def run(name, chip_bam, input_bam, genome_build, out_dir, config):
"""
Run macs2 for chip and input samples avoiding
errors due to samples.
"""
# output file name need to have the caller name
out_file = os.path.join(out_dir, name + "_peaks_macs2.xls")
macs2_file = os.path.join(out_dir, name + "_peaks.xls")
if utils.file_exists(out_file):
return out_file
macs2 = config_utils.get_program("macs2", config)
options = " ".join(config_utils.get_resources("macs2", config).get("options", ""))
if genome_build not in HS and options.find("-g") == -1:
raise ValueError("This %s genome doesn't have a pre-set value."
"You can add specific values using resources "
"option for macs2 in the YAML file (-g genome_size)."
"Check Chip-seq configuration in "
"bcbio-nextgen documentation.")
genome_size = "" if options.find("-g") > -1 else "-g %s" % HS[genome_build]
with utils.chdir(out_dir):
cmd = _macs2_cmd()
try:
do.run(cmd.format(**locals()), "macs2 for %s" % name)
utils.move_safe(macs2_file, out_file)
except subprocess.CalledProcessError:
raise RuntimeWarning("macs2 terminated with an error.\n"
"Please, check the message and report "
"error if it is related to bcbio.\n"
"You can add specific options for the sample "
"setting resources as explained in docs: "
"https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources")
return out_file
def _make_isomir_counts(data, srna_type="seqbuster", out_dir=None, stem=""):
"""
Parse miraligner files to create count matrix.
"""
work_dir = dd.get_work_dir(data[0][0])
if not out_dir:
out_dir = op.join(work_dir, "mirbase")
out_novel_isomir = append_stem(op.join(out_dir, "counts.tsv"), stem)
out_novel_mirna = append_stem(op.join(out_dir, "counts_mirna.tsv"), stem)
logger.debug("Create %s count data at %s." % (srna_type, out_dir))
if file_exists(out_novel_mirna):
return [out_novel_mirna, out_novel_isomir]
out_dts = []
for sample in data:
if sample[0].get(srna_type):
miraligner_fn = sample[0][srna_type]
reads = _read_miraligner(miraligner_fn)
if reads:
out_file, dt, dt_pre = _tab_output(reads, miraligner_fn + ".back", dd.get_sample_name(sample[0]))
out_dts.append(dt)
else:
logger.debug("WARNING::%s has NOT miRNA annotated for %s. Check if fasta files is small or species value." % (dd.get_sample_name(sample[0]), srna_type))
if out_dts:
out_files = _create_counts(out_dts, out_dir)
out_files = [move_safe(out_files[0], out_novel_isomir), move_safe(out_files[1], out_novel_mirna)]
return out_files
else:
logger.debug("WARNING::any samples have miRNA annotated for %s. Check if fasta files is small or species value." % srna_type)
def trim_srna_sample(data):
"""
Remove 3' adapter for smallRNA-seq
Uses cutadapt but with different parameters than for other pipelines.
"""
in_file = data["files"][0]
names = data["rgnames"]['sample']
work_dir = os.path.join(dd.get_work_dir(data), "trimmed")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = replace_directory(append_stem(in_file, ".clean"), out_dir)
trim_reads = data["config"]["algorithm"].get("trim_reads", True)
adapter = dd.get_adapters(data)
if trim_reads and not adapter and error_dnapi:
raise ValueError(error_dnapi)
adapters = adapter if adapter else _dnapi_prediction(in_file)
times = "" if len(adapters) == 1 else "--times %s" % len(adapters)
if trim_reads and adapters:
adapter_cmd = " ".join(map(lambda x: "-a " + x, adapters))
out_noadapter_file = replace_directory(
append_stem(in_file, ".fragments"), out_dir)
out_short_file = replace_directory(append_stem(in_file, ".short"),
out_dir)
log_out = os.path.join(out_dir, "%s.log" % names)
atropos = _get_atropos()
options = " ".join(
data.get('resources', {}).get('atropos', {}).get("options", ""))
cores = ("--threads %s" %
dd.get_num_cores(data) if dd.get_num_cores(data) > 1 else "")
if " ".join(
data.get('resources', {}).get('cutadapt',
{}).get("options", "")):
raise ValueError(
"Atropos is now used, but cutadapt options found in YAML file."
"See https://atropos.readthedocs.io/en/latest/")
cmd = _cmd_atropos()
if not utils.file_exists(out_file):
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), "remove adapter for %s" % names)
if utils.file_exists(log_out):
content = open(log_out).read().replace(
out_short_file, names)
open(log_out, 'w').write(content)
if options:
in_file = append_stem(tx_out_file, ".tmp")
utils.move_safe(tx_out_file, in_file)
cmd = "{atropos} {cores} {options} -se {in_file} -o {tx_out_file} -m 17"
do.run(cmd.format(**locals()),
"cutadapt with this %s for %s" % (options, names))
else:
if not trim_reads:
logger.debug("Skip trimming for: %s" % names)
elif not adapters:
logger.info("No adapter founds in %s, this is an issue related"
" to no small RNA enrichment in your sample." % names)
symlink_plus(in_file, out_file)
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
def run(name, chip_bam, input_bam, genome_build, out_dir, method, resources,
data):
"""
Run macs2 for chip and input samples avoiding
errors due to samples.
"""
# output file name need to have the caller name
config = dd.get_config(data)
out_file = os.path.join(out_dir, name + "_peaks_macs2.xls")
macs2_file = os.path.join(out_dir, name + "_peaks.xls")
if utils.file_exists(out_file):
_compres_bdg_files(out_dir)
return _get_output_files(out_dir)
macs2 = config_utils.get_program("macs2", config)
options = " ".join(resources.get("macs2", {}).get("options", ""))
genome_size = HS.get(
genome_build, bam.fasta.total_sequence_length(dd.get_ref_file(data)))
genome_size = "" if options.find("-g") > -1 else "-g %s" % genome_size
paired = "-f BAMPE" if bam.is_paired(chip_bam) else ""
with utils.chdir(out_dir):
cmd = _macs2_cmd(method)
try:
do.run(cmd.format(**locals()), "macs2 for %s" % name)
utils.move_safe(macs2_file, out_file)
except subprocess.CalledProcessError:
raise RuntimeWarning(
"macs2 terminated with an error.\n"
"Please, check the message and report "
"error if it is related to bcbio.\n"
"You can add specific options for the sample "
"setting resources as explained in docs: "
"https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources"
)
_compres_bdg_files(out_dir)
return _get_output_files(out_dir)
def run(name, chip_bam, input_bam, genome_build, out_dir, method, resources, data):
"""
Run macs2 for chip and input samples avoiding
errors due to samples.
"""
# output file name need to have the caller name
config = dd.get_config(data)
out_file = os.path.join(out_dir, name + "_peaks_macs2.xls")
macs2_file = os.path.join(out_dir, name + "_peaks.xls")
if utils.file_exists(out_file):
_compres_bdg_files(out_dir)
return _get_output_files(out_dir)
macs2 = config_utils.get_program("macs2", config)
options = " ".join(resources.get("macs2", {}).get("options", ""))
genome_size = bam.fasta.total_sequence_length(dd.get_ref_file(data))
genome_size = "" if options.find("-g") > -1 else "-g %s" % genome_size
paired = "-f BAMPE" if bam.is_paired(chip_bam) else ""
with utils.chdir(out_dir):
cmd = _macs2_cmd(method)
try:
do.run(cmd.format(**locals()), "macs2 for %s" % name)
utils.move_safe(macs2_file, out_file)
except subprocess.CalledProcessError:
raise RuntimeWarning("macs2 terminated with an error.\n"
"Please, check the message and report "
"error if it is related to bcbio.\n"
"You can add specific options for the sample "
"setting resources as explained in docs: "
"https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources")
_compres_bdg_files(out_dir)
return _get_output_files(out_dir)
def trim_srna_sample(data):
"""
Remove 3' adapter for smallRNA-seq
Uses cutadapt but with different parameters than for other pipelines.
"""
in_file = data["files"][0]
names = data["rgnames"]['sample']
work_dir = os.path.join(dd.get_work_dir(data), "trimmed")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = replace_directory(append_stem(in_file, ".clean"), out_dir)
trim_reads = data["config"]["algorithm"].get("trim_reads", True)
if utils.file_exists(out_file):
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
adapter = dd.get_adapters(data)
if trim_reads and not adapter and error_dnapi:
raise ValueError(error_dnapi)
adapters = adapter if adapter else _dnapi_prediction(in_file, out_dir)
times = "" if len(adapters) == 1 else "--times %s" % len(adapters)
if trim_reads and adapters:
adapter_cmd = " ".join(map(lambda x: "-a " + x, adapters))
out_noadapter_file = replace_directory(append_stem(in_file, ".fragments"), out_dir)
out_short_file = replace_directory(append_stem(in_file, ".short"), out_dir)
log_out = os.path.join(out_dir, "%s.log" % names)
atropos = _get_atropos()
options = " ".join(data.get('resources', {}).get('atropos', {}).get("options", ""))
cores = ("--threads %s" % dd.get_num_cores(data) if dd.get_num_cores(data) > 1 else "")
if " ".join(data.get('resources', {}).get('cutadapt', {}).get("options", "")):
raise ValueError("Atropos is now used, but cutadapt options found in YAML file."
"See https://atropos.readthedocs.io/en/latest/")
cmd = _cmd_atropos()
if not utils.file_exists(out_file):
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), "remove adapter for %s" % names)
if utils.file_exists(log_out):
content = open(log_out).read().replace(out_short_file, names)
open(log_out, 'w').write(content)
if options:
in_file = append_stem(tx_out_file, ".tmp")
utils.move_safe(tx_out_file, in_file)
cmd = "{atropos} {cores} {options} -se {in_file} -o {tx_out_file} -m 17"
do.run(cmd.format(**locals()), "cutadapt with this %s for %s" %(options, names))
else:
if not trim_reads:
logger.debug("Skip trimming for: %s" % names)
elif not adapters:
logger.info("No adapter founds in %s, this is an issue related"
" to no small RNA enrichment in your sample." % names)
symlink_plus(in_file, out_file)
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
def run(name, chip_bam, input_bam, genome_build, out_dir, method, resources,
data):
"""
Run macs2 for chip and input samples avoiding
errors due to samples.
"""
# output file name need to have the caller name
config = dd.get_config(data)
out_file = os.path.join(out_dir, name + "_peaks_macs2.xls")
macs2_file = os.path.join(out_dir, name + "_peaks.xls")
if utils.file_exists(out_file):
_compress_and_sort_bdg_files(out_dir, data)
return _get_output_files(out_dir)
macs2 = config_utils.get_program("macs2", config)
antibody = dd.get_antibody(data)
if antibody:
antibody = antibody.lower()
if antibody not in antibodies.SUPPORTED_ANTIBODIES:
logger.error(
f"{antibody} specified, but not listed as a supported antibody. Valid antibodies are {antibodies.SUPPORTED_ANTIBODIES}. If you know your antibody "
f"should be called with narrow or broad peaks, supply 'narrow' or 'broad' as the antibody."
f"It will run 'narrow' if the antibody is not supported.")
antibody = 'narrow'
antibody = antibodies.ANTIBODIES[antibody]
logger.info(
f"{antibody.name} specified, using {antibody.peaktype} peak settings."
)
peaksettings = select_peak_parameters(antibody)
elif method == "atac":
logger.info(f"ATAC-seq specified, using narrow peak settings.")
peaksettings = " "
else:
peaksettings = " "
options = " ".join(resources.get("macs2", {}).get("options", ""))
genome_size = bam.fasta.total_sequence_length(dd.get_ref_file(data))
genome_size = "" if options.find("-g") > -1 else "-g %s" % genome_size
paired = "-f BAMPE" if bam.is_paired(chip_bam) else ""
with utils.chdir(out_dir):
cmd = _macs2_cmd(data)
cmd += peaksettings
try:
do.run(cmd.format(**locals()), "macs2 for %s" % name)
utils.move_safe(macs2_file, out_file)
except subprocess.CalledProcessError:
raise RuntimeWarning(
"macs2 terminated with an error. "
"Please, check the message and report "
"error if it is related to bcbio. "
"You can add specific options for the sample "
"setting resources as explained in docs: "
"https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources"
)
_compress_and_sort_bdg_files(out_dir, data)
return _get_output_files(out_dir)
def trim_srna_sample(data):
"""
Remove 3' adapter for smallRNA-seq
Uses cutadapt but with different parameters than for other pipelines.
"""
in_file = data["files"][0]
names = data["rgnames"]['sample']
work_dir = os.path.join(dd.get_work_dir(data), "trimmed")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = replace_directory(append_stem(in_file, ".clean"), out_dir)
trim_reads = data["config"]["algorithm"].get("trim_reads", True)
adapter = dd.get_adapters(data)
if trim_reads and adapter:
adapter = adapter[0]
out_noadapter_file = replace_directory(
append_stem(in_file, ".fragments"), out_dir)
out_short_file = replace_directory(append_stem(in_file, ".short"),
out_dir)
log_out = os.path.join(out_dir, "%s.log" % names)
cutadapt = os.path.join(os.path.dirname(sys.executable), "cutadapt")
options = " ".join(
config_utils.get_resources("cutadapt",
data['config']).get("options", ""))
cmd = _cmd_cutadapt()
if not utils.file_exists(out_file):
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), "remove adapter for %s" % names)
if utils.file_exists(log_out):
content = open(log_out).read().replace(
out_short_file, names)
open(log_out, 'w').write(content)
if options:
in_file = tx_out_file + ".tmp.fastq"
utils.move_safe(tx_out_file, in_file)
cmd = "{cutadapt} {options} {in_file} -o {tx_out_file} -m 17"
do.run(cmd.format(**locals()),
"cutadapt with this %s for %s" % (options, names))
else:
logger.debug("Skip trimming for: %s" % names)
symlink_plus(in_file, out_file)
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
def trim_srna_sample(data):
"""
Remove 3' adapter for smallRNA-seq
Uses cutadapt but with different parameters than for other pipelines.
"""
in_file = data["files"][0]
names = data["rgnames"]['sample']
work_dir = os.path.join(dd.get_work_dir(data), "trimmed")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = replace_directory(append_stem(in_file, ".clean"), out_dir)
trim_reads = data["config"]["algorithm"].get("trim_reads", True)
adapter = dd.get_adapters(data)
if trim_reads and adapter:
adapter = adapter[0]
out_noadapter_file = replace_directory(append_stem(in_file, ".fragments"), out_dir)
out_short_file = replace_directory(append_stem(in_file, ".short"), out_dir)
log_out = os.path.join(out_dir, "%s.log" % names)
cutadapt = os.path.join(os.path.dirname(sys.executable), "cutadapt")
options = " ".join(data.get('resources', {}).get('cutadapt', {}).get("options", ""))
cmd = _cmd_cutadapt()
if not utils.file_exists(out_file):
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), "remove adapter for %s" % names)
if utils.file_exists(log_out):
content = open(log_out).read().replace(out_short_file, names)
open(log_out, 'w').write(content)
if options:
in_file = append_stem(tx_out_file, ".tmp")
utils.move_safe(tx_out_file, in_file)
cmd = "{cutadapt} {options} {in_file} -o {tx_out_file} -m 17"
do.run(cmd.format(**locals()), "cutadapt with this %s for %s" %(options, names))
else:
logger.debug("Skip trimming for: %s" % names)
symlink_plus(in_file, out_file)
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
def run(name, chip_bam, rep_bam, input_bam, gtf_file, out_dir, rlength, rpair, config):
"""
Run rmats for muatant and control samples avoiding
errors due to samples.
"""
# output file name need to have the caller name
MATS_output = os.path.join(out_dir, name + "_MATS_output")
MATS_dir = os.path.join(out_dir, "MATS_output")
rmats_file = os.path.join(out_dir, "summary.txt")
out_file = os.path.join(out_dir, name + "_summary.txt")
'''myCmd = 'samtools view '+chip_bam+' | head -n 1'
status,output=commands.getstatusoutput(myCmd)
rlength=len(output.strip().split('\t')[9])'''
libType = _get_stranded_flag(config)
if rep_bam != "":
chip_bam = chip_bam + "," + rep_bam
if utils.file_exists(out_file):
return out_file
rmats = config_utils.get_program("rmats", config)
options = " ".join(config_utils.get_resources("rmats", config).get("options", ""))
with utils.chdir(out_dir):
cmd = _rmats_cmd()
try:
do.run(cmd.format(**locals()), "rmats for %s" % name)
utils.move_safe(rmats_file, out_file)
utils.move_safe(MATS_dir, MATS_output)
repdir_dir = os.path.join(out_dir,"SAMPLE_1")
utils.remove_safe(repdir_dir)
repdir_dir = os.path.join(out_dir,"SAMPLE_2")
utils.remove_safe(repdir_dir)
print repdir_dir
except subprocess.CalledProcessError:
raise RuntimeWarning("rMATS terminated with an error.\n"
"Please, check the message and report "
"error if it is related to bcbio.\n"
"You can add specific options for the sample "
"setting resources as explained in docs: "
"https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources")
return (out_file)
def trim_srna_sample(data):
"""
Remove 3' adapter for smallRNA-seq
Uses cutadapt but with different parameters than for other pipelines.
"""
data = umi_transform(data)
in_file = data["files"][0]
names = data["rgnames"]['sample']
work_dir = os.path.join(dd.get_work_dir(data), "trimmed")
out_dir = os.path.join(work_dir, names)
log_out = os.path.join(out_dir, "%s.log" % names)
utils.safe_makedir(out_dir)
out_file = replace_directory(append_stem(in_file, ".clean"), out_dir)
trim_reads = data["config"]["algorithm"].get("trim_reads", True)
if utils.file_exists(out_file):
data["files"][0] = out_file
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
data["log_trimming"] = log_out
return [[data]]
adapter = dd.get_adapters(data)
is_4n = any([a == "4N" for a in adapter])
adapter = [a for a in adapter if re.compile("^([NATGC]+)$").match(a)]
if adapter and not trim_reads:
trim_reads = True
logger.info(
"Adapter is set up in config file, but trim_reads is not true."
"If you want to skip trimming, skip adapter option from config.")
if trim_reads and not adapter and error_dnapi:
raise ValueError(error_dnapi)
if trim_reads:
adapters = adapter if adapter else _dnapi_prediction(in_file, out_dir)
times = "" if not trim_reads or len(
adapters) == 1 else "--times %s" % len(adapters)
if trim_reads and adapters:
adapter_cmd = " ".join(map(lambda x: "-a " + x, adapters))
if any([a for a in adapters if re.compile("^N+$").match(a)]):
adapter_cmd = "-N %s" % adapter_cmd
out_noadapter_file = replace_directory(
append_stem(in_file, ".fragments"), out_dir)
out_short_file = replace_directory(append_stem(in_file, ".short"),
out_dir)
# atropos = _get_atropos()
atropos = config_utils.get_program("atropos", data, default="atropos")
options = " ".join(
data.get('resources', {}).get('atropos', {}).get("options", ""))
if options.strip() == "-u 4 -u -4":
options = ""
is_4n = "4N"
cores = ("--threads %s" %
dd.get_num_cores(data) if dd.get_num_cores(data) > 1 else "")
if " ".join(
data.get('resources', {}).get('cutadapt',
{}).get("options", "")):
raise ValueError(
"Atropos is now used, but cutadapt options found in YAML file."
"See https://atropos.readthedocs.io/en/latest/")
cmd = _cmd_atropos()
if not utils.file_exists(out_file):
with file_transaction(out_file) as tx_out_file:
do.run(cmd.format(**locals()), "remove adapter for %s" % names)
if utils.file_exists(log_out):
content = open(log_out).read().replace(
out_short_file, names)
open(log_out, 'w').write(content)
if is_4n:
options = "-u 4 -u -4"
in_file = append_stem(tx_out_file, ".tmp")
utils.move_safe(tx_out_file, in_file)
cmd = "{atropos} {cores} {options} -se {in_file} -o {tx_out_file} -m 17"
do.run(
cmd.format(**locals()),
"atropos with this parameters %s for %s" %
(options, names))
data["log_trimming"] = log_out
else:
if not trim_reads:
logger.debug("Skip trimming for: %s" % names)
elif not adapters:
logger.info("No adapter founds in %s, this is an issue related"
" to no small RNA enrichment in your sample." % names)
symlink_plus(in_file, out_file)
data["files"][0] = out_file
data["clean_fastq"] = out_file
data["collapse"] = _collapse(data["clean_fastq"])
data["size_stats"] = _summary(data['collapse'])
return [[data]]
