feature improved.

python/quantmsio/quantms_io/commands/feature_command.py

@@ -7,32 +7,40 @@
 @click.option("--sdrf_file", help="the SDRF file needed to extract some of the metadata", required=True)
 @click.option("--msstats_file", help="the MSstats input file, this will be considered the main format to convert", required=True)
 @click.option("--mztab_file", help="the mzTab file, this will be used to extract the protein information", required=True)
+@click.option("--consensusxml_file", help="the consensusXML file used to retrieve the mz/rt", required=False)
 @click.option("--output_folder", help="Folder where the Json file will be generated", required=True)
-@click.option("--output_file", help="Prefix of parquet file", required=False)
-@click.option("--delete_existing", help="Delete existing files in the output folder", is_flag=True)
-def convert_feature_file(sdrf_file: str, msstats_file: str, mztab_file: str, output_folder: str,
-                         output_file: str, delete_existing: bool):
+@click.option("--output_file", help="Parquet file name", required=False)
+def convert_feature_file(sdrf_file: str, msstats_file: str, mztab_file: str, consensusxml_file: str, output_folder: str,
+                         output_file: str):
     """
     Convert a msstats/mztab file to a parquet file. The parquet file will contain the features and the metadata.
     :param sdrf_file: the SDRF file needed to extract some of the metadata
     :param msstats_file: the MSstats input file, this will be considered the main format to convert
     :param mztab_file: the mzTab file, this will be used to extract the protein information
+    :param consensusxml_file: the consensusXML file used to retrieve the mz/rt
     :param output_folder: Folder where the Json file will be generated
     :param output_file: Prefix of the Json file needed to generate the file name
-    :param delete_existing: Delete existing files in the output folder
     :return: none
     """
 
     if sdrf_file is None or msstats_file is None or mztab_file is None or output_folder is None:
         raise click.UsageError("Please provide all the required parameters")
 
     feature_manager = FeatureHandler()
-    feature_manager.parquet_path = output_folder + "/" + output_file + ".parquet"
-    feature_manager.convert_mztab_msstats_to_feature(
+    feature_manager.parquet_path = output_folder + "/" + output_file
+    if consensusxml_file is not None:
+        feature_manager.convert_mztab_msstats_to_feature(
+            mztab_file=mztab_file,
+            msstats_file=msstats_file,
+            sdrf_file=sdrf_file,
+            consesusxml_file=consensusxml_file,
+            use_cache=True
+        )
+    else:
+        feature_manager.convert_mztab_msstats_to_feature(
         mztab_file=mztab_file,
         msstats_file=msstats_file,
-        sdrf_file=sdrf_file, use_cache=True
-    )
+        sdrf_file=sdrf_file, use_cache=True)
 
 
 

python/quantmsio/quantms_io/core/feature.py

@@ -362,7 +362,6 @@ def convert_mztab_msstats_to_feature(self, msstats_file: str, sdrf_file: str, mz
         feature_table = self.create_feature_table(feature_list)
         # Write the feature table to a parquet file
 
-        self.parquet_path = "feature.parquet"
         self.write_single_file_parquet(feature_table, write_metadata=True)
         mztab_handler.close()
 

python/quantmsio/requirements.txt

@@ -5,3 +5,4 @@ requests
 numpy
 pyarrow
 diskcache
+pyopenms

python/quantmsio/setup.py

@@ -35,7 +35,7 @@ def get_version(rel_path):
     package_data={"": ["*.xml"],},
     url="https://github.com/bigbio/quantms.io",
     packages=find_packages(),
-    install_requires=["click", "pandas", "pandas_schema", "requests", "pytest", "pyyaml", "pyarrow", "diskcache"],
+    install_requires=["click", "pandas", "pandas_schema", "requests", "pytest", "pyyaml", "pyarrow", "diskcache", "pyopenms"],
     entry_points={"console_scripts": ["quantmsio_cli = quantms_io.quantmsio_cli:quantms_io_main"]},
     platforms=["any"],
     classifiers=[