def read_fastqc_data(self, sample):
qc_info = OrderedDict()
over_seq = []
qc_desc = None
qc_data_pth = self.result_root / sample.full_name / 'fastqc_data.txt'
with open(qc_data_pth) as qc_data:
# parse FASTQC by brute force
for line in qc_data:
new_sec = line.startswith('>>')
sec_end = line.startswith('>>END_MODULE')
if new_sec and not sec_end:
qc_desc, qc_status = line.rstrip()[2:].rsplit('\t', 1)
qc_info[qc_desc] = qc_status
if qc_desc == "Overrepresented sequences":
next_line = next(qc_data)
while not sec_end:
if not next_line.startswith("#Seq"):
over_seq.append(
OverSeq(*next_line.rstrip().split('\t'))
)
next_line = next(qc_data)
sec_end = next_line.startswith('>>END_MODULE')
logger.debug(
"Sample {}'s qc_info: {}".format(sample.full_name, qc_info)
)
logger.debug("Over_seq length: {}".format(len(over_seq)))
return qc_info, over_seq
def output_report(self):
"""Output rendered htmls to output directory.
No original data is involved, just some file I/Oing.
"""
for name, content in self.report_html.items():
with open(self.report_root / '{}'.format(name), 'w') as f:
f.write(content)
def parse_sample(self, group, sample_list):
logger.debug("Reading align_summary.txt")
align_txt = self.result_root / group / 'align_summary.txt'
with open(align_txt) as align_summary:
raw_string = align_summary.read()
match_sep = _extract_separate(raw_string)
if not match_sep:
raise ValueError("Cannot get left/right info in align_summary.txt")
match_align = _extract_align(raw_string)
if not match_align:
raise ValueError("Cannot get pair info in align_summary.txt")
info_dict = {
k: D(v)
for m in [match_sep, match_align]
for k, v in m.groupdict().items()
}
return info_dict
def _read_yaml(self):
logger.info("Reading job_info.yaml")
with open(self.root_path / "job_info.yaml") as f:
return yaml.load(f)