validate_peptides.py -> spectrumai.py

pypgatk/commands/validate_peptides.py

@@ -3,18 +3,17 @@
 import click
 
 from pypgatk.toolbox.general import read_yaml_from_file
-from pypgatk.proteogenomics.validate_peptides import ValidatePeptidesService
+from pypgatk.proteogenomics.spectrumai import SpectrumAIService
 from pypgatk.commands.utils import print_help
 
 log = logging.getLogger(__name__)
 
 
-@click.command('validate_peptides',
+@click.command('spectrumai',
                short_help='Command to inspect MS2 spectra of single-subsititution peptide identifications')
 @click.option('-c', '--config_file', help='Configuration file for the validate peptides pipeline')
 @click.option('-p', '--mzml_path', help='The mzml file path.You only need to use either mzml_path or mzml_files')
-@click.option('-f', '--mzml_files',
-              help='The mzml files.Different files are separated by ",".You only need to use either mzml_path or mzml_files')
+@click.option('-f', '--mzml_files', help='The mzml files. Different files are separated by ","')
 @click.option('-i', '--infile_name', help='Variant peptide PSMs table')
 @click.option('-o', '--outfile_name', help='Output file for the results')
 @click.option('-ion', '--ions_tolerance', help='MS2 fragment ions mass accuracy')
@@ -25,8 +24,8 @@
               help='If the tsv was obtained from mzTab, please enable this option. Default to tsv obtained from parquet',
               is_flag=True)
 @click.pass_context
-def validate_peptides(ctx, config_file, mzml_path, mzml_files, infile_name, outfile_name, ions_tolerance,
-                      number_of_processes, relative, mztab):
+def spectrumai(ctx, config_file, mzml_path, mzml_files, infile_name, outfile_name, ions_tolerance,
+               number_of_processes, relative, mztab):
     config_data = None
     if config_file is not None:
         config_data = read_yaml_from_file(config_file)
@@ -38,18 +37,18 @@ def validate_peptides(ctx, config_file, mzml_path, mzml_files, infile_name, outf
     pipeline_arguments = {}
 
     if mzml_path is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_MZML_PATH] = mzml_path
+        pipeline_arguments[SpectrumAIService.CONFIG_MZML_PATH] = mzml_path
     if mzml_files is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_MZML_FILES] = mzml_files
+        pipeline_arguments[SpectrumAIService.CONFIG_MZML_FILES] = mzml_files
     if ions_tolerance is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_IONS_TOLERANCE] = ions_tolerance
+        pipeline_arguments[SpectrumAIService.CONFIG_IONS_TOLERANCE] = ions_tolerance
     if number_of_processes is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_NUMBER_OF_PROCESSES] = number_of_processes
+        pipeline_arguments[SpectrumAIService.CONFIG_NUMBER_OF_PROCESSES] = number_of_processes
     if relative is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_RELATIVE] = relative
+        pipeline_arguments[SpectrumAIService.CONFIG_RELATIVE] = relative
     if mztab is not None:
-        pipeline_arguments[ValidatePeptidesService.CONFIG_MZTAB] = mztab
+        pipeline_arguments[SpectrumAIService.CONFIG_MZTAB] = mztab
 
-    validate_peptides_service = ValidatePeptidesService(config_data, pipeline_arguments)
+    validate_peptides_service = SpectrumAIService(config_data, pipeline_arguments)
     if validate_flag:
         validate_peptides_service.validate(infile_name, outfile_name)

pypgatk/proteogenomics/validate_peptides.py → pypgatk/proteogenomics/spectrumai.py

@@ -10,7 +10,7 @@
 from pypgatk.toolbox.general import ParameterConfiguration
 
 
-class ValidatePeptidesService(ParameterConfiguration):
+class SpectrumAIService(ParameterConfiguration):
     CONFIG_KEY_VALIDATE_PEPTIDES = 'validate_peptides'
     CONFIG_MZML_PATH = 'mzml_path'
     CONFIG_MZML_FILES = 'mzml_files'
@@ -28,8 +28,8 @@ def __init__(self, config_data, pipeline_arguments):
       :param pipeline_arguments pipelines arguments
       """
 
-        super(ValidatePeptidesService, self).__init__(self.CONFIG_KEY_VALIDATE_PEPTIDES, config_data,
-                                                      pipeline_arguments)
+        super(SpectrumAIService, self).__init__(self.CONFIG_KEY_VALIDATE_PEPTIDES, config_data,
+                                                pipeline_arguments)
 
         self._mzml_path = self.get_validate_parameters(variable=self.CONFIG_MZML_PATH, default_value=False)
         self._mzml_files = self.get_validate_parameters(variable=self.CONFIG_MZML_FILES, default_value=False)
@@ -51,6 +51,7 @@ def get_validate_parameters(self, variable: str, default_value):
         return value_return
 
     def _predict_MS2_spectrum(self, peptide, size, product_ion_charge=1):
+
         tsg = TheoreticalSpectrumGenerator()
         spec = MSSpectrum()
         peptide = AASequence.fromString(peptide)
@@ -314,7 +315,6 @@ def validate(self, infile_name, outfile_name: str):
 
         df_output = pd.concat(self.df_list, axis=0, ignore_index=True)
 
-
         if outfile_name.endswith(".csv.gz"):
             df_output.to_csv(outfile_name, header=True, sep=",", index=None, compression="gzip")
         elif outfile_name.endswith(".csv"):

pypgatk/pypgatk_cli.py

@@ -46,7 +46,7 @@ def cli():
 cli.add_command(proteindb_decoy_cmd.generate_database)
 cli.add_command(proteindb_decoy_cmd.generate_database)
 cli.add_command(peptide_class_fdr_cmd.peptide_class_fdr)
-cli.add_command(validate_peptides_cmd.validate_peptides)
+cli.add_command(validate_peptides_cmd.spectrumai)
 cli.add_command(mztab_class_fdr_cmd.mztab_class_fdr)
 cli.add_command(blast_get_position_cmd.blast_get_position)