Picard- description: | Reverts SAM or BAM files to a previous state. . authors: - Patrik Smeds input: - - sam/bam file + - sam/bam file. This must be the first element of the input file list output: - - sam/bam file. + - sam/bam file. This must be the first element of the output file list +params: + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 03fa9440a353c0914c81916fc40bafd74ba9519e Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 180/191] [doc] (meta.yaml): bio/picard/samtofastq/meta.yaml updated --- bio/picard/samtofastq/meta.yaml | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/bio/picard/samtofastq/meta.yaml b/bio/picard/samtofastq/meta.yaml index 6ea80e50b40..4b29cd0b1de 100644 --- a/bio/picard/samtofastq/meta.yaml +++ b/bio/picard/samtofastq/meta.yaml @@ -1,9 +1,16 @@ name: picard SomToFastq +url: https://gatk.broadinstitute.org/hc/en-us/articles/360036485372-SamToFastq-Picard- description: | Converts a SAM or BAM file to FASTQ. authors: - Patrik Smeds input: - - sam/bam file + - sam/bam file. This must be the first element of the input file list output: - - fastq files. + - fastq1: Path to R1 fastq + - fastq2: Path to R2 fastq (Optional) + - unpaired_fastq: Path to unpaired fastq (Optional, required if ``fastq2`` is provided) +params: + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 8937b632a807742a6c3eb57fc41e7eb287ffe034 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 181/191] [doc] (meta.yaml): bio/picard/sortsam/meta.yaml updated --- bio/picard/sortsam/meta.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/bio/picard/sortsam/meta.yaml b/bio/picard/sortsam/meta.yaml index f5cb1a92eea..9367f69b3f2 100644 --- a/bio/picard/sortsam/meta.yaml +++ b/bio/picard/sortsam/meta.yaml @@ -1,9 +1,14 @@ name: picard SortSam +url: https://gatk.broadinstitute.org/hc/en-us/articles/360037594291-SortSam-Picard- description: | Sort sam/bam files using picard tools. authors: - Julian de Ruiter input: - - sam/bam file + - sam/bam file. This must be the first element of the input file list output: - - sorted sam/bam file. + - sorted sam/bam file. This must be the first element of the output file list +params: + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 56c09faf3d30ffa0a5bd2686f549461ae54ea84b Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 182/191] [doc] (meta.yaml): bio/pindel/call/meta.yaml updated --- bio/pindel/call/meta.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/bio/pindel/call/meta.yaml b/bio/pindel/call/meta.yaml index ded75e327b2..c5877c890ac 100644 --- a/bio/pindel/call/meta.yaml +++ b/bio/pindel/call/meta.yaml @@ -1,4 +1,13 @@ name: pindel +url: http://gmt.genome.wustl.edu/packages/pindel/ description: Call variants with pindel. authors: - Johannes Köster +params: + - extra: Optional parameters + - prefix: Output file prefix +input: + - config: Path to config file, see `documentation `_ for more information. + - ref: Path to fasta genome sequence +output: + - Calls. This must be the first output of the output file list From e3bb2ae1aec77c33ca8a4598fe908f68888ef125 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 183/191] [doc] (meta.yaml): bio/pindel/pindel2vcf/meta.yaml updated --- bio/pindel/pindel2vcf/meta.yaml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/bio/pindel/pindel2vcf/meta.yaml b/bio/pindel/pindel2vcf/meta.yaml index 1dabeda9b18..618204849df 100644 --- a/bio/pindel/pindel2vcf/meta.yaml +++ b/bio/pindel/pindel2vcf/meta.yaml @@ -1,4 +1,16 @@ name: pindel2vcf +url: http://gmt.genome.wustl.edu/packages/pindel/ description: Convert pindel output to vcf. authors: - Johannes Köster +input: + - ref: Reference genome sequence (fasta) + - pindel: Pindel call(s) +output: + - VCF formatted calls +params: + - refname: Reference genome + - refdate: Reference genome release date + - extra: Optional parameters +notes: | + This tool/wrapper does not handle multithreading From 353be5d73b8456efec8f30beaecd8f4840b29120 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 184/191] [doc] (meta.yaml): bio/plass/meta.yaml updated --- bio/plass/meta.yaml | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/bio/plass/meta.yaml b/bio/plass/meta.yaml index 5d580522bb7..1c796ff02b5 100644 --- a/bio/plass/meta.yaml +++ b/bio/plass/meta.yaml @@ -1,10 +1,14 @@ name: plass +url: https://github.com/soedinglab/plass description: "Plass (Protein-Level ASSembler) is software to assemble short read sequencing data on a protein level. The main purpose of Plass is the assembly of complex metagenomic datasets." authors: - N. Tessa Pierce input: - - fastq files + - left: Path to R1 fastq files + - right: Path to R2 fastq files (Optional) output: - - fasta containing protein assembly -citations: - - "Steinegger M, Mirdita M and Soeding J. Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. biorxiv, doi: doi.org/10.1101/386110 (2018)" + - fasta containing protein assembly, this must be the first element of the output file list +params: + - extra: Optional parameters +notes: | + "Steinegger M, Mirdita M and Soeding J. Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. biorxiv, doi: doi.org/10.1101/386110 (2018)" From 1a797cc7818f3dd496777cd69180f8a5faabf261 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 185/191] [doc] (meta.yaml): bio/preseq/lc_extrap/meta.yaml updated --- bio/preseq/lc_extrap/meta.yaml | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/bio/preseq/lc_extrap/meta.yaml b/bio/preseq/lc_extrap/meta.yaml index d0546615963..f0781877011 100644 --- a/bio/preseq/lc_extrap/meta.yaml +++ b/bio/preseq/lc_extrap/meta.yaml @@ -1,12 +1,15 @@ name: preseq lc_extrap +url: https://github.com/smithlabcode/preseq description: > ``preseq`` estimates the library complexity of existing sequencing data to then estimate the yield of future experiments based on their design. For usage information, please see ``preseq``'s command line help (this seems more up to date than the available `documentation from 2014 `_ ). - For more information about ``preseq``, also see the `source code `_. authors: - Antonie Vietor input: - - bed files containing duplicates and sorted by chromosome, start position, strand position and finally strand OR + - bed/bam files containing duplicates and sorted by chromosome, start position, strand position and finally strand OR - bam files containing duplicates and sorted by using bamtools or samtools sort. + - Only the first element of the input list is used in this wrapper output: - - lc_extrap (.lc_extrap) + - lc_extrap (.lc_extrap) This must be the first element of the output list +params: + - Optional parameters From af0c782ec56fcaa3afbe67f0eb301acd543fc340 Mon Sep 17 00:00:00 2001 From: tdayris Date: Fri, 30 Jul 2021 13:01:11 +0200 Subject: [PATCH 186/191] [doc] (meta.yaml): bio/primerclip/meta.yaml updated --- bio/primerclip/meta.yaml | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/bio/primerclip/meta.yaml b/bio/primerclip/meta.yaml index 961d173b3ae..9b2a433680e 100644 --- a/bio/primerclip/meta.yaml +++ b/bio/primerclip/meta.yaml @@ -1,10 +1,20 @@ name: primerclip +url: https://github.com/swiftbiosciences/primerclip description: | - Primer trimming on sam file, https://github.com/swiftbiosciences/primerclip + Primer trimming on sam file authors: - Patrik Smeds input: - - sam file - - master primer file + - alignment_file: sam file + - master_file: master primer file output: - - sam file + - alignment_file: sam file +notes: | + This wrapper uses 4 threads: + + * samtools view + * primerclip + * head + * samtools view + + Despite being present in the Snakefile, this wrapper does not hantle extra parameters From 78acaf3618ff143b725f31541244a6b0b3229fc3 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 16 Aug 2021 08:06:30 +0200 Subject: [PATCH 187/191] [fix] (Syntax): Syntax error fiexed in bio/pbmm2/align/meta.yaml --- bio/pbmm2/align/meta.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bio/pbmm2/align/meta.yaml b/bio/pbmm2/align/meta.yaml index 63c6b6bcd99..63fed155e15 100644 --- a/bio/pbmm2/align/meta.yaml +++ b/bio/pbmm2/align/meta.yaml @@ -6,7 +6,7 @@ authors: input: - reference: Genome index or genome fasta sequence - query: Path to unaligned bam (ubam), or sequences (fasta, fastq) -- output: +output: - bam: Aligned bam - index: Bam index params: From 22077f4d2fb9226a9cc5cbff29976bc1d9af3ed5 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 16 Aug 2021 08:07:12 +0200 Subject: [PATCH 188/191] [doc] (meta.yaml): bio/prosolo/control-fdr/meta.yaml updated --- bio/prosolo/control-fdr/meta.yaml | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/bio/prosolo/control-fdr/meta.yaml b/bio/prosolo/control-fdr/meta.yaml index f1327095829..a85f4d6a77d 100644 --- a/bio/prosolo/control-fdr/meta.yaml +++ b/bio/prosolo/control-fdr/meta.yaml @@ -1,9 +1,15 @@ name: "ProSolo FDR control" +url: https://github.com/ProSolo/prosolo description: | ProSolo can control the false discovery rate of any combination of its defined single cell events (like the presence of an alternative allele or the dropout of an allele). authors: - David Lähnemann input: - - Variants called with prosolo in vcf or bcf format, including the fine-grained posterior probabilities for single cell events. + - Variants called with prosolo in vcf or bcf format, including the fine-grained posterior probabilities for single cell events. This must be the only element of the input file list output: - - bcf file with all variants that satisfy the chosen false discovery rate threshold with regard to the specified events. + - bcf file with all variants that satisfy the chosen false discovery rate threshold with regard to the specified events. This must be the only element of the output file list +params: + - events: comma-separated set of events for whose (joint) false discovery rate you want to control false discovery rate to control for + - fdr: fdr threshold +notes: | + This tool/wrapper does not handle multithreading From 659f4bddb1abbc987964ee32fdce017110358f45 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 16 Aug 2021 08:07:12 +0200 Subject: [PATCH 189/191] [doc] (meta.yaml): bio/prosolo/single-cell-bulk/meta.yaml updated --- bio/prosolo/single-cell-bulk/meta.yaml | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/bio/prosolo/single-cell-bulk/meta.yaml b/bio/prosolo/single-cell-bulk/meta.yaml index 6a8693c07bb..d4d828e6b43 100644 --- a/bio/prosolo/single-cell-bulk/meta.yaml +++ b/bio/prosolo/single-cell-bulk/meta.yaml @@ -1,12 +1,17 @@ name: "ProSolo" +url: https://github.com/ProSolo/prosolo description: | ProSolo calls variants or other events (like allele dropout) in a single cell sample against a bulk background sample. The single cell should stem from the same population of cells as the bulk background sample. The single cell sample should be amplified using multiple displacement amplification to match ProSolo's statistical model. authors: - David Lähnemann input: - - A position-sorted single cell bam file, with its index. - - A position-sorted bulk bam file, with its index. - - A reference genome sequence in fasta format, with its index. - - A vcf or bcf file specifying candidate sites to perform calling on. + - single_cell: A position-sorted single cell bam file, with its index. + - bulk: A position-sorted bulk bam file, with its index. + - ref: A reference genome sequence in fasta format, with its index. + - candidates: A vcf or bcf file specifying candidate sites to perform calling on. output: - - Variants called in bcf format, with fine-grained posterior probabilities for single cell events. + - output: Variants called in bcf format, with fine-grained posterior probabilities for single cell events. These must be the only output elements +params: + - extra: Optional parameters +note: | + This wrapper/tool does not handle multi-threading From dfaa6f9be8988b4588a5dafea5f5ee5be6c25f74 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 16 Aug 2021 08:07:12 +0200 Subject: [PATCH 190/191] [doc] (meta.yaml): bio/ptrimmer/meta.yaml updated --- bio/ptrimmer/meta.yaml | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/bio/ptrimmer/meta.yaml b/bio/ptrimmer/meta.yaml index 0afdba3ccf7..63aabe47200 100644 --- a/bio/ptrimmer/meta.yaml +++ b/bio/ptrimmer/meta.yaml @@ -1,4 +1,14 @@ name: "ptrimmer" +url: https://github.com/DMU-lilab/pTrimmer description: Tool to trim off the primer sequence from mutiplex amplicon sequencing authors: - Felix Mölder +input: + - r1: Path to fastq-formatted foreward reads + - r2: For paired-end only, path to fastq-formatted downstream reads + - primers: Fasta formatted primers +output: + - r1: Path to fastq-formatted foreward output reads + - r2: For paired-end only, path to fastq-formatted downstream reads +note: | + This wrapper/tool does not handle multi-threading From 6495544f433a4fea5c9789ec28a4d478b91a0c73 Mon Sep 17 00:00:00 2001 From: tdayris Date: Mon, 16 Aug 2021 08:07:12 +0200 Subject: [PATCH 191/191] [doc] (meta.yaml): bio/pyfastaq/replace_bases/meta.yaml updated --- bio/pyfastaq/replace_bases/meta.yaml | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/bio/pyfastaq/replace_bases/meta.yaml b/bio/pyfastaq/replace_bases/meta.yaml index 778c5ab129d..71be189938e 100644 --- a/bio/pyfastaq/replace_bases/meta.yaml +++ b/bio/pyfastaq/replace_bases/meta.yaml @@ -1,4 +1,14 @@ name: pyfastaq replace_bases +url: https://github.com/Jverma/fastAQ description: Replaces all occurrences of one letter with another. authors: - Michael Hall +input: + - Path to fastq/fasta file. This must be the first element of the input file list. +output: + - Path to replaced fasta/fastq file. This must be the first element of the output file list. +params: + - old_base: The base that is to be replaced + - new_base: Tha base to replace with +note: | + This wrapper/tool does not handle multi-threading