def create_ataqv_report(samples):
"""
make the ataqv report from a set of ATAC-seq samples
"""
data = samples[0][0]
new_samples = []
reportdir = os.path.join(dd.get_work_dir(data), "qc", "ataqv")
sentinel = os.path.join(reportdir, "index.html")
if utils.file_exists(sentinel):
ataqv_output = {"base": sentinel, "secondary": get_ataqv_report_files(reportdir)}
new_data = []
for data in dd.sample_data_iterator(samples):
data = tz.assoc_in(data, ["ataqv_report"], ataqv_output)
new_data.append(data)
return dd.get_samples_from_datalist(new_data)
mkarv = config_utils.get_program("mkarv", dd.get_config(data))
ataqv_files = []
for data in dd.sample_data_iterator(samples):
qc = dd.get_summary_qc(data)
ataqv_file = tz.get_in(("ataqv", "base"), qc, None)
if ataqv_file and utils.file_exists(ataqv_file):
ataqv_files.append(ataqv_file)
if not ataqv_files:
return samples
ataqv_json_file_string = " ".join(ataqv_files)
with file_transaction(reportdir) as txreportdir:
cmd = f"{mkarv} {txreportdir} {ataqv_json_file_string}"
message = f"Creating ataqv report from {ataqv_json_file_string}."
do.run(cmd, message)
new_data = []
ataqv_output = {"base": sentinel, "secondary": get_ataqv_report_files(reportdir)}
for data in dd.sample_data_iterator(samples):
data = tz.assoc_in(data, ["ataqv_report"], ataqv_output)
new_data.append(data)
return dd.get_samples_from_datalist(new_data)
def create_peaktable(samples):
"""create a table of peak counts per sample to use with differential peak calling
"""
data = dd.get_data_from_sample(samples[0])
peakcounts = []
out_dir = os.path.join(dd.get_work_dir(data), "consensus")
out_file = os.path.join(out_dir, "consensus-counts.tsv")
if dd.get_chip_method(data) == "chip":
for data in dd.sample_data_iterator(samples):
peakcounts.append(tz.get_in(("peak_counts"), data))
elif dd.get_chip_method(data) == "atac":
for data in dd.sample_data_iterator(samples):
if bam.is_paired(dd.get_work_bam(data)):
peakcounts.append(tz.get_in(("peak_counts", "NF"), data))
else:
logger.info(f"Creating peak table from full BAM file because "
f"{dd.get_work_bam(data)} is single-ended.")
peakcounts.append(tz.get_in(("peak_counts", "full"), data))
combined_peaks = count.combine_count_files(peakcounts,
out_file,
ext=".counts")
new_data = []
for data in dd.sample_data_iterator(samples):
data = tz.assoc_in(data, ("peak_counts", "peaktable"), combined_peaks)
new_data.append(data)
new_samples = dd.get_samples_from_datalist(new_data)
return new_samples
def create_peaktable(samples):
"""create a table of peak counts per sample to use with differential peak calling
"""
data = dd.get_data_from_sample(samples[0])
peakcounts = []
out_dir = os.path.join(dd.get_work_dir(data), "consensus")
out_file = os.path.join(out_dir, "consensus-counts.tsv")
if dd.get_chip_method(data) == "chip":
for data in dd.sample_data_iterator(samples):
peakcounts.append(tz.get_in(("peak_counts"), data))
elif dd.get_chip_method(data) == "atac":
for data in dd.sample_data_iterator(samples):
peakcounts.append(tz.get_in(("peak_counts", "NF"), data))
combined_peaks = count.combine_count_files(peakcounts,
out_file,
ext=".counts")
new_data = []
for data in dd.sample_data_iterator(samples):
data = tz.assoc_in(data, ("peak_counts", "peaktable"), combined_peaks)
new_data.append(data)
new_samples = dd.get_samples_from_datalist(new_data)
return new_samples