import pandas as pd, numpy as np, pathlib
import pickle
import matplotlib
matplotlib.use('Agg')
if 0:
sys.argv = [
"%(prog)s", "./RT_align", "./iproph",
"/data/dattam/PROJECTS/CoreFacility/PDLC/dda-lib-atcc-mm-R1/workdir/iproph",
"/data/teog/tpp5/bin/"
]
has_DDA = sys.argv[3] != "none"
rtalign_data_directory = str_to_path(sys.argv[1])
dia_pepxml_directory = str_to_path(sys.argv[2])
dda_pepxml_directory = str_to_path(sys.argv[3]) if has_DDA else None
TPP_BIN = str_to_path(sys.argv[4])
rtalign_data_directory.mkdir(parents=True, exist_ok=False)
rt_dicts_file = rtalign_data_directory / "RT_dicts.pickle"
PEPTIDE_PROB = 0.9
abs_paths = [
None if e is None else e.resolve() for e in [
rtalign_data_directory, dia_pepxml_directory, dda_pepxml_directory,
TPP_BIN / 'indexmzXML'
]
]
print((TPP_BIN / 'indexmzXML').resolve(strict=True))
# if __name__=='__main__':
# def main():
import doctest
doctest.testmod(verbose=False)
script_dir = pathlib.Path(__file__).resolve().parent
if script_dir.suffix == '.pyz':
script_dir = script_dir.parent
# philosopher_path = str_to_path(sys.argv[1]).resolve(strict=True)
SPECTRAST_PATH = (script_dir / {
'linux': 'linux/spectrast',
'win32': 'win/spectrast.exe'
}[sys.platform]).resolve(strict=True)
fasta = str_to_path(sys.argv[1]).resolve(strict=True)
# msproteomicstools_bin_path = str_to_path(sys.argv[3]).resolve(strict=True)
# msproteomicstools_bin_path = str_to_path(pathlib.Path(sys.executable).parent).resolve(strict=True)
iproph_RT_aligned = str_to_path(sys.argv[2]).resolve(strict=True)
prot_xml_file = str_to_path(sys.argv[3]).resolve(strict=True)
output_directory = str_to_path(sys.argv[4])
if 'PATHEXT' in os.environ:
os.environ['PATHEXT'] = '.py' + os.pathsep + os.environ['PATHEXT']
os.environ['PATH'] = os.getcwd() + os.pathsep + os.environ['PATH']
philosopher = pathlib.Path(shutil.which('philosopher'))
# philosopher = philosopher_path
# msproteomicstools_path = pathlib.Path('/storage/teog/anaconda3/bin')
align_with_iRT: bool = True
# spectrast2spectrast_irt_py_path = msproteomicstools_bin_path / 'spectrast2spectrast_irt.py'
# "/data/dattam/PROJECTS/CoreFacility/PDLC/dda-lib-atcc-mm-singleInjection-R1/workdir/con_lib.tsv"
# "/data/teog/LFQbench/TTOF6600_SWATH_1ug_64windows_subset/workdir_tpp5/libgen/con_lib.tsv",
# "/data/teog/LFQbench/TTOF6600_SWATH_1ug_64windows_subset/workdir_tpp5/libgen_DDA/con_lib.tsv"
# "/data/teog/LFQbench/TTOF6600_SWATH_1ug_32windows/workdir/con_lib.tsv",
# "/data/teog/LFQbench/DDA/workdir/lib_TTOF6600_32win/con_lib.tsv",
# "/data/teog/LFQbench/TTOF6600_SWATH_1ug_64windows/workdir/con_lib.tsv",
# "/data/teog/LFQbench/DDA/workdir/lib_TTOF6600_64win/con_lib.tsv",
# "/data/dattam/PROJECTS/CoreFacility/PDLC/dia-atcc-mm-R1/workdir/con_lib.tsv",
# "/data/dattam/PROJECTS/CoreFacility/PDLC/dda-lib-atcc-mm-R1/workdir/con_lib.tsv"
#"/data/dattam/PROJECTS/CoreFacility/PDLC/dda-lib-atcc-mm-singleInjection-R1/workdir/con_lib.tsv"
]
dia_con_lib_path = str_to_path(sys.argv[1])
dda_con_lib_path = str_to_path(sys.argv[2])
assert dia_con_lib_path.exists()
assert dda_con_lib_path.exists()
dia = pd.read_csv(dia_con_lib_path, sep='\t')
dia_transition_group_id = dia["transition_group_id"].values
# last int of the trans group id
dia_trans_grp_id_end = int(dia_transition_group_id[-1].split("_")[0])
dia_startidx = np.fromiter((next(v) for k, v in itertools.groupby(
dia.index, lambda x: dia_transition_group_id[x])),
dtype=dia.index.dtype)
dia_pep_name_charge = dia[["FullUniModPeptideName", "PrecursorCharge"]].values
dia_pep_name_charge_set = {
tuple(dia_pep_name_charge[lo])