Skip to content

Commit

Permalink
Adding new option for shared resources, i.e. FastQ Screen and Kraken2…
Browse files Browse the repository at this point in the history 
… DBs
  • Loading branch information
@skchronicles
skchronicles committed Oct 25, 2022
1 parent 11ebbe9 commit 3bf833f
Show file tree
Hide file tree
Showing 2 changed files with 316 additions and 36 deletions.
105 changes: 93 additions & 12 deletions rna-seek
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ import argparse # potential python3 3rd party package, added in python/3.5

# Pipeline Metadata and globals
__author__ = 'Skyler Kuhn'
__version__ = 'v1.6.0'
__version__ = 'v1.7.0'
__email__ = '[email protected]'
__home__ = os.path.dirname(os.path.abspath(__file__))
_name = os.path.basename(sys.argv[0])
Expand Down Expand Up @@ -613,12 +613,17 @@ def setup(sub_args, ifiles, repo_path, output_path):
config['options']['star_2_pass_basic'] = sub_args.star_2_pass_basic
config['options']['small_rna'] = sub_args.small_rna
config['options']['tmp_dir'] = sub_args.tmp_dir
config['options']['shared_resources'] = sub_args.shared_resources

# Get latest git commit hash
git_hash = get_repo_git_commit_hash(repo_path)
config['project']['git_commit_hash'] = git_hash


if sub_args.shared_resources:
# Update paths to shared resources directory
config['bin']['rnaseq']['tool_parameters']['FASTQ_SCREEN_CONFIG'] = os.path.join(sub_args.shared_resources, "fastq_screen_db", "fastq_screen_p1.conf")
config['bin']['rnaseq']['tool_parameters']['FASTQ_SCREEN_CONFIG2'] = os.path.join(sub_args.shared_resources, "fastq_screen_db", "fastq_screen_p2.conf")
config['bin']['rnaseq']['tool_parameters']['KRAKENBACDB'] = os.path.join(sub_args.shared_resources, "20180907_standard_kraken2")

# Save config to output directory
print("\nGenerating config file in '{}'... ".format(os.path.join(output_path, 'config.json')), end = "")
Expand Down Expand Up @@ -981,6 +986,7 @@ def _configure(sub_args, filename, git_repo):
fh.write('BUILD_HOME: "{}"\n'.format(git_repo))
fh.write('SMALL_GENOME: "{}"\n'.format(sub_args.small_genome))
fh.write('TMP_DIR: "{}"\n'.format(sub_args.tmp_dir))
fh.write('SHARED_RESOURCES: "{}"\n'.format(sub_args.shared_resources))
fh.write('READLENGTHS:\n')
read_lengths = ['50', '75', '100', '125', '150']
for rl in read_lengths:
Expand Down Expand Up @@ -1032,28 +1038,51 @@ def build(sub_args):
@param sub_args <parser.parse_args() object>:
Parsed arguments for unlock sub-command
"""
# Get PATH to RNA-seek git repository for copying over pipeline resources
# Get PATH to RNA-seek git repository
# for copying over pipeline resources
git_repo = os.path.dirname(os.path.abspath(__file__))

# Build Output directory
output_path = os.path.abspath(sub_args.output)

# Configure build output directory: initialize, copy resources, generate config file
additional_bind_paths = configure_build(sub_args = sub_args, git_repo = git_repo, output_path = output_path)
# Configure build output directory,
# initialize, copy resources, and
# generate config file
additional_bind_paths = configure_build(
sub_args = sub_args,
git_repo = git_repo,
output_path = output_path
)

# Add any additional bindpaths
if sub_args.shared_resources:
# Check if shared resource path
# needs to be added to bindlist
if not sub_args.shared_resources in additional_bind_paths:
additional_bind_paths.append(sub_args.shared_resources)

additional_bind_paths = ','.join(additional_bind_paths)

# Dryrun pipeline
if sub_args.dry_run:
dryrun_output = dryrun(outdir = output_path, config = os.path.join('config', 'build.yml'), snakefile = os.path.join('workflow', 'rules', 'build.smk'))
# python3 returns byte-string representation
print("\nDry-running RNA-seek Reference building pipeline:\n{}".format(dryrun_output.decode("utf-8")))
sys.exit(0)
dryrun_output = dryrun(
outdir = output_path,
config = os.path.join('config', 'build.yml'),
snakefile = os.path.join('workflow', 'rules', 'build.smk')
)

print(
"\nDry-running RNA-seek Reference building pipeline:\n{}".format(
dryrun_output.decode("utf-8")
)
)
sys.exit(0)

# Run RNA-seek reference building pipeline
masterjob = orchestrate(
mode = 'slurm',
outdir = output_path,
additional_bind_paths = [],
additional_bind_paths = additional_bind_paths,
alt_cache = sub_args.singularity_cache,
submission_script = 'builder',
masterjob = 'pl:build',
Expand Down Expand Up @@ -1216,6 +1245,7 @@ def parsed_arguments(name, description):
$ {0} run [--help] \\
[--small-rna] [--star-2-pass-basic] \\
[--dry-run] [--mode {{slurm, local}}] \\
[--shared-resources SHARED_RESOURCES] \\
[--singularity-cache SINGULARITY_CACHE] \\
[--sif-cache SIF_CACHE] \\
[--tmp-dir TMP_DIR] \\
Expand Down Expand Up @@ -1312,6 +1342,23 @@ def parsed_arguments(name, description):
recommended running the pipeline in this mode as it
will be significantly faster.
Example: --mode slurm
--shared-resources Local path to shared resources. The pipeline uses a set
of shared reference files that can be re-used across ref-
erence genomes. These currently include reference files
for kraken and FQScreen. These reference files can be
downloaded with the build sub command's --shared-resources
option. These files only need to be downloaded once. If
you are running the pipeline on Biowulf, you do NOT need
to download these reference files! They already exist on
the filesystem in a location that anyone can acceess. If
you are running the pipeline on another cluster or target
system, you will need to download the shared resources
with the build sub command, and you will need to provide
this option to the run sub command every time. Please
provide the same path that was provided to the build sub
command's --shared-resources option.
Example: --shared-resources /data/shared/rna-seek
--singularity-cache SINGULARITY_CACHE
Overrides the $SINGULARITY_CACHEDIR variable. Images
Expand Down Expand Up @@ -1480,6 +1527,17 @@ def parsed_arguments(name, description):
help = argparse.SUPPRESS
)

# Path to previously downloaded shared
# reference files, see build option for
# more information
subparser_run.add_argument(
'--shared-resources',
type = lambda option: permissions(parser, os.path.abspath(os.path.expanduser(option)), os.R_OK),
required = False,
default = None,
help = argparse.SUPPRESS
)

# Singularity cache directory,
# default uses output directory
subparser_run.add_argument(
Expand Down Expand Up @@ -1535,8 +1593,8 @@ def parsed_arguments(name, description):
{1}{2}Synopsis:{4}
$ {0} build [--help] \\
[--dry-run] [--small-genome] \\
[--singularity-cache SINGULARITY_CACHE] \\
[--shared-resources SHARED_RESOURCES] [--small-genome] \\
[--dry-run] [--singularity-cache SINGULARITY_CACHE] \\
[--sif-cache SIF_CACHE] [--tmp-dir TMP_DIR] \\
--ref-fa REF_FA \\
--ref-name REF_NAME \\
Expand Down Expand Up @@ -1588,6 +1646,20 @@ def parsed_arguments(name, description):
Example: --output /data/$USER/refs/GRCh38_41
{1}{2}Build options:{4}
--shared-resources Path to download shared resources. The pipeline uses a
set of shared reference files that can be re-used across
reference genomes. These currently include reference files
for kraken and FQScreen. With that being said, these files
can be downloaded once in a shared or common location. If
you are running the pipeline on Biowulf, you do NOT need
to download these reference files. They already exist in
an accessible location on the filesystem. If you're setting
up the pipeline on a new cluster or target system, you will
need to provide this option at least one time. The path
provided to this option can be provided to the rna-seek
run sub command via the --shared-resources option.
Example: --shared-resources /data/shared/rna-seek
--small-genome Builds a small genome index. For small genomes, it is
recommeded running STAR with --genomeSAindexNbases value
scaled down. This option runs the build pipeline in a
Expand Down Expand Up @@ -1740,6 +1812,15 @@ def parsed_arguments(name, description):
help = argparse.SUPPRESS
)

# Path to download shared refs
subparser_build.add_argument(
'--shared-resources',
type = lambda option: os.path.abspath(os.path.expanduser(option)),
required = False,
default = None,
help = argparse.SUPPRESS
)

# Small Genome build option for STAR
subparser_build.add_argument(
'--small-genome',
Expand Down
Loading

0 comments on commit 3bf833f

Please sign in to comment.