def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
data = cwlutils.normalize_missing(utils.to_single_data(data))
data = cwlutils.unpack_tarballs(data, data)
bam_file = data.get("align_bam") or data.get("work_bam")
ref_file = dd.get_ref_file(data)
if vmulti.bam_needs_processing(data) and bam_file and bam_file.endswith(".bam"):
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data)))
bam_file_ready = os.path.join(out_dir, os.path.basename(bam_file))
if not utils.file_exists(bam_file_ready):
utils.symlink_plus(bam_file, bam_file_ready)
bam.index(bam_file_ready, data["config"])
covinfo = callable.sample_callable_bed(bam_file_ready, ref_file, data)
callable_region_bed, nblock_bed = \
callable.block_regions(covinfo.raw_callable, bam_file_ready, ref_file, data)
data["regions"] = {"nblock": nblock_bed,
"callable": covinfo.raw_callable,
"sample_callable": covinfo.callable,
"mapped_stats": readstats.get_cache_file(data)}
data["depth"] = covinfo.depth_files
data = coverage.assign_interval(data)
data = samtools.run_and_save(data)
data = recalibrate.prep_recal(data)
data = recalibrate.apply_recal(data)
elif dd.get_variant_regions(data):
callable_region_bed, nblock_bed = \
callable.block_regions(dd.get_variant_regions(data), bam_file, ref_file, data)
data["regions"] = {"nblock": nblock_bed, "callable": dd.get_variant_regions(data),
"sample_callable": dd.get_variant_regions(data)}
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if vmulti.bam_needs_processing(data) and data["work_bam"].endswith(".bam"):
ref_file = dd.get_ref_file(data)
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], ref_file, data)
highdepth_bed = highdepth.identify(data)
bam.index(data["work_bam"], data["config"])
sample_callable = callable.sample_callable_bed(data["work_bam"],
ref_file, data)
offtarget_stats = callable.calculate_offtarget(data["work_bam"],
ref_file, data)
data["regions"] = {
"nblock": nblock_bed,
"callable": callable_bed,
"highdepth": highdepth_bed,
"sample_callable": sample_callable,
"offtarget_stats": offtarget_stats
}
data = coverage.assign_interval(data)
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
data = cwlutils.normalize_missing(utils.to_single_data(data))
bam_file = data.get("align_bam") or data.get("work_bam")
if vmulti.bam_needs_processing(data) and bam_file and bam_file.endswith(
".bam"):
ref_file = dd.get_ref_file(data)
out_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data)))
bam_file_ready = os.path.join(out_dir, os.path.basename(bam_file))
if not utils.file_exists(bam_file_ready):
utils.symlink_plus(bam_file, bam_file_ready)
bam.index(bam_file_ready, data["config"])
covinfo = callable.sample_callable_bed(bam_file_ready, ref_file, data)
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(covinfo.raw_callable, bam_file_ready, ref_file, data)
data["regions"] = {
"nblock": nblock_bed,
"callable": callable_bed,
"highdepth": covinfo.highdepth,
"sample_callable": covinfo.callable,
"coverage_depth_bed": covinfo.depth,
"avg_coverage": covinfo.avg_coverage
}
data = coverage.assign_interval(data)
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data = clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
data = utils.to_single_data(data)
bam_file = data.get("align_bam") or data.get("work_bam")
if vmulti.bam_needs_processing(data) and bam_file and bam_file.endswith(".bam"):
ref_file = dd.get_ref_file(data)
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data)))
bam_file_ready = os.path.join(out_dir, os.path.basename(bam_file))
if not utils.file_exists(bam_file_ready):
utils.symlink_plus(bam_file, bam_file_ready)
bam.index(bam_file_ready, data["config"])
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(bam_file_ready, ref_file, data)
sample_callable = callable.sample_callable_bed(bam_file_ready, ref_file, data)
offtarget_stats = callable.calculate_offtarget(bam_file_ready, ref_file, data)
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed,
"sample_callable": sample_callable,
"offtarget_stats": offtarget_stats}
data = coverage.assign_interval(data)
highdepth_bed = highdepth.identify(data)
data["regions"]["highdepth"] = highdepth_bed
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
data = cwlutils.normalize_missing(utils.to_single_data(data))
data = cwlutils.unpack_tarballs(data, data)
bam_file = data.get("align_bam") or data.get("work_bam")
if vmulti.bam_needs_processing(data) and bam_file and bam_file.endswith(
".bam"):
ref_file = dd.get_ref_file(data)
out_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data)))
bam_file_ready = os.path.join(out_dir, os.path.basename(bam_file))
if not utils.file_exists(bam_file_ready):
utils.symlink_plus(bam_file, bam_file_ready)
bam.index(bam_file_ready, data["config"])
covinfo = callable.sample_callable_bed(bam_file_ready, ref_file, data)
callable_region_bed, nblock_bed = \
callable.block_regions(covinfo.raw_callable, bam_file_ready, ref_file, data)
data["regions"] = {
"nblock": nblock_bed,
"callable": covinfo.raw_callable,
"sample_callable": covinfo.callable,
"mapped_stats": readstats.get_cache_file(data)
}
data["depth"] = covinfo.depth_files
data = coverage.assign_interval(data)
data = samtools.run_and_save(data)
data = recalibrate.prep_recal(data)
data = recalibrate.apply_recal(data)
return [[data]]
def align_prep_full(fastq1, fastq2, info, lane_name, lane_desc, dirs, config,
config_file):
"""Perform alignment and post-processing required on full BAM files.
Prepare list of callable genome regions allowing subsequent parallelization.
"""
if fastq1 is None and "vrn_file" in info:
_, ref_file = get_genome_ref(info["genome_build"], None,
dirs["galaxy"])
config["algorithm"]["variantcaller"] = ""
data = {
"info": info,
"sam_ref": ref_file,
"work_bam": None,
"genome_build": info["genome_build"],
"name": ("", lane_desc),
"vrn_file": info["vrn_file"],
"dirs": copy.deepcopy(dirs),
"config": config
}
else:
align_out = process_alignment(fastq1, fastq2, info, lane_name,
lane_desc, dirs, config)[0]
data = _organize_merge_samples(align_out, dirs, config_file)
callable_region_bed, analysis_regions = callable.block_regions(
data["work_bam"], data["sam_ref"], config)
data["regions"] = analysis_regions
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def align_prep_full(fastq1, fastq2, info, lane_name, lane_desc,
dirs, config, config_file):
"""Perform alignment and post-processing required on full BAM files.
Prepare list of callable genome regions allowing subsequent parallelization.
"""
if fastq1 is None and "vrn_file" in info:
_, ref_file = get_genome_ref(info["genome_build"], None, dirs["galaxy"])
config["algorithm"]["variantcaller"] = ""
data = {"info": info, "sam_ref": ref_file,
"work_bam": None,
"genome_build": info["genome_build"],
"name": ("", lane_desc),
"vrn_file": info["vrn_file"],
"dirs": copy.deepcopy(dirs), "config": config}
else:
align_out = process_alignment(fastq1, fastq2, info, lane_name, lane_desc,
dirs, config)[0]
data = _organize_merge_samples(align_out, dirs, config_file)
callable_region_bed, analysis_regions = callable.block_regions(data["work_bam"],
data["sam_ref"], config)
data["regions"] = analysis_regions
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def align_prep_full(fastq1, fastq2, info, lane_name, lane_desc,
dirs, config, config_file):
"""Perform alignment and post-processing required on full BAM files.
Prepare list of callable genome regions allowing subsequent parallelization.
"""
align_out = process_alignment(fastq1, fastq2, info, lane_name, lane_desc,
dirs, config)[0]
data = _organize_merge_samples(align_out, dirs, config_file)
data["regions"] = callable.block_regions(data["work_bam"],
data["sam_ref"], config)
data = _recal_no_markduplicates(data)
return [data]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if data["work_bam"]:
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if vmulti.bam_needs_processing(data) and data["work_bam"].endswith(".bam"):
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if data["work_bam"]:
callable_region_bed, nblock_bed = callable.block_regions(data["work_bam"],
data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
Cleans input BED files to avoid issues with overlapping input segments.
"""
data = bedutils.clean_inputs(data)
if vmulti.bam_needs_processing(data):
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [data]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
Cleans input BED files to avoid issues with overlapping input segments.
"""
data = bedutils.clean_inputs(data)
if data["work_bam"]:
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [data]
def align_prep_full(data, config_file):
"""Perform alignment and post-processing required on full BAM files.
Prepare list of callable genome regions allowing subsequent parallelization.
"""
if data["files"][0] is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = ""
data["work_bam"] = None
else:
data = process_alignment(data)[0][0]
callable_region_bed, nblock_bed = callable.block_regions(data["work_bam"],
data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed}
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def align_prep_full(data, config_file):
"""Perform alignment and post-processing required on full BAM files.
Prepare list of callable genome regions allowing subsequent parallelization.
"""
if data["files"][0] is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = ""
data["work_bam"] = None
else:
data = process_alignment(data)[0][0]
callable_region_bed, nblock_bed = callable.block_regions(
data["work_bam"], data["sam_ref"], data["config"])
data["regions"] = {"nblock": nblock_bed}
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data["callable_bam"] = data["work_bam"]
data = _recal_no_markduplicates(data)
return [data]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if vmulti.bam_needs_processing(data) and data["work_bam"].endswith(".bam"):
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], data["sam_ref"], data["config"])
highdepth_bed = highdepth.identify(data)
data["regions"] = {
"nblock": nblock_bed,
"callable": callable_bed,
"highdepth": highdepth_bed
}
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
if vmulti.bam_needs_processing(data) and data["work_bam"].endswith(".bam"):
ref_file = dd.get_ref_file(data)
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(data["work_bam"], ref_file, data)
highdepth_bed = highdepth.identify(data)
sample_callable = callable.sample_callable_bed(data["work_bam"], ref_file, data)
offtarget_stats = callable.calculate_offtarget(data["work_bam"], ref_file, data)
data["regions"] = {"nblock": nblock_bed, "callable": callable_bed, "highdepth": highdepth_bed,
"sample_callable": sample_callable,
"offtarget_stats": offtarget_stats}
data = coverage.assign_interval(data)
if (os.path.exists(callable_region_bed) and
not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"]["variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]