Update file examples

src/annotate/onclass/config.vsh.yaml

@@ -47,14 +47,17 @@ argument_groups:
         type: file
         description: The .nlp.emb file with the cell type embeddings.
         required: true
+        example: cl.ontology.nlp.emb
       - name: "--cl_ontology_file"
         type: file
         description: The .ontology file with the cell type ontology.
         required: true
+        example: cl.ontology
       - name: "--cl_obo_file"
         type: file
         description: The .obo file with the cell type ontology.
         required: true
+        example: cl.obo
 
   - name: Reference
     description: Arguments related to the reference dataset.

src/annotate/scanvi/config.vsh.yaml

@@ -21,6 +21,7 @@ argument_groups:
         description: Input h5mu file. Note that this needs to be the exact same dataset as the --scvi_model was trained on.
         direction: input
         required: true
+        example: input.h5mu
       - name: "--modality"
         description: |
           Which modality from the input MuData file to process.
@@ -63,6 +64,7 @@ argument_groups:
       - name: "--output"
         alternatives: ["-o"]
         type: file
+        example: output.h5mu
         description: Output h5mu file.
         direction: output
         required: true
@@ -71,6 +73,7 @@ argument_groups:
         description: Folder where the state of the trained model will be saved to.
         required: false
         direction: output
+        example: path/to/output_model/
       - name: "--obsm_output"
         type: string
         default: "X_scanvi_integrated"

src/compression/compress_h5mu/config.vsh.yaml

@@ -12,13 +12,14 @@ arguments:
     type: file
     description: Path to the input .h5mu.
     required: true
-    example: sample_path
+    example: input.h5mu
     direction: input
   - name: "--output"
     type: file
     description: location of output file.
     required: true
     direction: output
+    example: output.h5mu
 __merge__: [., /src/base/h5_compression_argument.yaml]
 resources:
   - type: python_script

src/convert/from_10xh5_to_h5mu/config.vsh.yaml

@@ -19,7 +19,7 @@ argument_groups:
       - name: "--input_metrics_summary"
         type: file
         description: A metrics summary csv file as generated by Cell Ranger.
-        example: metrics_cellranger.h5
+        example: metrics_cellranger.csv
   - name: Outputs
     arguments:
       - name: "--output"

src/convert/from_bd_to_10x_molecular_barcode_tags/config.vsh.yaml

@@ -12,14 +12,14 @@ arguments:
     type: file
     must_exist: true
     description: Input SAM or BAM file.
-    example: input.bam
+    example: input.bam, input.sam
     direction: input
     required: true
   - name: "--output"
     alternatives: ["-o"]
     type: file
     description: Output alignment file.
-    example: output.sam
+    example: output.sam, output.bam
     direction: output
   - name: "--bam"
     type: boolean_true

src/convert/from_h5mu_or_h5ad_to_tiledb/config.vsh.yaml

@@ -126,6 +126,7 @@ argument_groups:
     arguments:
       - name: "--tiledb_dir"
         type: file
+        example: path/to/tiledb_dir
         direction: output
         description: |
           Directory where the TileDB output will be written to.

src/dataflow/merge/config.vsh.yml

@@ -14,6 +14,7 @@ arguments:
     description: Paths to the single-modality .h5mu files that need to be combined
     required: true
     default: sample_paths
+    example: ["/path/to/modality_1.h5mu", "/path/to/modality_2.h5mu"]
   - name: "--output"
     description: Path to the output file.
     alternatives: ["-o"]

src/dataflow/split_h5mu/config.vsh.yaml

@@ -13,6 +13,7 @@ argument_groups:
     type: file
     description: Path to a single .h5mu file.
     required: true
+    example: input.h5mu
   - name: "--modality"
     description: |
       Which modality from the input MuData file to process.

src/dataflow/split_modalities/config.vsh.yaml

@@ -15,6 +15,7 @@ arguments:
     description: Path to a single .h5mu file.
     required: true
     default: sample_path
+    example: input.h5mu
   - name: "--output"
     alternatives: ["-o"]
     type: file

src/differential_expression/create_pseudobulk/config.vsh.yaml

@@ -28,6 +28,7 @@ argument_groups:
         description: Input h5mu file.
         direction: input
         required: true
+        example: input.h5mu
       - name: "--modality"
         description: |
           Which modality from the input MuData file to process.
@@ -78,6 +79,7 @@ argument_groups:
         description: Output h5mu file containing the aggregated pseudobulk samples.
         direction: output
         required: true
+        example: output.h5mu
       - name: "--output_compression"
         type: string
         description: |

src/download/download_file/config.vsh.yaml

@@ -16,10 +16,8 @@ arguments:
     type: string
     description: "URL to a file to download."
     required: true
-    example: "https://cf.10xgenomics.com/samples/cell-exp/3.0.0/pbmc_1k_protein_v3/pbmc_1k_protein_v3_raw_feature_bc_matrix.h5"
   - name: "--output"
     type: file
-    example: pbmc_1k_protein_v3_raw_feature_bc_matrix.h5
     required: true
     direction: output
     description: "Path where to store output."

src/filter/filter_with_counts/config.vsh.yaml

@@ -29,7 +29,6 @@ argument_groups:
         required: false
 
       - name: "--layer"
-        description: |
         description: |
           Location of the count matrix. If specified, will be used to select a key from .layers,
           otherwise .X is used.

src/genetic_demux/bcftools/config.vsh.yaml

@@ -10,6 +10,7 @@ arguments:
     type: file
     required: true
     multiple: true
+    example: ["input_1.vcf", "input_2.vcf"]
     description: VCF files, must have the same sample columns appearing in the same order.
   - name: "--concat"
     type: boolean_true

src/genetic_demux/cellsnp/config.vsh.yaml

@@ -11,24 +11,31 @@ argument_groups:
   - name: "--sam_file"
     type: file
     description: "Indexed sam/bam file(s), comma separated multiple samples. Mode 1a & 2a: one sam/bam file with single cell. Mode 1b & 2b: one or multiple bulk sam/bam files, no barcodes needed, but sample ids and regionsVCF."
+    example: input.bam, input.sam
   - name: "--sam_index_file"
     type: file
     description: Input SAM/BAM Index file, problem with samFileList.
+    example: input.bai, input.sai
   - name: "--sam_fileList"
     type: file
     description: A list file containing bam files, each per line, for Mode 1b & 2b.
+    example: file_list.txt
   - name: "--regions_vcf"
     type: file
     description: A vcf file listing all candidate SNPs, for fetch each variants. If None, pileup the genome. Needed for bulk samples.
+    example: regions.vcf
   - name: "--targets_vcf"
     type: file
     description: "Similar as --regions_vcf, but the next position is accessed by streaming rather than indexing/jumping (like -T in samtools/bcftools mpileup)."
+    example: targets.vcf
   - name: "--barcode_file"
     type: file
     description: A plain file listing all effective cell barcode.
+    example: barcodes.tsv
   - name: "--sample_list"
     type: file
     description: A list file containing sample IDs, each per line.
+    example: samples.txt
   - name: "--sample_ids"
     type: string
     description: Comma separated sample ids.

src/genetic_demux/demuxlet/config.vsh.yaml

@@ -15,6 +15,7 @@ argument_groups:
   - name: "--sam"
     type: file
     description: Input SAM/BAM/CRAM file. Must be sorted by coordinates and indexed.
+    example: input.bam, input.sam, input.cram
   - name: "--tag_group"
     type: string
     default: 'CB'
@@ -29,6 +30,7 @@ argument_groups:
   - name: "--vcf"
     type: file
     description: Input VCF/BCF file, containing the individual genotypes (GT), posterior probability (GP), or genotype likelihood (PL).
+    example: input.vcf, input.bcf
   - name: "--field"
     type: string
     default: "GT"

src/genetic_demux/dsc_pileup/config.vsh.yaml

@@ -15,6 +15,7 @@ argument_groups:
   - name: "--sam"
     type: file
     description: Input SAM/BAM/CRAM file. Must be sorted by coordinates and indexed.
+    example: input.bam, input.sam, input.cram
   - name: "--tag_group"
     type: string
     default: 'CB'
@@ -30,6 +31,7 @@ argument_groups:
   - name: "--vcf"
     type: file
     description: "Input VCF/BCF file for dsc-pileup, containing the AC and AN field."
+    example: input.vcf, input.bcf
   - name: "--sm"
     type: string
     description: "List of sample IDs to compare to (default: use all)."

src/genetic_demux/freebayes/config.vsh.yaml

@@ -13,30 +13,37 @@ argument_groups:
   - name: "--bam"
     type: file
     description: Add FILE to the set of BAM files to be analyzed.
+    example: input.bam
   - name: "--bam_list"
     type: file
     description: A file containing a list of BAM files to be analyzed.
+    example: bam_list.txt
   - name: "--stdin"
     type: boolean_true
     description: Read BAM input on stdin.
   - name: "--fasta_reference"
     type: file
     description: Use FILE as the reference sequence for analysis. An index file (FILE.fai) will be created if none exists. If neither --targets nor --region are specified, FreeBayes will analyze every position in this reference.
+    example: reference.fasta
   - name: "--fasta_reference_index"
     type: file
     description: Use FILE.fai as the index of reference sequence for analysis.
+    example: file.fai
   - name: "--targets"
     type: file
     description: Limit analysis to targets listed in the BED-format FILE.
+    example: targets.bed
   - name: "--region"
     type: string
     description: Limit analysis to the specified region, 0-base coordinates, end_position not included (same as BED format).
   - name: "--samples"
     type: file
     description: Limit analysis to samples listed (one per line) in the FILE. By default FreeBayes will analyze all samples in its input BAM files.
+    example: samples.txt
   - name: "--populations"
     type: file
     description: Each line of FILE should list a sample and a population which it is part of. The population-based bayesian inference model will then be partitioned on the basis of the populations.
+    example: populations.txt
   - name: "--cnv_map"
     type: file
     description: Read a copy number map from the BED file FILE, which has either a sample-level ploidy or a region-specific format.
@@ -49,6 +56,7 @@ argument_groups:
   - name: "--variant_input"
     type: file
     description: Use variants reported in VCF file as input to the algorithm. Variants in this file will included in the output even if there is not enough support in the data to pass input filters.
+    example: variant_input.vcf
   - name: "--only_use_input_alleles"
     type: boolean_true
     description: Only provide variant calls and genotype likelihoods for sites and alleles which are provided in the VCF input, and provide output in the VCF for all input alleles, not just those which have support in the data.
@@ -199,6 +207,7 @@ argument_groups:
     description: Disable use of aggregate probability of observation balance between alleles as a component of the priors.
   - name: "--observation_bias"
     type: file
+    example: observation_bias.txt
     description: Read length-dependent allele observation biases from FILE. The format is [length] [alignment efficiency relative to reference] where the efficiency is 1 if there is no relative observation bias.
   - name: "--base_quality_cap"
     type: integer
@@ -212,6 +221,7 @@ argument_groups:
     description: Use legacy (polybayes equivalent) genotype likelihood calculations
   - name: "--contamination_estimates"
     type: file
+    example: contamination_estimates.txt
     description: A file containing per-sample estimates of contamination, such as those generated by VerifyBamID.
   - name: "--report_genotype_likelihood_max"
     type: boolean_true

src/genetic_demux/freemuxlet/config.vsh.yaml

@@ -16,6 +16,7 @@ argument_groups:
     description: "Prefix of input files generated by dsc-pileup"
   - name: "--init_cluster"
     type: file
+    example: init_cluster.txt
     description: "Input file containing the initial cluster information."
   - name: "--nsample"
     type: integer

src/genetic_demux/samtools/config.vsh.yaml

@@ -10,6 +10,7 @@ arguments:
     type: file
     required: true
     description: "Input bam file for filtering."
+    example: input.bam
   - name: "--output"
     type: file
     direction: output

src/genetic_demux/scsplit/config.vsh.yaml

@@ -11,19 +11,23 @@ argument_groups:
   - name: "--vcf"
     type: file
     description: VCF from mixed BAM
+    example: input.vcf
   - name: "--bam"
     type: file
     description: mixed sample BAM
+    example: input.bam
   - name: "--bar"
     type: file
     description: barcodes whitelist
+    example: barcodes.txt
   - name: "--tag"
     type: string
     default: "CB"
     description: tag for barcode
   - name: "--com"
     type: file
     description: common SNVs
+    example: common_snvs.txt
   - name: "--num"
     type: integer
     description: expected number of mixed samples
@@ -40,6 +44,7 @@ argument_groups:
     description: correction for doublets. There will be no refinement on the results if this optional parameter is not specified or specified percentage is less than doublet rates detected during the run.
   - name: "--vcf_known"
     type: file
+    example: known_variants.vcf
     description: known individual genotypes to limit distinguishing variants to available variants, so that users do not need to redo genotyping on selected variants, otherwise any variants could be selected as distinguishing variants.
   - name: "--geno"
     type: boolean_true

src/genetic_demux/souporcell/config.vsh.yaml

@@ -11,15 +11,19 @@ argument_groups:
   - name: "--fasta"
     type: file
     description: reference fasta file
+    example: reference.fasta
   - name: "--bam"
     type: file
     description: cellranger bam
+    example: input.bam
   - name: "--bam_index"
     type: file
     description: cellranger bam index
+    example: input.bam.bai
   - name: "--barcodes"
     type: file
     description: barcodes.tsv from cellranger
+    example: barcodes.tsv
   - name: "--clusters"
     type: integer
     description: number cluster, tbd add easy way to run on a range of k
@@ -44,10 +48,12 @@ argument_groups:
     description: number of restarts in clustering, when there are > 12 clusters we recommend increasing this to avoid local minima
   - name: "--common_variants"
     type: file
+    example: common_variants.vcf
     description: common variant loci or known variant loci vcf, must be vs same reference fasta
   - name: "--known_genotypes"
     type: file
-    description: known variants per clone in population vcf mode, must be .vcf right now we dont accept gzip or bcf sorry
+    description: known variants per clone in population vcf mode
+    example: known_variants.vcf
   - name: "--known_genotypes_sample_names"
     type: string
     description: which samples in population vcf from known genotypes option represent the donors in your sample

src/genetic_demux/vireo/config.vsh.yaml

@@ -11,13 +11,15 @@ argument_groups:
   - name: "--cell_data"
     type: file
     description: The cell genotype file in VCF format or cellSNP folder with sparse matrices.
+    example: cell_data.vcf
   - name: "--n_donor"
     type: integer
     default: 2
     description: Number of donors to demultiplex; can be larger than provided in donor_file.
   - name: "--vartrix_data"
     type: file
     description: The cell genotype files in vartrix outputs.
+    example: path/to/vatrix_outputs
   - name: "--donor_file"
     type: file
     description: The donor genotype file in VCF format. Please filter the sample and region with bcftools first!

src/integrate/harmony/config.vsh.yaml

@@ -14,12 +14,14 @@ arguments:
     type: file
     description: Input h5mu file
     direction: input
+    example: input.h5mu
     required: true
   - name: "--output"
     alternatives: ["-o"]
     type: file
     description: Output h5mu file.
     direction: output
+    example: output.h5mu
     required: true
   - name: "--modality"
     type: string