Merge pull request #142 from wilhelm-lab/release/0.7.4

release/0.7.4

Author: WassimG

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: victor.giurcoiu@tum.de
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.7.3
+version: 0.7.4
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.7.3 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.7.3 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.7.4 " # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.7.4 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/run_tests.yml

@@ -119,6 +119,7 @@ jobs:
               if: always() && matrix.session == 'tests' && matrix.os == 'ubuntu-latest'
               uses: actions/upload-artifact@v4
               with:
+                  include-hidden-files: "true"
                   name: coverage-data
                   path: ".coverage.*"
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.7.3
+current_version = 0.7.4
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_fundamentals/__init__.py

docs/_key_contributors.rst

@@ -2,24 +2,21 @@
 
    Current developers
 
-   * `Mario Picciani <https://github.com/picciama>`_: lead developer since 2022, maintainer
-   * `Mostafa Kalhor <https://github.com/mostafakalhor>`_: developer, crosslinking
-   * `Wassim Gabriel <https://github.com/WassimG>`_: developer, PTMs, neutral losses, GUI
-   * `Arne van den Berg <https://github.com/arne-vdb>`_: developer, diverse contributions
-   * `Victor-George Giurcoiu <https://github.com/victorgiurcoiu>`_: developer, diverse contributions
-   * `Ludwig Lautenbacher <https://github.com/LLautenbacher>`_: developer, Koina, GUI
-   * `Armin Soleymaniniya <https://github.com/arminsl>`_: developer, GUI
-   * `Ayla Schröder <https://github.com/ayla-s>`_: developer, pickedGroupFDR
-   * Zixuan Xiao: developer, GUI
-
-   Previous developers
-
-   * `Matthew The <https://github.com/MatthewThe>`_: developer, percolator
-   * `Omar Shouman <https://github.com/omsh>`_: developer, diverse contributions
-   * Firas Hamood: developer, diverse contributions
-   * Cecilia Jensen: developer, diverse contributions
-   * Julian Mueller: developer, diverse contributions
+   * `Arne van den Berg <https://github.com/arne-vdb>`_
+   * `Wassim Gabriel <https://github.com/WassimG>`_
+   * `Victor-George Giurcoiu <https://github.com/victorgiurcoiu>`_
+   * `Firas Hamood <https://github.com/fhamood>`_
+   * `Cecilia Jensen`_
+   * `Mostafa Kalhor <https://github.com/mostafakalhor>`_
+   * `Ludwig Lautenbacher <https://github.com/LLautenbacher>`_
+   * `Julian Mueller <https://github.com/jmueller95>`_
+   * `Mario Picciani <https://github.com/picciama>`_
+   * `Ayla Schröder <https://github.com/ayla-s>`_
+   * `Omar Shouman <https://github.com/omsh>`_
+   * `Armin Soleymaniniya <https://github.com/arminsl>`_
+   * `Matthew The <https://github.com/MatthewThe>`_
+   * `Zixuan Xiao <https://github.com/zix-xiao>`_
 
    Other roles
 
-   * `Mathias Wilhelm <https://github.com/mwilhelm42>`_: advisor and PI of wilhelmlab
+   * `Mathias Wilhelm <https://github.com/mwilhelm42>`_ advisor and PI of wilhelmlab

docs/conf.py

@@ -52,9 +52,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.7.3"
+version = "0.7.4"
 # The full version, including alpha/beta/rc tags.
-release = "0.7.3"
+release = "0.7.4"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "spectrum_fundamentals"
-version = "0.7.3"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.7.4"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "Fundamental functions, annotation pipeline and constants for oktoberfest"
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"

spectrum_fundamentals/__init__.py

@@ -1,8 +1,11 @@
 """Spectrum Fundamentals."""
 
-__author__ = "Mario Picciani"
-__email__ = "mario.picciani@tum.de"
-__version__ = "0.7.3"
+from datetime import datetime
+
+__author__ = """The Oktoberfest development team (Wilhelmlab at Technical University of Munich)"""
+__copyright__ = f"Copyright {datetime.now():%Y}, Wilhelmlab at Technical University of Munich"
+__license__ = "MIT"
+__version__ = "0.7.4"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.7.3", message=click.style("spectrum_fundamentals Version: 0.7.3"))
+@click.version_option(version="0.7.4", message=click.style("spectrum_fundamentals Version: 0.7.4"))
 def main() -> None:
     """spectrum_fundamentals."""
 

spectrum_fundamentals/annotation/annotation.py

@@ -17,7 +17,7 @@ def match_peaks(
     tmt_n_term: int,
     unmod_sequence: str,
     charge: int,
-) -> List[Dict[str, Union[str, int, float]]]:
+) -> Tuple[List[Dict[str, Union[str, int, float]]], int]:
     """
     Matching experimental peaks with theoretical fragment ions.
 
@@ -36,6 +36,7 @@ def match_peaks(
     temp_list = []
     next_start_peak = 0
     matched_peak = False
+    count_annotated_nl = 0
     fragment_no: float
     for fragment in fragments_meta_data:
         min_mass = fragment["min_mass"]
@@ -56,27 +57,32 @@ def match_peaks(
             if (
                 not (fragment["ion_type"][0] == "b" and fragment_no == 1)
                 or (unmod_sequence[0] == "R" or unmod_sequence[0] == "H" or unmod_sequence[0] == "K")
-                and (tmt_n_term == 1)
+                or (tmt_n_term == 2)
             ):
-                row_list.append(
-                    {
-                        "ion_type": fragment["ion_type"],
-                        "no": fragment_no,
-                        "charge": fragment["charge"],
-                        "exp_mass": peak_mass,
-                        "theoretical_mass": fragment["mass"],
-                        "intensity": peak_intensity,
-                    }
-                )
-                if peak_intensity > max_intensity:
-                    max_intensity = float(peak_intensity)
+                # For now only counting neutral loss peaks this can change with different models later
+                if fragment["neutral_loss"] == "":
+                    row_list.append(
+                        {
+                            "ion_type": fragment["ion_type"],
+                            "no": fragment_no,
+                            "charge": fragment["charge"],
+                            "exp_mass": peak_mass,
+                            "theoretical_mass": fragment["mass"],
+                            "intensity": peak_intensity,
+                        }
+                    )
+                    if peak_intensity > max_intensity:
+                        max_intensity = float(peak_intensity)
+                else:
+                    count_annotated_nl += 1
+
             matched_peak = True
             next_start_peak = start_peak
             start_peak += 1
     for row in row_list:
         row["intensity"] = float(row["intensity"]) / max_intensity
         temp_list.append(row)
-    return temp_list
+    return temp_list, count_annotated_nl
 
 
 def handle_multiple_matches(
@@ -123,6 +129,7 @@ def annotate_spectra(
     unit_mass_tolerance: Optional[str] = None,
     custom_mods: Optional[Dict[str, float]] = None,
     fragmentation_method: str = "HCD",
+    annotate_neutral_loss: Optional[bool] = False,
 ) -> pd.DataFrame:
     """
     Annotate a set of spectra.
@@ -143,6 +150,7 @@ def annotate_spectra(
     :param unit_mass_tolerance: unit for the mass tolerance (da or ppm)
     :param fragmentation_method: fragmentation method that was used
     :param custom_mods: mapping of custom UNIMOD string identifiers ('[UNIMOD:xyz]') to their mass
+    :param annotate_neutral_loss: flag to indicate whether to annotate neutral losses or not
     :return: a Pandas DataFrame containing the annotated spectra with meta data
     """
     raw_file_annotations = []
@@ -155,14 +163,22 @@ def annotate_spectra(
             unit_mass_tolerance,
             fragmentation_method=fragmentation_method,
             custom_mods=custom_mods,
+            annotate_neutral_losses=annotate_neutral_loss,
         )
         if not results:
             continue
         raw_file_annotations.append(results)
     results_df = pd.DataFrame(raw_file_annotations)
 
     if "CROSSLINKER_TYPE" not in index_columns:
-        results_df.columns = ["INTENSITIES", "MZ", "CALCULATED_MASS", "removed_peaks"]
+        results_df.columns = [
+            "INTENSITIES",
+            "MZ",
+            "CALCULATED_MASS",
+            "removed_peaks",
+            "ANNOTATED_NL_COUNT",
+            "EXPECTED_NL_COUNT",
+        ]
     else:
         results_df.columns = [
             "INTENSITIES_A",
@@ -347,9 +363,10 @@ def parallel_annotate(
     unit_mass_tolerance: Optional[str] = None,
     custom_mods: Optional[Dict[str, float]] = None,
     fragmentation_method: str = "HCD",
+    annotate_neutral_losses: Optional[bool] = False,
 ) -> Optional[
     Union[
-        Tuple[np.ndarray, np.ndarray, float, int],
+        Tuple[np.ndarray, np.ndarray, float, int, int, int],
         Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, float, float, int, int],
     ]
 ]:
@@ -369,6 +386,7 @@ def parallel_annotate(
     :param unit_mass_tolerance: unit for the mass tolerance (da or ppm)
     :param custom_mods: mapping of custom UNIMOD string identifiers ('[UNIMOD:xyz]') to their mass
     :param fragmentation_method: fragmentation method that was used
+    :param annotate_neutral_losses: flag to indicate whether to annotate neutral losses or not
     :return: a tuple containing intensity values (np.ndarray), masses (np.ndarray), calculated mass (float),
              and any removed peaks (List[str])
     """
@@ -383,6 +401,7 @@ def parallel_annotate(
             unit_mass_tolerance,
             fragmentation_method=fragmentation_method,
             custom_mods=custom_mods,
+            add_neutral_losses=annotate_neutral_losses,
         )
 
     if (spectrum[index_columns["PEPTIDE_LENGTH_A"]] > 30) or (spectrum[index_columns["PEPTIDE_LENGTH_B"]] > 30):
@@ -399,6 +418,7 @@ def _annotate_linear_spectrum(
     unit_mass_tolerance: Optional[str],
     custom_mods: Optional[Dict[str, float]] = None,
     fragmentation_method: str = "HCD",
+    add_neutral_losses: Optional[bool] = False,
 ):
     """
     Annotate a linear peptide spectrum.
@@ -409,21 +429,24 @@ def _annotate_linear_spectrum(
     :param unit_mass_tolerance: Unit for the mass tolerance (da or ppm)
     :param custom_mods: mapping of custom UNIMOD string identifiers ('[UNIMOD:xyz]') to their mass
     :param fragmentation_method: fragmentation method that was used
+    :param add_neutral_losses: flag to indicate whether to annotate neutral losses or not
     :return: Annotated spectrum
     """
     mod_seq_column = "MODIFIED_SEQUENCE"
     if "MODIFIED_SEQUENCE_MSA" in index_columns:
         mod_seq_column = "MODIFIED_SEQUENCE_MSA"
-    fragments_meta_data, tmt_n_term, unmod_sequence, calc_mass = initialize_peaks(
+
+    fragments_meta_data, tmt_n_term, unmod_sequence, calc_mass, expected_nl = initialize_peaks(
         sequence=spectrum[index_columns[mod_seq_column]],
         mass_analyzer=spectrum[index_columns["MASS_ANALYZER"]],
         charge=spectrum[index_columns["PRECURSOR_CHARGE"]],
         mass_tolerance=mass_tolerance,
         unit_mass_tolerance=unit_mass_tolerance,
         fragmentation_method=fragmentation_method,
         custom_mods=custom_mods,
+        add_neutral_losses=add_neutral_losses,
     )
-    matched_peaks = match_peaks(
+    matched_peaks, count_annotated_nl = match_peaks(
         fragments_meta_data,
         spectrum[index_columns["INTENSITIES"]],
         spectrum[index_columns["MZ"]],
@@ -439,13 +462,13 @@ def _annotate_linear_spectrum(
     if len(matched_peaks) == 0:
         intensity = np.full(vec_length, 0.0)
         mass = np.full(vec_length, 0.0)
-        return intensity, mass, calc_mass, 0
+        return intensity, mass, calc_mass, 0, 0, 0
 
     matched_peaks, removed_peaks = handle_multiple_matches(matched_peaks)
     intensities, mass = generate_annotation_matrix(
         matched_peaks, unmod_sequence, spectrum[index_columns["PRECURSOR_CHARGE"]], fragmentation_method
     )
-    return intensities, mass, calc_mass, removed_peaks
+    return intensities, mass, calc_mass, removed_peaks, count_annotated_nl, expected_nl
 
 
 def _annotate_crosslinked_spectrum(
@@ -493,7 +516,7 @@ def _xl_annotation_workflow(seq_id: str, non_cl_xl: bool):
             array_size = 348
         inputs.append(custom_mods)
         fragments_meta_data, tmt_n_term, unmod_sequence, calc_mass = initialize_peaks_xl(*inputs)
-        matched_peaks = match_peaks(
+        matched_peaks, annotated_nl = match_peaks(
             fragments_meta_data,
             np.array(spectrum[index_columns["INTENSITIES"]]),
             np.array(spectrum[index_columns["MZ"]]),  # Convert to numpy array