def test_progenesis(self):
## SONAR MSE
compound_to_scan_mapping = progenesis_formatter.convert_to_feature_csv("./reference_input_file_for_formatter/Progenesis/SONAR_20_Yeast_Peaks.txt", \
"./progenesis_MSE_output.csv")
self.assertTrue(filecmp.cmp("./progenesis_MSE_output.csv", "./reference_input_file_for_formatter/Progenesis/SONAR_20_Yeast_Peaks_output.csv", shallow=False))
progenesis_formatter.convert_mgf("./reference_input_file_for_formatter/Progenesis/SONAR_20_Yeast_MSMS.msp", "SONAR_20_Yeast_MSMS.mgf", compound_to_scan_mapping)
self.assertTrue(filecmp.cmp("./SONAR_20_Yeast_MSMS.mgf", "./reference_input_file_for_formatter/Progenesis/SONAR_20_Yeast_MSMS.mgf", shallow=False))
## CATECHIN MSE
compound_to_scan_mapping = progenesis_formatter.convert_to_feature_csv("./reference_input_file_for_formatter/Progenesis/Neg_MSE_Catechin.txt", "./Neg_MSE_Catechin_output.csv")
self.assertTrue(filecmp.cmp("./Neg_MSE_Catechin_output.csv", "./reference_input_file_for_formatter/Progenesis/Neg_MSE_Catechin_output.csv", shallow=False))
progenesis_formatter.convert_mgf("./reference_input_file_for_formatter/Progenesis/Neg_MSE_Catechin.msp", "Neg_MSE_Catechin.mgf", compound_to_scan_mapping)
self.assertTrue(filecmp.cmp("./Neg_MSE_Catechin.mgf", "./reference_input_file_for_formatter/Progenesis/Neg_MSE_Catechin.mgf", shallow=False))
## IMS
compound_to_scan_mapping = progenesis_formatter.convert_to_feature_csv("./reference_input_file_for_formatter/Progenesis/161118_pos_IMS.txt", \
"./progenesis_IMS_output.csv")
self.assertTrue(filecmp.cmp("./progenesis_IMS_output.csv", "./reference_input_file_for_formatter/Progenesis/161118_pos_IMS_output.csv", shallow=False))
progenesis_formatter.convert_mgf("./reference_input_file_for_formatter/Progenesis/161118_pos_IMS.msp", "161118_pos_IMS.mgf", compound_to_scan_mapping)
self.assertTrue(filecmp.cmp("./161118_pos_IMS.mgf", "./reference_input_file_for_formatter/Progenesis/161118_pos_IMS.mgf", shallow=False))
#More input
compound_to_scan_mapping = progenesis_formatter.convert_to_feature_csv("./reference_input_file_for_formatter/Progenesis/202005_IMS_w_tags.txt", \
"./progenesis_IMS_output.csv")
self.assertTrue(filecmp.cmp("./progenesis_IMS_output.csv", "./reference_input_file_for_formatter/Progenesis/202005_IMS_w_tags_output.csv", shallow=False))
progenesis_formatter.convert_mgf("./reference_input_file_for_formatter/Progenesis/202005_IMS_w_tags.msp", "202005_IMS_w_tags.mgf", compound_to_scan_mapping)
self.assertTrue(filecmp.cmp("./202005_IMS_w_tags.mgf", "./reference_input_file_for_formatter/Progenesis/202005_IMS_w_tags.mgf", shallow=False))
def main():
parser = argparse.ArgumentParser(description='Create parallel parameters')
parser.add_argument('toolname', help='name of input tool')
parser.add_argument('quantification_table', help='quantification_table')
parser.add_argument('quantification_table_reformatted',
help='quantification_table_reformatted')
parser.add_argument('input_mgf', help='input_mgf')
parser.add_argument('output_mgf', help='output_mgf')
args = parser.parse_args()
if args.toolname == "MZMINE2":
print("MZMINE2")
shutil.copyfile(args.input_mgf, args.output_mgf)
mzmine2_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPENMS":
print("OPENMS")
shutil.copyfile(args.input_mgf, args.output_mgf)
openms_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPTIMUS":
print("OPTIMUS")
shutil.copyfile(args.input_mgf, args.output_mgf)
optimus_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "MSDIAL":
print("MSDIAL")
shutil.copyfile(args.input_mgf, args.output_mgf)
msdial_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "METABOSCAPE":
print("METABOSCAPE")
shutil.copyfile(args.input_mgf, args.output_mgf)
metaboscape_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "XCMS3":
print("XCMS3")
shutil.copyfile(args.input_mgf, args.output_mgf)
xcms_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "PROGENESIS":
print("PROGENESIS")
compound_scan_mapping = progenesis_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
progenesis_formatter.convert_mgf(args.input_mgf, args.output_mgf,
compound_scan_mapping)
def test_progenesis(self):
progenesis_formatter.convert_to_feature_csv("./reference_input_file_for_formatter/Progensis_MSE/SONAR_20_Yeast_Peaks.csv", \
"./progenesis_output.csv")
def main():
parser = argparse.ArgumentParser(description='Create parallel parameters')
parser.add_argument('toolname', help='name of input tool')
parser.add_argument('quantification_table', help='quantification_table')
parser.add_argument('quantification_table_reformatted',
help='quantification_table_reformatted')
parser.add_argument('input_spectra_folder', help='input_spectra_folder')
parser.add_argument('output_mgf', help='output_mgf')
parser.add_argument('workflowParameters', help='workflowParameters')
args = parser.parse_args()
input_filenames = glob.glob(os.path.join(args.input_spectra_folder, "*"))
if args.toolname == "MZMINE2":
print("MZMINE2")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
mzmine2_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPENMS":
print("OPENMS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
openms_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPTIMUS":
print("OPTIMUS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
optimus_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "MSDIAL":
print("MSDIAL")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
msdial_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "METABOSCAPE":
print("METABOSCAPE")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
metaboscape_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "XCMS3":
print("XCMS3")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
xcms_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "PROGENESIS":
print("PROGENESIS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
compound_scan_mapping = progenesis_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
progenesis_formatter.convert_mgf(input_mgf, args.output_mgf,
compound_scan_mapping)
elif args.toolname == "MZTABM":
print("MZTABM")
workflow_parameters = proteosafe.parse_xml_file(
args.workflowParameters)
mangled_mapping = proteosafe.get_mangled_file_mapping(
workflow_parameters)
name_mangle_mapping = {}
for key in mangled_mapping:
demangled_name = mangled_mapping[key]
name_mangle_mapping[os.path.basename(
demangled_name)] = os.path.join(args.input_spectra_folder, key)
compound_filename_mapping = mztabm_formatter.convert_to_feature_csv(
args.quantification_table, args.quantification_table_reformatted)
mztabm_formatter.create_mgf(input_filenames,
args.output_mgf,
compound_filename_mapping,
name_mangle_mapping=name_mangle_mapping)
def main():
parser = argparse.ArgumentParser(description='Create parallel parameters')
parser.add_argument('toolname', help='name of input tool')
parser.add_argument('quantification_table', help='quantification_table')
parser.add_argument('quantification_table_reformatted', help='quantification_table_reformatted')
parser.add_argument('input_spectra_folder', help='input_spectra_folder')
parser.add_argument('output_mgf', help='output_mgf')
parser.add_argument('workflowParameters', help='workflowParameters')
parser.add_argument('--QUANT_FILE_NORM', default="None", help='QUANT_FILE_NORM')
args = parser.parse_args()
input_filenames = glob.glob(os.path.join(args.input_spectra_folder, "*"))
if args.toolname == "MZMINE2":
print("MZMINE2")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
mzmine2_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPENMS":
print("OPENMS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
openms_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "OPTIMUS":
print("OPTIMUS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
optimus_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "MSDIAL":
print("MSDIAL")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
msdial_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "METABOSCAPE":
print("METABOSCAPE")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
metaboscape_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "XCMS3":
print("XCMS3")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
shutil.copyfile(input_mgf, args.output_mgf)
xcms_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
elif args.toolname == "PROGENESIS":
print("PROGENESIS")
if len(input_filenames) != 1:
print("Must input exactly 1 spectrum mgf file")
exit(1)
input_mgf = input_filenames[0]
compound_scan_mapping = progenesis_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
progenesis_formatter.convert_mgf(input_mgf, args.output_mgf, compound_scan_mapping)
elif args.toolname == "MZTABM":
print("MZTABM")
workflow_parameters = proteosafe.parse_xml_file(args.workflowParameters)
mangled_mapping = proteosafe.get_mangled_file_mapping(workflow_parameters)
name_mangle_mapping = {}
for key in mangled_mapping:
demangled_name = mangled_mapping[key]
name_mangle_mapping[os.path.basename(demangled_name)] = os.path.join(args.input_spectra_folder, key)
compound_filename_mapping = mztabm_formatter.convert_to_feature_csv(args.quantification_table, args.quantification_table_reformatted)
mztabm_formatter.create_mgf(input_filenames, args.output_mgf, compound_filename_mapping, name_mangle_mapping=name_mangle_mapping)
# Finally, we can renormlize the output
try:
if args.QUANT_FILE_NORM == "RowSum":
import pandas as pd
quant_df = pd.read_csv(args.quantification_table_reformatted, sep=",")
quant_df = quant_df.loc[:, ~quant_df.columns.str.contains('^Unnamed')]
for column in quant_df:
if "Peak area" in column:
quant_df[column] = quant_df[column] / sum(quant_df[column]) * 1000000
quant_df.to_csv(args.quantification_table_reformatted, sep=",", index=False)
except:
pass