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()
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]]
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]]