Merge pull request #87 from wilhelm-lab/patch/0.5.1

Patch/0.5.1

.cookietemple.yml

@@ -15,5 +15,5 @@ full_name: Victor Giurcoiu
 email: [email protected]
 project_name: spectrum_fundamentals
 project_short_description: Fundamentals public repo
-version: 0.5.0
+version: 0.5.1
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.5.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.5.0 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.5.1 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.5.1 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/run_tests.yml

@@ -1,8 +1,14 @@
 name: Run spectrum_fundamentals Tests
 
 on:
-    - push
-    - pull_request
+    push:
+        branches:
+            - development
+            - main
+            - "release/*"
+    pull_request:
+        branches:
+            - "*"
 
 jobs:
     tests:

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.5.0
+current_version = 0.5.1
 
 [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 = "0.5.0"
+version = "0.5.1"
 # The full version, including alpha/beta/rc tags.
-release = "0.5.0"
+release = "0.5.1"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

noxfile.py

@@ -1,4 +1,5 @@
 """Nox sessions."""
+
 import os
 import shlex
 import shutil

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "spectrum_fundamentals"
-version = "0.5.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.5.1"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "Fundamental functions, annotation pipeline and constants for oktoberfest"
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"

requirements.txt

@@ -1,8 +1,29 @@
-click>=8.0.0
-rich>=10.3.0
-PyYAML>=5.4.1
-numpy>=1.24.1
-pandas>=1.3.0
-scikit-learn>=1.0
-joblib>=1.0.1
-moepy>=1.1.4
+click==8.1.7 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+colorama==0.4.6 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0" and platform_system == "Windows"
+contourpy==1.1.1 ; python_version >= "3.8" and python_full_version < "3.11.0"
+cycler==0.12.1 ; python_version >= "3.8" and python_full_version < "3.11.0"
+fonttools==4.51.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+importlib-resources==6.4.0 ; python_version >= "3.8" and python_version < "3.10"
+joblib==1.4.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+kiwisolver==1.4.5 ; python_version >= "3.8" and python_full_version < "3.11.0"
+markdown-it-py==3.0.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+matplotlib==3.7.5 ; python_version >= "3.8" and python_full_version < "3.11.0"
+mdurl==0.1.2 ; python_version >= "3.8" and python_full_version < "3.11.0"
+moepy==1.1.4 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+numpy==1.24.4 ; python_version >= "3.8" and python_full_version < "3.11.0"
+packaging==24.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+pandas==1.5.3 ; python_version >= "3.8" and python_full_version < "3.11.0"
+pillow==10.3.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+pygments==2.17.2 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+pyparsing==3.1.2 ; python_version >= "3.8" and python_full_version < "3.11.0"
+python-dateutil==2.9.0.post0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+pytz==2024.1 ; python_version >= "3.8" and python_full_version < "3.11.0"
+pyyaml==6.0.1 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+rich==13.7.1 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+scikit-learn==1.3.2 ; python_version >= "3.8" and python_full_version < "3.11.0"
+scipy==1.10.1 ; python_version >= "3.8" and python_full_version < "3.11.0"
+six==1.16.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+threadpoolctl==3.4.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+tqdm==4.66.2 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+typing-extensions==4.11.0 ; python_version >= "3.8" and python_version < "3.9"
+zipp==3.18.1 ; python_version >= "3.8" and python_version < "3.10"

spectrum_fundamentals/__init__.py

@@ -1,7 +1,8 @@
 """Initialize fundamentals."""
+
 __author__ = "Mario Picciani"
 __email__ = "[email protected]"
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 
 import logging
 import logging.handlers

spectrum_fundamentals/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.5.0", message=click.style("spectrum_fundamentals Version: 0.5.0"))
+@click.version_option(version="0.5.1", message=click.style("spectrum_fundamentals Version: 0.5.1"))
 def main() -> None:
     """spectrum_fundamentals."""
 

spectrum_fundamentals/charge.py

@@ -22,7 +22,7 @@ def indices_to_one_hot(labels: Union[int, List[int], np.ndarray], classes: Optio
             f"Type of labels not understood. Only int, List[int] and np.ndarray are supported. Given: {type(labels)}."
         )
 
-    max_label = labels.max()
+    max_label = int(labels.max())
     if classes is None:
         classes = max_label
     if max_label > classes:

spectrum_fundamentals/constants.py

@@ -109,6 +109,17 @@
     "n[214]": "[UNIMOD:214]-",
 }
 
+#######################
+# Xisearch constants #
+#######################
+
+XISEARCH_VAR_MODS = {
+    "ox": "[UNIMOD:35]",
+    "cm": "[UNIMOD:4]",
+    "dsso": "[UNIMOD:1896]",
+    "dsbu": "[UNIMOD:1884]",
+}
+
 ####################
 # MASS CALCULATION #
 ####################

spectrum_fundamentals/metrics/fragments_ratio.py

@@ -31,7 +31,7 @@ class FragmentsRatio(Metric):
 
     @staticmethod
     def count_with_ion_mask(
-        boolean_array: scipy.sparse.csr_matrix, ion_mask: Optional[Union[np.ndarray, scipy.sparse.csr_matrix]] = None
+        boolean_array: scipy.sparse.csr_matrix, ion_mask: Optional[Union[np.ndarray, scipy.sparse.spmatrix]] = None
     ) -> np.ndarray:
         """
         Count the number of ions.
@@ -43,8 +43,6 @@ def count_with_ion_mask(
         :return: number of observed/predicted peaks not masked by ion_mask
         """
         if ion_mask is None:
-            ion_mask = []
-        if len(ion_mask) == 0:
             ion_mask = scipy.sparse.csr_matrix(np.ones((174, 1)))
         else:
             ion_mask = scipy.sparse.csr_matrix(ion_mask).T

spectrum_fundamentals/mod_string.py

@@ -1,9 +1,20 @@
 import difflib
 import re
 from itertools import repeat
-from typing import Dict, List, Optional, Tuple
+from typing import Dict, List, Optional, Tuple, Union
 
-from .constants import MAXQUANT_VAR_MODS, MOD_MASSES, MOD_MASSES_SAGE, MOD_NAMES, MSFRAGGER_VAR_MODS, SPECTRONAUT_MODS
+import numpy as np
+import pandas as pd
+
+from .constants import (
+    MAXQUANT_VAR_MODS,
+    MOD_MASSES,
+    MOD_MASSES_SAGE,
+    MOD_NAMES,
+    MSFRAGGER_VAR_MODS,
+    SPECTRONAUT_MODS,
+    XISEARCH_VAR_MODS,
+)
 
 
 def sage_to_internal(sequences: List[str]) -> List[str]:
@@ -54,7 +65,60 @@ def replace(match):
     return modified_strings
 
 
-def internal_to_spectronaut(sequences: List[str]) -> List[str]:
+def xisearch_to_internal(
+    xl: str,
+    seq: str,
+    mod: str,
+    crosslinker_position: int,
+    mod_positions: str,
+):
+    """
+    Function to translate a xisearch modstring to the XL-Prosit format.
+
+    :param xl: type of crosslinker used. Can be 'DSSO' or 'DSBU'.
+    :param seq: unmodified peptide sequence
+    :param mod: all modifications of pep
+    :param crosslinker_position: crosslinker position of peptide
+    :param mod_positions: position of all modifications of peptide
+    :raises ValueError: if suplied type of crosslinker is unknown
+
+    :return: modified sequence
+    """
+
+    def add_mod_sequence(split_seq: List[str], mods: str, mod_positions: str):
+        """
+        Apply modifications.
+
+        :param split_seq: List containing the sequence characters
+        :param mods: String containing modifications
+        :param mod_positions: String containing positions of modifications
+        """
+        if mod_positions.lower() in ["", "nan", "null"]:
+            return
+
+        split_mod = mods.split(";")
+        split_mod_positions = mod_positions.split(";")
+
+        for mod, pos in zip(split_mod, split_mod_positions):
+            modification = XISEARCH_VAR_MODS.get(mod)
+            pos_mod = int(pos)
+            if modification:
+                split_seq[pos_mod - 1] += modification
+            else:
+                split_seq[pos_mod - 1] += f"({mod})"
+
+    # Check the crosslinker type and apply modification accordingly
+    modification = XISEARCH_VAR_MODS.get(xl.lower())
+    if modification is None:
+        raise ValueError(f"Unknown crosslinker type provided: {xl}. Only 'DSSO' and 'DSBU' are supported.")
+
+    split_seq = [x for x in seq]
+    add_mod_sequence(split_seq, mod, mod_positions)
+    split_seq[crosslinker_position - 1] += modification
+    return "".join(split_seq)
+
+
+def internal_to_spectronaut(sequences: Union[np.ndarray, pd.Series, List[str]]) -> List[str]:
     """
     Function to translate a modstring from the internal format to the spectronaut format.
 
@@ -65,7 +129,9 @@ def internal_to_spectronaut(sequences: List[str]) -> List[str]:
     return [regex.sub(lambda mo: SPECTRONAUT_MODS[mo.string[mo.start() : mo.end()]], seq) for seq in sequences]
 
 
-def maxquant_to_internal(sequences: List[str], fixed_mods: Optional[Dict[str, str]] = None) -> List[str]:
+def maxquant_to_internal(
+    sequences: Union[np.ndarray, pd.Series, List[str]], fixed_mods: Optional[Dict[str, str]] = None
+) -> List[str]:
     """
     Function to translate a MaxQuant modstring to the Prosit format.
 
@@ -116,7 +182,9 @@ def find_replacement(match: re.Match) -> str:
     return [regex.sub(find_replacement, seq).replace("_", "") for seq in sequences]
 
 
-def msfragger_to_internal(sequences: List[str], fixed_mods: Optional[Dict[str, str]] = None) -> List[str]:
+def msfragger_to_internal(
+    sequences: Union[np.ndarray, pd.Series, List[str]], fixed_mods: Optional[Dict[str, str]] = None
+) -> List[str]:
     """
     Function to translate a MSFragger modstring to the Prosit format.
 

tests/test_main.py

@@ -1,4 +1,5 @@
 """Test cases for the __main__ module."""
+
 import pytest
 from click.testing import CliRunner
 

tests/unit_tests/test_charge.py

@@ -8,9 +8,6 @@
 class TestCharge(unittest.TestCase):
     """Class to test charge."""
 
-    def test_indices_to_one_hot(self):
-        """Test get_mask_observed_valid."""
-
     def test_indices_to_one_hot_with_classes(self):
         """Test indices_to_one_hot with given number of classes."""
         labels = np.array([1, 2, 3])
@@ -38,17 +35,6 @@ def test_indices_to_one_hot_with_list_and_class(self):
         expected_output = np.array([[1, 0, 0, 0], [0, 1, 0, 0], [0, 0, 1, 0]])
         np.testing.assert_equal(charge.indices_to_one_hot(labels, classes), expected_output)
 
-    """
-    def test_indices_to_one_hot_with_wrong_input_type(self):
-        # Test indices_to_one_hot correctly raises TypeError on wrong input type.
-        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."""
         labels = [1, 2, 3]

tests/unit_tests/test_mod_string.py

@@ -37,6 +37,53 @@ def test_sage_to_internal_tmt(self):
         )
 
 
+class TestXisearchToInternal(unittest.TestCase):
+    """Class to test Internal to Xisearch."""
+
+    def test_internal_to_xisearch_carbamidomethylation_oxidation_dsso(self):
+        """Test internal_to_xisearch_carbamidomethylation and oxidation along with DSSO as crosslinker ."""
+        self.assertEqual(
+            mod.xisearch_to_internal(
+                xl="DSSO", seq="SNVPALEACPQKR", mod="cm", crosslinker_position=12, mod_positions="9"
+            ),
+            ("SNVPALEAC[UNIMOD:4]PQK[UNIMOD:1896]R"),
+        )
+
+    def test_internal_to_xisearch_no_modification_dsso(self):
+        """Test internal_to_xisearch_no_variable along with DSSO as crosslinker."""
+        self.assertEqual(
+            mod.xisearch_to_internal(
+                xl="DSSO", seq="SNVPALEACPQKR", mod="NaN", crosslinker_position=12, mod_positions="NaN"
+            ),
+            ("SNVPALEACPQK[UNIMOD:1896]R"),
+        )
+
+    def test_internal_to_xisearch_carbamidomethylation_oxidation_dsbu(self):
+        """Test internal_to_xisearch_carbamidomethylation and oxidation along with DSBU as crosslinker."""
+        self.assertEqual(
+            mod.xisearch_to_internal(
+                xl="DSBU", seq="SNVPALEACPQKR", mod="cm", crosslinker_position=12, mod_positions="9"
+            ),
+            ("SNVPALEAC[UNIMOD:4]PQK[UNIMOD:1884]R"),
+        )
+
+    def test_internal_to_xisearch_no_modification_dsbu(self):
+        """Test internal_to_xisearch_no_variable along with DSBU as crosslinker."""
+        self.assertEqual(
+            mod.xisearch_to_internal(
+                xl="DSBU", seq="SNVPALEACPQKR", mod="NaN", crosslinker_position=12, mod_positions="NaN"
+            ),
+            ("SNVPALEACPQK[UNIMOD:1884]R"),
+        )
+
+    def test_internal_to_xisearch_double_modifications(self):
+        """Test internal_to_xisearch_double_variable."""
+        self.assertEqual(
+            mod.xisearch_to_internal(xl="DSSO", seq="MKRM", mod="ox;ox", crosslinker_position=2, mod_positions="1;4"),
+            ("M[UNIMOD:35]K[UNIMOD:1896]RM[UNIMOD:35]"),
+        )
+
+
 class TestMaxQuantToInternal(unittest.TestCase):
     """Class to test MaxQuant to internal."""