Merge pull request #80 from wilhelm-lab/feature/generic_model_support

Feature/generic model support

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Mario Picciani
 email: [email protected]
 project_name: spectrum_io
 project_short_description: IO related functionalities for oktoberfest.
-version: 0.3.4
+version: 0.4.0
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.3.4 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.3.4 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.4.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.4.0 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2022, Mario Picciani
+Copyright (c) 2023, Wilhelmlab at Technical University of Munich
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.4
+current_version = 0.4.0
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_io/__init__.py

docs/conf.py

@@ -53,9 +53,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.3.4"
+version = "0.4.0"
 # The full version, including alpha/beta/rc tags.
-release = "0.3.4"
+release = "0.4.0"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

pyproject.toml

@@ -1,8 +1,8 @@
 [tool.poetry]
 name = "spectrum_io"
-version = "0.3.4"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.4.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "IO related functionalities for oktoberfest."
-authors = ["Mario Picciani <[email protected]>"]
+authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"
 readme = "README.rst"
 homepage = "https://github.com/wilhelm-lab/spectrum_io"
@@ -30,7 +30,7 @@ pymzml = "^2.5.0"
 pyteomics = "^4.3.3"
 lxml= '^4.5.2'
 tables = "^3.6.1"
-spectrum-fundamentals = ">=0.4.4,<0.5.0"
+spectrum-fundamentals = ">=0.5.0,<0.6.0"
 
 [tool.poetry.dev-dependencies]
 pytest = ">=6.2.3"

spectrum_io/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Mario Picciani"
 __email__ = "[email protected]"
-__version__ = "0.3.4"
+__version__ = "0.4.0"
 
 import logging
 import logging.handlers

spectrum_io/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.3.4", message=click.style("spectrum_io Version: 0.3.4"))
+@click.version_option(version="0.4.0", message=click.style("spectrum_io Version: 0.4.0"))
 def main() -> None:
     """spectrum_io."""
 

spectrum_io/raw/msraw.py

@@ -157,6 +157,7 @@ def _read_mzml_pymzml(file_list: List[Path], scanidx: Optional[List] = None, *ar
                 file_name = file_path.stem
                 mass_analyzer = get_mass_analyzer(file_path)
                 namespace = "{http://psi.hupo.org/ms/mzml}"
+                instrument_name = data_iter.info["referenceable_param_group_list_element"][0][0].get("name")
 
                 if scanidx is None:
                     spectra = data_iter
@@ -204,6 +205,7 @@ def _read_mzml_pymzml(file_list: List[Path], scanidx: Optional[List] = None, *ar
                         mass_analyzer.get(instrument_configuration_ref, "unknown"),
                         fragmentation,
                         collision_energy,
+                        instrument_name,
                     ]
                 data_iter.close()
         data = pd.DataFrame.from_dict(data_dict, orient="index", columns=MZML_DATA_COLUMNS)
@@ -217,6 +219,7 @@ def _read_mzml_pyteomics(file_list: List[Path], *args, **kwargs) -> pd.DataFrame
             logger.info(f"Reading mzML file: {file_path}")
             data_iter = mzml.read(source=str(file_path), *args, **kwargs)
             file_name = file_path.stem
+            instrument_name = list(data_iter.get_by_id("commonInstrumentParams").keys())[1]
             for spec in data_iter:
                 if spec["ms level"] != 2:
                     continue  # filter out ms1 spectra if there are any
@@ -250,6 +253,7 @@ def _read_mzml_pyteomics(file_list: List[Path], *args, **kwargs) -> pd.DataFrame
                     mass_analyzer.get(instrument_configuration_ref, "unknown"),
                     fragmentation,
                     collision_energy,
+                    instrument_name,
                 ]
             data_iter.close()
         data = pd.DataFrame.from_dict(data_dict, orient="index", columns=MZML_DATA_COLUMNS)

spectrum_io/spectral_library/spectronaut.py

@@ -111,7 +111,8 @@ def prepare_spectrum(self):
         inter_df["iRT"] = irt.tolist()
         if len(list(self.grpc_output)) > 2:
             inter_df["proteotypicity"] = proteotypicity.tolist()
-        inter_df["intensities"], inter_df["fragment_mz"] = intensities.tolist(), fragment_mz.tolist()
+        inter_df["intensities"] = intensities.tolist()
+        inter_df["fragment_mz"] = fragment_mz.tolist()
         inter_df["fragment_types"] = fragment_types.tolist()
         inter_df["fragment_numbers"] = fragment_numbers.tolist()
         inter_df["fragment_charges"] = fragment_charges.tolist()