Merge pull request #65 from wilhelm-lab/release/0.4.1

Release/0.4.1

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: [email protected]
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.4.0
+version: 0.4.1
 license: MIT

.flake8

@@ -1,6 +1,6 @@
 [flake8]
 select = B,B9,C,D,DAR,E,F,N,RST,S,W
-ignore = E203,E501,RST201,RST203,RST301,W503,D100,D212,S101,E731,S404,S603,S607
+ignore = E203,E501,RST201,RST203,RST301,W503,D100,D212,S101,E731,S404,S603,S607,B905
 max-line-length = 120
 max-complexity = 10
 docstring-convention = google

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.4.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.4.0 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.4.1 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.4.1 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.0
+current_version = 0.4.1
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_fundamentals/__init__.py

docs/conf.py

@@ -54,9 +54,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.4.0"
+version = "0.4.1"
 # The full version, including alpha/beta/rc tags.
-release = "0.4.0"
+release = "0.4.1"
 
 # 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 = "0.4.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.4.1"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "Fundamentals public repo"
 authors = ["WassimG <[email protected]>"]
 license = "MIT"

spectrum_fundamentals/__init__.py

@@ -1,7 +1,7 @@
 """Initialize fundamentals."""
 __author__ = "Victor Giurcoiu"
 __email__ = "[email protected]"
-__version__ = "0.4.0"
+__version__ = "0.4.1"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.4.0", message=click.style("spectrum_fundamentals Version: 0.4.0"))
+@click.version_option(version="0.4.1", message=click.style("spectrum_fundamentals Version: 0.4.1"))
 def main() -> None:
     """spectrum_fundamentals."""
 

spectrum_fundamentals/annotation/annotation.py

@@ -11,7 +11,7 @@
 
 
 def match_peaks(
-    fragments_meta_data: pd.DataFrame,
+    fragments_meta_data: List[dict],
     peaks_intensity: np.ndarray,
     peaks_masses: np.ndarray,
     tmt_n_term: int,
@@ -37,7 +37,8 @@ def match_peaks(
     next_start_peak = 0
     seq_len = len(unmod_sequence)
     matched_peak = False
-    for _, fragment in fragments_meta_data.iterrows():
+    fragment_no: float
+    for fragment in fragments_meta_data:
         min_mass = fragment["min_mass"]
         max_mass = fragment["max_mass"]
         fragment_no = fragment["no"]

spectrum_fundamentals/fragments.py

@@ -1,8 +1,8 @@
 import logging
+from operator import itemgetter
 from typing import Dict, List, Optional, Tuple
 
 import numpy as np
-import pandas as pd
 
 from . import constants as constants
 
@@ -106,7 +106,7 @@ def compute_peptide_mass(sequence: str) -> float:
     return forward_sum + ion_type_offsets[0] + ion_type_offsets[1]
 
 
-def initialize_peaks(sequence: str, mass_analyzer: str, charge: int) -> Tuple[pd.DataFrame, int, str, float]:
+def initialize_peaks(sequence: str, mass_analyzer: str, charge: int) -> Tuple[List[dict], int, str, float]:
     """
     Generate theoretical peaks for a modified peptide sequence.
 
@@ -123,13 +123,9 @@ def initialize_peaks(sequence: str, mass_analyzer: str, charge: int) -> Tuple[pd
     else:
         modification_deltas, tmt_n_term, peptide_sequence = modifications
 
-    col_dtypes = {"ion_type": str, "no": int, "charge": float, "mass": float, "min_mass": float, "max_mass": float}
     peptide_length = len(peptide_sequence)
-
     if peptide_length > 30:
-        df_out = pd.DataFrame(columns=col_dtypes.keys())
-        df_out = df_out.astype(col_dtypes)
-        return df_out, -1, "", 0.0
+        return [{}], -1, "", 0.0
 
     # initialize constants
     if int(round(charge)) <= 3:
@@ -181,18 +177,17 @@ def initialize_peaks(sequence: str, mass_analyzer: str, charge: int) -> Tuple[pd
                 mass = (ion_type_masses[ion_type] + charge_delta) / charge
                 min_mass, max_mass = get_min_max_mass(mass_analyzer, mass)
                 fragments_meta_data.append(
-                    [
-                        ion_types[ion_type],  # ion type
-                        i + 1,  # no
-                        charge,  # charge
-                        mass,  # mass
-                        min_mass,  # min mass
-                        max_mass,  # max mass
-                    ]
+                    {
+                        "ion_type": ion_types[ion_type],  # ion type
+                        "no": i + 1,  # no
+                        "charge": charge,  # charge
+                        "mass": mass,  # mass
+                        "min_mass": min_mass,  # min mass
+                        "max_mass": max_mass,  # max mass
+                    }
                 )
-    df_out = pd.DataFrame(data=fragments_meta_data, columns=col_dtypes.keys())
-    df_out.sort_values(by="mass", inplace=True)
-    return df_out, tmt_n_term, peptide_sequence, (forward_sum + ion_type_offsets[0] + ion_type_offsets[1])
+    fragments_meta_data = sorted(fragments_meta_data, key=itemgetter("mass"))
+    return fragments_meta_data, tmt_n_term, peptide_sequence, (forward_sum + ion_type_offsets[0] + ion_type_offsets[1])
 
 
 def get_min_max_mass(mass_analyzer: str, mass: float) -> Tuple[float, float]:

spectrum_fundamentals/metrics/similarity.py

@@ -216,8 +216,8 @@ def correlation(
         :param method: either pearson or spearman
         :return: calculated correlations
         """
-        observed_intensities = observed_intensities.toarray()
-        predicted_intensities = predicted_intensities.toarray()
+        obs_int_arr = observed_intensities.toarray()
+        pred_int_arr = predicted_intensities.toarray()
 
         if charge != 0:
             if charge == 1:
@@ -232,13 +232,13 @@ def correlation(
                 boolean_array = constants.Y_ION_MASK
 
             boolean_array = scipy.sparse.csr_matrix(boolean_array)
-            observed_intensities = scipy.sparse.csr_matrix(observed_intensities)
-            predicted_intensities = scipy.sparse.csr_matrix(predicted_intensities)
-            observed_intensities = observed_intensities.multiply(boolean_array).toarray()
-            predicted_intensities = predicted_intensities.multiply(boolean_array).toarray()
+            obs_int_arr = scipy.sparse.csr_matrix(obs_int_arr)
+            pred_int_arr = scipy.sparse.csr_matrix(pred_int_arr)
+            obs_int_arr = obs_int_arr.multiply(boolean_array).toarray()
+            pred_int_arr = pred_int_arr.multiply(boolean_array).toarray()
 
         pear_corr = []
-        for obs, pred in zip(observed_intensities, predicted_intensities):
+        for obs, pred in zip(obs_int_arr, pred_int_arr):
             valid_ion_mask = pred > constants.EPSILON
             obs = obs[valid_ion_mask]
             pred = pred[valid_ion_mask]

tests/unit_tests/test_charge.py

@@ -40,8 +40,12 @@ def test_indices_to_one_hot_with_list_and_class(self):
 
     def test_indices_to_one_hot_with_wrong_input_type(self):
         """Test indices_to_one_hot correctly raises TypeError on wrong input type."""
-        labels = None
-        self.assertRaises(TypeError, charge.indices_to_one_hot, labels)
+        try:
+            labels = None
+            self.assertRaises(TypeError, charge.indices_to_one_hot, labels)
+        except Exception as e:  # explicitly silence typeguard.TypeCheckError here without importing TypeGuard
+            if e.__class__.__name__ != "TypeCheckError":
+                raise
 
     def test_indices_to_one_hot_with_incompatible_classes(self):
         """Test indices_to_one_hot correctly raises TypeError on wrong input type."""