def parallel_callable_loci(in_bam, ref_file, data):
config = copy.deepcopy(data["config"])
num_cores = config["algorithm"].get("num_cores", 1)
out_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "align", dd.get_sample_name(data)))
data = {
"work_bam": in_bam,
"config": config,
"reference": data["reference"],
"dirs": {
"out": out_dir
}
}
parallel = {
"type": "local",
"cores": num_cores,
"module": "bcbio.distributed"
}
items = [[data]]
with prun.start(parallel, items, config,
multiplier=int(num_cores)) as runner:
split_fn = shared.process_bam_by_chromosome("-callable.bed",
"work_bam",
remove_alts=True)
out = parallel_split_combine(items, split_fn, runner,
"calc_callable_loci", "combine_bed",
"callable_bed", ["config"])[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, config):
num_cores = config["algorithm"].get("num_cores", 1)
config = copy.deepcopy(config)
data = {
"work_bam": in_bam,
"config": config,
"reference": {
"fasta": {
"base": ref_file
}
}
}
parallel = {
"type": "local",
"cores": num_cores,
"module": "bcbio.distributed"
}
items = [[data]]
with prun.start(parallel, items, config,
multiplier=int(num_cores)) as runner:
split_fn = shared.process_bam_by_chromosome("-callable.bed",
"work_bam")
out = parallel_split_combine(items, split_fn, runner,
"calc_callable_loci", "combine_bed",
"callable_bed", ["config"])[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, config):
num_cores = config["algorithm"].get("num_cores", 1)
data = {"work_bam": in_bam, "sam_ref": ref_file, "config": config}
parallel = {"type": "local", "cores": num_cores, "module": "bcbio.distributed"}
runner = parallel_runner(parallel, {}, config)
split_fn = shared.process_bam_by_chromosome("-callable.bed", "work_bam")
out = parallel_split_combine([[data]], split_fn, runner,
"calc_callable_loci", "combine_bed",
"callable_bed", ["config"])[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, data):
config = copy.deepcopy(data["config"])
num_cores = config["algorithm"].get("num_cores", 1)
data = {"work_bam": in_bam, "config": config, "reference": data["reference"]}
parallel = {"type": "local", "cores": num_cores, "module": "bcbio.distributed"}
items = [[data]]
with prun.start(parallel, items, config, multiplier=int(num_cores)) as runner:
split_fn = shared.process_bam_by_chromosome("-callable.bed", "work_bam", remove_alts=True)
out = parallel_split_combine(
items, split_fn, runner, "calc_callable_loci", "combine_bed", "callable_bed", ["config"]
)[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, config):
num_cores = config["algorithm"].get("num_cores", 1)
config = copy.deepcopy(config)
config["algorithm"]["memory_adjust"] = {"direction": "decrease", "magnitude": 2}
data = {"work_bam": in_bam, "sam_ref": ref_file, "config": config}
parallel = {"type": "local", "cores": num_cores, "module": "bcbio.distributed"}
items = [[data]]
with prun.start(parallel, items, config) as runner:
split_fn = shared.process_bam_by_chromosome("-callable.bed", "work_bam")
out = parallel_split_combine(
items, split_fn, runner, "calc_callable_loci", "combine_bed", "callable_bed", ["config"]
)[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, config):
num_cores = config["algorithm"].get("num_cores", 1)
config = copy.deepcopy(config)
config["algorithm"]["memory_adjust"] = {"direction": "decrease", "magnitude": 2}
data = {"work_bam": in_bam, "sam_ref": ref_file, "config": config}
parallel = {"type": "local", "cores": num_cores, "module": "bcbio.distributed"}
items = [[data]]
with prun.start(parallel, items, config, multiplier=int(num_cores)) as runner:
split_fn = shared.process_bam_by_chromosome("-callable.bed", "work_bam")
out = parallel_split_combine(items, split_fn, runner,
"calc_callable_loci", "combine_bed",
"callable_bed", ["config"])[0]
return out[0]["callable_bed"]
def parallel_callable_loci(in_bam, ref_file, config):
num_cores = config["algorithm"].get("num_cores", 1)
data = {"work_bam": in_bam, "sam_ref": ref_file, "config": config}
parallel = {
"type": "local",
"cores": num_cores,
"module": "bcbio.distributed"
}
runner = parallel_runner(parallel, {}, config)
split_fn = shared.process_bam_by_chromosome("-callable.bed", "work_bam")
out = parallel_split_combine([[data]], split_fn, runner,
"calc_callable_loci", "combine_bed",
"callable_bed", ["config"])[0]
return out[0]["callable_bed"]
def parallel_realign_sample(sample_info, parallel_fn):
"""Realign samples, running in parallel over individual chromosomes.
"""
to_process = []
finished = []
for x in sample_info:
if x[0]["config"]["algorithm"].get("realign", True):
to_process.append(x)
else:
finished.append(x)
if len(to_process) > 0:
file_key = "work_bam"
split_fn = process_bam_by_chromosome("-realign.bam", file_key,
default_targets=["nochr"])
processed = parallel_split_combine(to_process, split_fn, parallel_fn,
"realign_sample", "combine_bam",
file_key, ["config"])
finished.extend(processed)
return finished
def parallel_variantcall(sample_info, parallel_fn):
"""Provide sample genotyping, running in parallel over individual chromosomes.
"""
to_process = []
finished = []
for x in sample_info:
if x[0]["config"]["algorithm"]["snpcall"]:
to_process.extend(_handle_multiple_variantcallers(x))
else:
finished.append(x)
if len(to_process) > 0:
split_fn = process_bam_by_chromosome("-variants.vcf", "work_bam",
dir_ext_fn = _get_variantcaller)
processed = parallel_split_combine(to_process, split_fn, parallel_fn,
"variantcall_sample",
"combine_variant_files",
"vrn_file", ["sam_ref", "config"])
finished.extend(processed)
return finished
def parallel_variantcall(sample_info, parallel_fn):
"""Provide sample genotyping, running in parallel over individual chromosomes.
"""
to_process = []
finished = []
for x in sample_info:
if get_variantcaller(x[0]):
to_process.extend(handle_multiple_variantcallers(x))
else:
finished.append(x)
if len(to_process) > 0:
split_fn = process_bam_by_chromosome("-variants.vcf", "work_bam",
dir_ext_fn=get_variantcaller)
processed = grouped_parallel_split_combine(
to_process, split_fn, multi.group_batches, parallel_fn,
"variantcall_sample", "split_variants_by_sample", "combine_variant_files",
"vrn_file", ["sam_ref", "config"])
finished.extend(processed)
return finished
def parallel_variantcall(sample_info, parallel_fn):
"""Provide sample genotyping, running in parallel over individual chromosomes.
"""
to_process = []
finished = []
for x in sample_info:
if get_variantcaller(x[0]):
to_process.extend(handle_multiple_variantcallers(x))
else:
finished.append(x)
if len(to_process) > 0:
split_fn = process_bam_by_chromosome("-variants.vcf.gz", "work_bam",
dir_ext_fn=get_variantcaller)
processed = grouped_parallel_split_combine(
to_process, split_fn, multi.group_batches, parallel_fn,
"variantcall_sample", "split_variants_by_sample", "combine_variant_files",
"vrn_file", ["sam_ref", "config"])
finished.extend(processed)
return finished
def parallel_realign_sample(sample_info, parallel_fn):
"""Realign samples, running in parallel over individual chromosomes.
"""
to_process = []
finished = []
for x in sample_info:
if x[0]["config"]["algorithm"].get("realign", True):
to_process.append(x)
else:
finished.append(x)
if len(to_process) > 0:
file_key = "work_bam"
split_fn = process_bam_by_chromosome("-realign.bam",
file_key,
default_targets=["nochr"])
processed = parallel_split_combine(to_process, split_fn, parallel_fn,
"realign_sample", "combine_bam",
file_key, ["config"])
finished.extend(processed)
return finished
def parallel_write_recal_bam(xs, parallel_fn):
"""Rewrite a recalibrated BAM file in parallel, working off each chromosome.
"""
to_process = []
finished = []
for x in xs:
if x[0]["config"]["algorithm"].get("recalibrate", True):
to_process.append(x)
else:
finished.append(x)
if len(to_process) > 0:
file_key = "work_bam"
split_fn = process_bam_by_chromosome("-gatkrecal.bam", file_key,
default_targets=["nochr"])
processed = parallel_split_combine(to_process, split_fn, parallel_fn,
"write_recal_bam", "combine_bam",
file_key, ["config"])
finished.extend(processed)
# Save diskspace from original to recalibrated
#save_diskspace(data["work_bam"], "Recalibrated to %s" % recal_bam,
# data["config"])
return finished
def parallel_write_recal_bam(xs, parallel_fn):
"""Rewrite a recalibrated BAM file in parallel, working off each chromosome.
"""
to_process = []
finished = []
for x in xs:
if x[0]["config"]["algorithm"].get("recalibrate", True):
to_process.append(x)
else:
finished.append(x)
if len(to_process) > 0:
file_key = "work_bam"
split_fn = process_bam_by_chromosome("-gatkrecal.bam",
file_key,
default_targets=["nochr"])
processed = parallel_split_combine(to_process, split_fn, parallel_fn,
"write_recal_bam", "combine_bam",
file_key, ["config"])
finished.extend(processed)
# Save diskspace from original to recalibrated
#save_diskspace(data["work_bam"], "Recalibrated to %s" % recal_bam,
# data["config"])
return finished
