def _detect_duplicates(bam_file, out_dir, data):
"""
count duplicate percentage
"""
out_file = os.path.join(out_dir, "dup_metrics.txt")
if not utils.file_exists(out_file):
dup_align_bam = postalign.dedup_bam(bam_file, data)
num_cores = dd.get_num_cores(data)
with file_transaction(data, out_file) as tx_out_file:
sambamba = config_utils.get_program("sambamba",
data,
default="sambamba")
dup_count = ("{sambamba} view --nthreads {num_cores} --count "
"-F 'duplicate and not unmapped' "
"{dup_align_bam} >> {tx_out_file}")
message = "Counting duplicates in {bam_file}.".format(
bam_file=bam_file)
do.run(dup_count.format(**locals()), message)
tot_count = ("{sambamba} view --nthreads {num_cores} --count "
"-F 'not unmapped' "
"{dup_align_bam} >> {tx_out_file}")
message = "Counting reads in {bam_file}.".format(bam_file=bam_file)
do.run(tot_count.format(**locals()), message)
with open(out_file) as in_handle:
dupes = float(in_handle.next().strip())
total = float(in_handle.next().strip())
return {"Duplication Rate of Mapped": dupes / total}
def _detect_duplicates(bam_file, out_dir, data):
"""
count duplicate percentage
"""
out_file = os.path.join(out_dir, "dup_metrics.txt")
if not utils.file_exists(out_file):
dup_align_bam = postalign.dedup_bam(bam_file, data)
logger.info("Detecting duplicates in %s." % dup_align_bam)
dup_count = readstats.number_of_mapped_reads(data,
dup_align_bam,
keep_dups=False)
tot_count = readstats.number_of_mapped_reads(data,
dup_align_bam,
keep_dups=True)
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
out_handle.write("%s\n%s\n" % (dup_count, tot_count))
with open(out_file) as in_handle:
dupes = float(next(in_handle).strip())
total = float(next(in_handle).strip())
if total == 0:
rate = "NA"
else:
rate = dupes / total
return {"Duplication Rate of Mapped": rate}
def process_alignment(data, alt_input=None):
"""Do an alignment of fastq files, preparing a sorted BAM output file.
"""
fastq1, fastq2 = dd.get_input_sequence_files(data)
if alt_input:
fastq1, fastq2 = alt_input
config = data["config"]
aligner = config["algorithm"].get("aligner", None)
if fastq1 and objectstore.file_exists_or_remote(fastq1) and aligner:
logger.info("Aligning lane %s with %s aligner" %
(data["rgnames"]["lane"], aligner))
data = align_to_sort_bam(fastq1, fastq2, aligner, data)
data = _add_supplemental_bams(data)
elif fastq1 and os.path.exists(fastq1) and fastq1.endswith(".bam"):
sort_method = config["algorithm"].get("bam_sort")
bamclean = config["algorithm"].get("bam_clean")
if bamclean is True or bamclean == "picard":
if sort_method and sort_method != "coordinate":
raise ValueError(
"Cannot specify `bam_clean: picard` with `bam_sort` other than coordinate: %s"
% sort_method)
out_bam = cleanbam.picard_prep(fastq1, data["rgnames"],
data["sam_ref"], data["dirs"], data)
elif sort_method:
runner = broad.runner_from_config(config)
out_file = os.path.join(
data["dirs"]["work"], "{}-sort.bam".format(
os.path.splitext(os.path.basename(fastq1))[0]))
out_bam = runner.run_fn("picard_sort", fastq1, sort_method,
out_file)
else:
out_bam = link_bam_file(
fastq1,
os.path.join(data["dirs"]["work"], "prealign",
data["rgnames"]["sample"]))
bam.index(out_bam, data["config"])
bam.check_header(out_bam, data["rgnames"], data["sam_ref"],
data["config"])
dedup_bam = postalign.dedup_bam(out_bam, data)
bam.index(dedup_bam, data["config"])
data["work_bam"] = dedup_bam
elif fastq1 and objectstore.file_exists_or_remote(
fastq1) and fastq1.endswith(".cram"):
data["work_bam"] = fastq1
elif fastq1 is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = False
data["work_bam"] = None
elif not fastq1:
raise ValueError("No 'files' specified for input sample: %s" %
dd.get_sample_name(data))
else:
raise ValueError(
"Could not process input file from sample configuration. \n" +
fastq1 + "\nIs the path to the file correct?\n" +
"If it is a fastq file (not pre-aligned BAM or CRAM), "
"is an aligner specified in the input configuration?")
return [[data]]
def process_alignment(data, alt_input=None):
"""Do an alignment of fastq files, preparing a sorted BAM output file.
"""
data = utils.to_single_data(data)
fastq1, fastq2 = dd.get_input_sequence_files(data)
if alt_input:
fastq1, fastq2 = alt_input
config = data["config"]
aligner = config["algorithm"].get("aligner", None)
if fastq1 and objectstore.file_exists_or_remote(fastq1) and aligner:
logger.info("Aligning lane %s with %s aligner" % (data["rgnames"]["lane"], aligner))
data = align_to_sort_bam(fastq1, fastq2, aligner, data)
data = _add_supplemental_bams(data)
elif fastq1 and objectstore.file_exists_or_remote(fastq1) and fastq1.endswith(".bam"):
sort_method = config["algorithm"].get("bam_sort")
bamclean = config["algorithm"].get("bam_clean")
if bamclean is True or bamclean == "picard":
if sort_method and sort_method != "coordinate":
raise ValueError("Cannot specify `bam_clean: picard` with `bam_sort` other than coordinate: %s"
% sort_method)
out_bam = cleanbam.picard_prep(fastq1, data["rgnames"], dd.get_ref_file(data), data["dirs"],
data)
elif bamclean == "fixrg":
out_bam = cleanbam.fixrg(fastq1, data["rgnames"], dd.get_ref_file(data), data["dirs"], data)
elif sort_method:
runner = broad.runner_from_path("picard", config)
out_file = os.path.join(data["dirs"]["work"], "{}-sort.bam".format(
os.path.splitext(os.path.basename(fastq1))[0]))
out_bam = runner.run_fn("picard_sort", fastq1, sort_method, out_file)
else:
out_bam = link_bam_file(fastq1, os.path.join(data["dirs"]["work"], "prealign",
data["rgnames"]["sample"]))
bam.index(out_bam, data["config"])
bam.check_header(out_bam, data["rgnames"], dd.get_ref_file(data), data["config"])
dedup_bam = postalign.dedup_bam(out_bam, data)
bam.index(dedup_bam, data["config"])
data["work_bam"] = dedup_bam
elif fastq1 and objectstore.file_exists_or_remote(fastq1) and fastq1.endswith(".cram"):
data["work_bam"] = fastq1
elif fastq1 is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = False
data["work_bam"] = None
elif not fastq1:
raise ValueError("No 'files' specified for input sample: %s" % dd.get_sample_name(data))
else:
raise ValueError("Could not process input file from sample configuration. \n" +
fastq1 +
"\nIs the path to the file correct or is empty?\n" +
"If it is a fastq file (not pre-aligned BAM or CRAM), "
"is an aligner specified in the input configuration?")
if data.get("work_bam"):
# Add stable 'align_bam' target to use for retrieving raw alignment
data["align_bam"] = data["work_bam"]
data = _add_hla_files(data)
return [[data]]
def process_alignment(data):
"""Do an alignment of fastq files, preparing a sorted BAM output file.
"""
if "files" not in data:
fastq1, fastq2 = None, None
elif len(data["files"]) == 2:
fastq1, fastq2 = data["files"]
else:
assert len(data["files"]) == 1, data["files"]
fastq1, fastq2 = data["files"][0], None
config = data["config"]
aligner = config["algorithm"].get("aligner", None)
if fastq1 and utils.file_exists_or_remote(fastq1) and aligner:
logger.info("Aligning lane %s with %s aligner" %
(data["rgnames"]["lane"], aligner))
data = align_to_sort_bam(fastq1, fastq2, aligner, data)
data = _add_supplemental_bams(data)
elif fastq1 and os.path.exists(fastq1) and fastq1.endswith(".bam"):
sort_method = config["algorithm"].get("bam_sort")
bamclean = config["algorithm"].get("bam_clean")
if bamclean is True or bamclean == "picard":
if sort_method and sort_method != "coordinate":
raise ValueError(
"Cannot specify `bam_clean: picard` with `bam_sort` other than coordinate: %s"
% sort_method)
out_bam = cleanbam.picard_prep(fastq1, data["rgnames"],
data["sam_ref"], data["dirs"], data)
elif sort_method:
runner = broad.runner_from_config(config)
out_file = os.path.join(
data["dirs"]["work"], "{}-sort.bam".format(
os.path.splitext(os.path.basename(fastq1))[0]))
out_bam = runner.run_fn("picard_sort", fastq1, sort_method,
out_file)
else:
out_bam = link_bam_file(
fastq1,
os.path.join(data["dirs"]["work"], "prealign",
data["rgnames"]["sample"]))
bam.check_header(out_bam, data["rgnames"], data["sam_ref"],
data["config"])
dedup_bam = postalign.dedup_bam(out_bam, data)
data["work_bam"] = dedup_bam
elif fastq1 and utils.file_exists_or_remote(fastq1) and fastq1.endswith(
".cram"):
data["work_bam"] = fastq1
elif fastq1 is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = False
data["work_bam"] = None
else:
raise ValueError("Could not process input file: %s" % fastq1)
return [[data]]
def process_alignment(data):
"""Do an alignment of fastq files, preparing a sorted BAM output file.
"""
if "files" not in data:
fastq1, fastq2 = None, None
elif len(data["files"]) == 2:
fastq1, fastq2 = data["files"]
else:
assert len(data["files"]) == 1, data["files"]
fastq1, fastq2 = data["files"][0], None
config = data["config"]
aligner = config["algorithm"].get("aligner", None)
if fastq1 and os.path.exists(fastq1) and aligner:
logger.info("Aligning lane %s with %s aligner" % (data["rgnames"]["lane"], aligner))
data = align_to_sort_bam(fastq1, fastq2, aligner, data)
data = _add_supplemental_bams(data)
elif fastq1 and os.path.exists(fastq1) and fastq1.endswith(".bam"):
sort_method = config["algorithm"].get("bam_sort")
bamclean = config["algorithm"].get("bam_clean")
if bamclean is True or bamclean == "picard":
if sort_method and sort_method != "coordinate":
raise ValueError(
"Cannot specify `bam_clean: picard` with `bam_sort` other than coordinate: %s" % sort_method
)
out_bam = cleanbam.picard_prep(fastq1, data["rgnames"], data["sam_ref"], data["dirs"], data)
elif sort_method:
runner = broad.runner_from_config(config)
out_file = os.path.join(
data["dirs"]["work"], "{}-sort.bam".format(os.path.splitext(os.path.basename(fastq1))[0])
)
out_bam = runner.run_fn("picard_sort", fastq1, sort_method, out_file)
else:
out_bam = link_bam_file(fastq1, os.path.join(data["dirs"]["work"], "prealign", data["rgnames"]["sample"]))
bam.check_header(out_bam, data["rgnames"], data["sam_ref"], data["config"])
dedup_bam = postalign.dedup_bam(out_bam, data)
data["work_bam"] = dedup_bam
elif fastq1 and os.path.exists(fastq1) and fastq1.endswith(".cram"):
data["work_bam"] = fastq1
elif fastq1 is None and "vrn_file" in data:
data["config"]["algorithm"]["variantcaller"] = False
data["work_bam"] = None
else:
raise ValueError("Could not process input file: %s" % fastq1)
return [[data]]
def _detect_duplicates(bam_file, out_dir, data):
"""
count duplicate percentage
"""
out_file = os.path.join(out_dir, "dup_metrics.txt")
if not utils.file_exists(out_file):
dup_align_bam = postalign.dedup_bam(bam_file, data)
logger.info("Detecting duplicates in %s." % dup_align_bam)
dup_count = readstats.number_of_mapped_reads(data, dup_align_bam, keep_dups=False)
tot_count = readstats.number_of_mapped_reads(data, dup_align_bam, keep_dups=True)
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
out_handle.write("%s\n%s\n" % (dup_count, tot_count))
with open(out_file) as in_handle:
dupes = float(next(in_handle).strip())
total = float(next(in_handle).strip())
if total == 0:
rate = "NA"
else:
rate = dupes / total
return {"Duplication Rate of Mapped": rate}
def _detect_duplicates(bam_file, out_dir, data):
"""
count duplicate percentage
"""
out_file = os.path.join(out_dir, "dup_metrics.txt")
if not utils.file_exists(out_file):
dup_align_bam = dedup_bam(bam_file, data)
num_cores = dd.get_num_cores(data)
with file_transaction(out_file) as tx_out_file:
sambamba = config_utils.get_program("sambamba", data, default="sambamba")
dup_count = ("{sambamba} view --nthreads {num_cores} --count "
"-F 'duplicate and not unmapped' "
"{bam_file} >> {tx_out_file}")
message = "Counting duplicates in {bam_file}.".format(bam_file=bam_file)
do.run(dup_count.format(**locals()), message)
tot_count = ("{sambamba} view --nthreads {num_cores} --count "
"-F 'not unmapped' "
"{bam_file} >> {tx_out_file}")
message = "Counting reads in {bam_file}.".format(bam_file=bam_file)
do.run(tot_count.format(**locals()), message)
with open(out_file) as in_handle:
dupes = float(in_handle.next().strip())
total = float(in_handle.next().strip())
return {"Duplication Rate of Mapped": dupes / total}
def rnaseq_gatk_variant_calling(data):
data = dd.set_deduped_bam(data, dedup_bam(dd.get_work_bam(data), data))
data = gatk_splitreads(data)
data = gatk_rnaseq_calling(data)
return data
def process_alignment(data, alt_input=None):
"""Do an alignment of fastq files, preparing a sorted BAM output file.
"""
data = cwlutils.normalize_missing(utils.to_single_data(data))
data = cwlutils.unpack_tarballs(data, data)
fastq1, fastq2 = dd.get_input_sequence_files(data)
if alt_input:
fastq1, fastq2 = alt_input
config = data["config"]
aligner = config["algorithm"].get("aligner", None)
if fastq1 and objectstore.file_exists_or_remote(fastq1) and aligner:
logger.info("Aligning lane %s with %s aligner" %
(data["rgnames"]["lane"], aligner))
data = align_to_sort_bam(fastq1, fastq2, aligner, data)
if dd.get_correct_umis(data):
data["work_bam"] = postalign.correct_umis(data)
if dd.get_umi_consensus(data):
data["umi_bam"] = dd.get_work_bam(data)
if fastq2:
f1, f2, avg_cov = postalign.umi_consensus(data)
data["config"]["algorithm"]["rawumi_avg_cov"] = avg_cov
del data["config"]["algorithm"]["umi_type"]
data["config"]["algorithm"]["mark_duplicates"] = False
data = align_to_sort_bam(f1, f2, aligner, data)
else:
raise ValueError(
"Single fastq input for UMI processing; fgbio needs paired reads: %s"
% dd.get_sample_name(data))
data = _add_supplemental_bams(data)
elif fastq1 and objectstore.file_exists_or_remote(
fastq1) and fastq1.endswith(".bam"):
sort_method = config["algorithm"].get("bam_sort")
bamclean = config["algorithm"].get("bam_clean")
if bamclean is True or bamclean == "picard":
if sort_method and sort_method != "coordinate":
raise ValueError(
"Cannot specify `bam_clean: picard` with `bam_sort` other than coordinate: %s"
% sort_method)
ref_file = dd.get_ref_file(data)
out_bam = cleanbam.picard_prep(fastq1, data["rgnames"], ref_file,
data["dirs"], data)
elif bamclean == "fixrg":
out_bam = cleanbam.fixrg(fastq1, data["rgnames"],
dd.get_ref_file(data), data["dirs"], data)
elif bamclean == "remove_extracontigs":
out_bam = cleanbam.remove_extracontigs(fastq1, data)
elif sort_method:
runner = broad.runner_from_path("picard", config)
out_file = os.path.join(
data["dirs"]["work"], "{}-sort.bam".format(
os.path.splitext(os.path.basename(fastq1))[0]))
if not utils.file_exists(out_file):
work_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "bamclean",
dd.get_sample_name(data)))
out_file = os.path.join(
work_dir, "{}-sort.bam".format(dd.get_sample_name(data)))
out_bam = runner.run_fn("picard_sort", fastq1, sort_method,
out_file)
else:
out_bam = _link_bam_file(
fastq1,
os.path.join(dd.get_work_dir(data), "prealign",
dd.get_sample_name(data)), data)
bam.index(out_bam, data["config"])
bam.check_header(out_bam, data["rgnames"], dd.get_ref_file(data),
data["config"])
dedup_bam = postalign.dedup_bam(out_bam, data)
bam.index(dedup_bam, data["config"])
data["work_bam"] = dedup_bam
elif fastq1 and objectstore.file_exists_or_remote(
fastq1) and fastq1.endswith(".cram"):
data["work_bam"] = fastq1
elif fastq1 is None and not dd.get_aligner(data):
data["config"]["algorithm"]["variantcaller"] = False
data["work_bam"] = None
elif not fastq1:
raise ValueError("No 'files' specified for input sample: %s" %
dd.get_sample_name(data))
elif "kraken" in config["algorithm"]: # kraken doesn's need bam
pass
else:
raise ValueError(
"Could not process input file from sample configuration. \n" +
fastq1 + "\nIs the path to the file correct or is empty?\n" +
"If it is a fastq file (not pre-aligned BAM or CRAM), "
"is an aligner specified in the input configuration?")
if data.get("work_bam"):
# Add stable 'align_bam' target to use for retrieving raw alignment
data["align_bam"] = data["work_bam"]
data = _add_hla_files(data)
return [[data]]
