def run_waters_pipeline(raw_folder,
fasta_file,
out_folder="C:/Symphony/Temp/test",
parameters_file="C:/Symphony/Search/251.xml",
apex_kwds={},
pep3d_kwds={},
iadbs_kwds={}):
"""Run Waters pipeline.
A convenience wrapper around apex3d, peptide3d, and iaDBs.
Args:
raw_folder (str): a path to the input folder with raw Waters data.
fasta_file (str): Path to the fasta file used in iaDBs peptide search.
out_folder (str): Path to where to place the output.
parameters_file (str): Path to the search parameters used in iaDBs peptide search.
apex_kwds (dict): Other named arguments to apex3d.
pep3d_kwds (dict): Other named arguments to peptide3d.
iadbs_kwds (dict): Other named arguments to iaDBs.
Returns:
Paths to Apex3D, Peptide3D and iaDBs output files.
"""
raw_folder = Path(raw_folder)
out_folder = Path(out_folder)
apexOutPath, apex_proc = apex3d(raw_folder,
out_folder,
write_binary=True,
capture_output=True,
**apex_kwds)
apexOutBIN = apexOutPath.with_suffix('.bin')
pep3dOutPath, pep_proc = peptide3d(apexOutBIN,
out_folder,
write_binary=True,
min_LEMHPlus=350.0,
capture_output=True,
**pep3d_kwds)
pep3dOutXML = pep3dOutPath.with_suffix('.xml')
iadbsOutXML, iadbs_proc = iadbs(pep3dOutXML,
out_folder,
fasta_file=Path(fasta_file),
parameters_file=Path(parameters_file),
capture_output=True,
**iadbs_kwds)
return apexOutBIN, pep3dOutXML, iadbsOutXML
raw_folder = rawdatapath.stem
out_folder = Path(
"D:/projects/proteome_tools/RES/pool2") / raw_folder[0:5] / raw_folder
if debug:
print('rawdatapath', '\n\t', rawdatapath, '\n\t', str(rawdatapath))
print('fastapath', '\n\t', fastapath, '\n\t', str(fastapath))
print('raw_folder', '\n\t', raw_folder)
print('out_folder', '\n\t', out_folder)
print('parameters_file', '\n\t', parameters_file)
print('timeout\n\t{} h'.format(timeout / 3600))
timings[raw_folder] = {}
try:
t_apex = time()
apexOut, apex_proc = apex3d(rawdatapath,
out_folder,
write_binary=True,
capture_output=capture_output,
debug=debug,
timeout=timeout)
timings[raw_folder]['apex3d'] = t_apex = time() - t_apex
if debug:
print(apexOut, apex_proc)
except subprocess.TimeoutExpired:
print("apex3d reached a timeout of {} hour(s).".format(timeout / 3600))
OK = False
except StdErr as e:
print("Sometimes the errors are not reflected in the output.")
print(e.err)
apexOut = out_folder / (out_folder.name + "_Apex3D.bin")
exceptions[rawdatapath].append(e)
OK = False
if OK:
proc = subprocess.Popen(cmd,
stdout=subprocess.PIPE)
subprocess.Popen("Taskkill /IM Apex3D64.exe /F")
from pathlib import Path
from vodkas import apex3d
from subprocess import TimeoutExpired
raw_folder = "C:/ms_soft/MasterOfPipelines/Data/O190302_01.raw"
output_dir = "C:/SYMPHONY_VODKAS/temp/subproc_test"
try:
apex3d(raw_folder, output_dir, timeout=2, make_log=True)
except TimeoutExpired as e:
print(e)
try:
outs, errs = proc.communicate(timeout=15)
except TimeoutExpired:
proc.kill()
outs, errs = proc.communicate()
if make_log:
log = output_dir/"apex3d.log"
kill = "Taskkill /IM {} /F".format(algo.name)
"C:/SYMPHONY_VODKAS/temp/O1903/O190302_01_IA_workflow.xml")
pprint(xml_params['apex3d'])
pprint(xml_params['apex3d'])
proj_tag = "O1903"
p = Path()
len(list(p.parent.glob(proj_tag)))
# there is a problem
raw_folder = 'C:/SYMPHONY_VODKAS/temp/O1903'
out_folder = 'C:/SYMPHONY_VODKAS/temp'
network_out_folder = 'J:/test_RES'
raw_folder = 'C:/SYMPHONY_VODKAS/temp/O1904'
out_folder = 'C:/SYMPHONY_VODKAS/temp'
network_out_folder = 'J:/test_RES'
raw = Path(raw_folder)
out = Path(out_folder)
net_out = Path(network_out_folder)
proj_tag = raw.name[:5]
from vodkas import apex3d
from pathlib import Path
pr = apex3d('a', 'b')
pr.communicate()
pr.poll()
pr.stderr
log.info(f"analyzing folders: {dump2json(raw_folders)}")
for raw_folder in raw_folders:
try:
if not raw_folder.is_dir():
log.error(f"missing: {raw_folder}")
continue
log.info(f"analyzing: {raw_folder}")
sender.update_group(raw_folder) # wtf??? change name ....
acquired_name = raw_folder.stem
header_txt = parse_header_txt(raw_folder / '_HEADER.TXT')
sample_set = header_txt['Sample Description'][:8]
# C:/SYMPHONY_PIPELINE/2019-008/O191017-04
local_folder = local_output_folder / sample_set / acquired_name
a = apex3d(raw_folder, local_folder, **apex3d_kwds)
if peptide3d_kwds['timeout'] >= 0:
p = peptide3d(a.with_suffix('.bin'), local_folder,
**peptide3d_kwds)
if iadbs_kwds['timeout'] >= 0:
i = iadbs(p, local_folder, fasta_file, parameters_file,
**iadbs_kwds)
if i is not None:
params = create_params_file(a, p, i) # for projectizer2.0
with open(a.parent / "params.json", 'w') as f:
json.dump(params, f)
search_stats = get_search_stats(i)
rows2csv(i.parent / 'stats.csv',
[list(search_stats),
list(search_stats.values())])
if net_folder:
from pathlib import Path
from vodkas import apex3d, peptide3d, iadbs
from vodkas.fs import cp
# if __name__ == "__main__":
# raw = Path("//MSSERVER/restoredData/proteome_tools/net/idefix/WIRD_GESICHERT/T1707/T170722_03.raw")#big
raw = Path("C:/ms_soft/MasterOfPipelines/RAW/O1903/O190302_01.raw") #small
temp = Path("C:/Symphony/Temp/test") #TODO: WTF if this file already existed?
apexOutPath, apex_proc = apex3d(raw,
temp,
write_binary=True,
capture_output=True)
# apexOutPath = temp/(raw.stem + "_Apex3D")
apexOutBIN = apexOutPath.with_suffix('.bin')
pep3dOutPath, pep_proc = peptide3d(apexOutBIN,
temp,
write_binary=True,
min_LEMHPlus=350.0,
capture_output=True)
# pep3dOutPath = temp/(raw.stem + "_Pep3D_Spectrum")
pep3dOutXML = pep3dOutPath.with_suffix('.xml')
iadbsOutPath, iadbs_proc = iadbs(pep3dOutXML,
temp,
fasta_file="C:/Symphony/Search/wheat.fasta",
parameters_file="C:/Symphony/Search/251.xml",
capture_output=True)