print(iadbsOut, iadbs_proc)
except Exception as e:
print(e)
exceptions[rawdatapath].append(e)
OK = False
except subprocess.TimeoutExpired:
print("iadbs reached a timeout of {} hour(s).".format(timeout /
3600))
OK = False
# iadbsOut = Path(r"D:/projects/proteome_tools/RES/T1707/T170722_03/T170722_03_IA_workflow")
# out_folder= Path(r"D:/projects/proteome_tools/RES/T1707/T170722_03")
if OK:
try:
t_wx2csv = time()
report, wx2csv_proc = wx2csv(iadbsOut.with_suffix('.xml'),
out_folder / "report.csv",
debug=debug)
timings[raw_folder]['wx2csv'] = t_wx2csv = time() - t_wx2csv
if debug:
print(report, wx2csv_proc)
print("Finished")
except Exception as e:
print(e)
exceptions.append(e)
timings_path = Path("D:/projects/proteome_tools/RES/pool2/timings.json")
with open(timings_path, 'w') as f:
json.dump(timings, f, indent=4)
print("And now all the exceptions:")
print(exceptions)
# pep3dOutXML = pep3dOut.with_suffix('.xml')
pep3dOutXML = temp_folder / (raw_folder + "_Pep3D_Spectrum.xml")
fasta_file = Path(settings[raw_folder])
if debug:
print(pep3dOutXML, fasta_file, str(fasta_file))
for parameters_file in (proj_folder / "params").iterdir():
if debug:
print(parameters_file)
print(temp_folder / parameters_file.stem)
iadbsOut, iadbs_proc = iadbs(pep3dOutXML,
temp_folder / parameters_file.stem,
fasta_file=fasta_file,
parameters_file=parameters_file,
capture_output=True,
debug=True)
if debug:
print(iadbsOut, iadbs_proc)
report, wx2csv_proc = wx2csv(iadbsOut.with_suffix('.xml'),
temp_folder / parameters_file.stem /
"report.csv",
debug=debug)
# cp(apexOutBIN, final_folder)
# cp(pep3dOutXML, final_folder)
# cp(iadbsOutXML, final_folder)
# cp(temp_folder/'apex3d.log', final_folder)
# cp(temp_folder/'peptide3d.log', final_folder)
# cp(temp_folder/'iadbs.log', final_folder)
#TODO: add file removal!!!!
if debug:
print("Finished")
missing = pool2 - existing
missing_files = [(f, fas) for f, fas in settings if Path(f).stem in missing]
logging.basicConfig(
filename=out_folder / "pool2.log",
format='PLGS %(asctime)s:%(name)s:%(levelname)s:%(message)s:',
level=logging.INFO)
logger = logging.getLogger('PLGS')
timeout = 8 * 60 # 8 hours timeout [in minutes]
for rawdatapath, fastapath in missing_files:
rawdatapath = Path(rawdatapath)
fastapath = Path(fastapath)
raw_folder = rawdatapath.stem
final_out_folder = out_folder / raw_folder[0:5] / raw_folder
for low_energy_thr in [300, 400, 500]:
try:
ok = plgs(rawdatapath,
final_out_folder,
low_energy_thr=low_energy_thr,
fastas=fastapath,
timeout_apex3d=timeout,
timeout_peptide3d=timeout,
timeout_iadbs=timeout)
workflow_xml = next(final_out_folder.glob('*_IA_workflow.xml'))
df, _ = wx2csv(workflow_xml, final_out_folder / 'report.csv')
break
except Exception as e:
logger.warning(repr(e))
# try:
# df,_ = wx2csv(res_folder/'reversed_search'/f"{raw.stem}_IA_workflow.xml",
# res_folder/'reversed_search'/f"{raw.stem}_report.csv")
# except Exception as e:
# print(e)
# troubles.append(e)
res = Path(r"D:/projects/proteome_tools/RES")
# RECALCULATING ALL THE BLOODY REPORTS
troubles = []
# proj_folder = next(res.glob("pool*/*/*"))
for proj_folder in res.glob("pool*/*/*"):
try:
df, _ = wx2csv(
proj_folder / 'reversed_search' /
f"{proj_folder.stem}_IA_workflow.xml",
proj_folder / 'reversed_search' / f"{proj_folder.stem}_report.csv")
except Exception as e:
print(e)
troubles.append(e)
# proj_folder = next(res.glob("pool*/*/*"))
def iter_results(res):
for proj_folder in res.glob("pool*/*/*"):
report_path = proj_folder / "reversed_search" / f"{proj_folder.stem}_report.csv"
fasta_path = next(proj_folder.glob("*_reversed.fasta"))
peptides, target, qcs, all_peptides_no = get_input_for_coverages(
report_path, fasta_path)
r = get_coverages(peptides, target, qcs)
r['fasta'] = fasta_path.stem
troubles = []
dfs = {}
# proj = next(iter(zero_cover_raw_folders))
for proj in zero_cover_raw_folders:
FA = fastas[proj]
RF = raw_folders[proj]
pool = FA.parent.parent.parent.stem
OF = output_path / pool / proj[:5] / proj
OK = False
try:
OK = plgs(raw_folder=RF, out_folder=OF, fastas=FA, timeout_apex3d=120)
except TimeoutExpired:
logger.warning('Trying out higher energies.')
try:
OK = plgs(raw_folder=RF,
out_folder=OF,
fastas=FA,
timeout_apex3d=120,
low_energy_thr=600,
high_energy_thr=60)
except Exception as e:
logger.warning('Failed again.')
troubles.append((p, e))
if OK:
try:
dfs[proj], _ = wx2csv(OF / f"{proj}_IA_workflow.xml",
OF / f"{proj}_report.csv")
except Exception as e:
troubles.append((p, e))