Merge development into feature/digest_nr_oxidations_arg

.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: 0.4.2
+version: 0.4.3
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.4.2 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.4.2 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.4.3 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.4.3 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

.github/workflows/build_package.yml

@@ -12,7 +12,7 @@ jobs:
                 python: [3.8, 3.9]
 
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
               name: Check out source-code repository
 
             - name: Setup Python

.github/workflows/labeler.yml

@@ -11,7 +11,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             - name: Check out the repository
-              uses: actions/checkout@v2.3.3
+              uses: actions/checkout@v4
 
             - name: Run Labeler
               uses: crazy-max/[email protected]

.github/workflows/publish_docs.yml

@@ -7,7 +7,7 @@ jobs:
         runs-on: ubuntu-latest
 
         steps:
-            - uses: actions/checkout@v2
+            - uses: actions/checkout@v4
               name: Check out source-code repository
 
             - name: Setup Python

.github/workflows/publish_package.yml

@@ -10,7 +10,7 @@ jobs:
         runs-on: ubuntu-latest
         steps:
             - name: Check out the repository
-              uses: actions/checkout@v2.3.4
+              uses: actions/checkout@v4
               with:
                   fetch-depth: 2
 
@@ -29,7 +29,7 @@ jobs:
                   poetry build --ansi
 
             - name: Publish package on PyPI
-              uses: pypa/gh-action-pypi-publish@v1.6.4
+              uses: pypa/gh-action-pypi-publish@v1.8.14
               with:
                   # TODO COOKIETEMPLE: Configure your PyPI Token to enable automatic deployment to PyPi on releases
                   # https://help.github.com/en/actions/configuring-and-managing-workflows/creating-and-storing-encrypted-secrets

.github/workflows/run_cookietemple_lint.yml

@@ -7,7 +7,7 @@ jobs:
         runs-on: ubuntu-latest
 
         steps:
-            - uses: actions/checkout@v2
+            - uses: actions/checkout@v4
               name: Check out source-code repository
 
             - name: Setup Python

.github/workflows/run_tests.yml

@@ -69,7 +69,7 @@ jobs:
 
         steps:
             - name: Check out the repository
-              uses: actions/checkout@v2.3.4
+              uses: actions/checkout@v4
 
             - name: Set up Python ${{ matrix.python-version }}
               uses: actions/setup-python@v4
@@ -104,7 +104,7 @@ jobs:
                   print("::set-output name=result::{}".format(result))
 
             - name: Restore pre-commit cache
-              uses: actions/cache@v3.2.4
+              uses: actions/cache@v4.0.2
               if: matrix.session == 'pre-commit'
               with:
                   path: ~/.cache/pre-commit
@@ -134,7 +134,7 @@ jobs:
         needs: tests
         steps:
             - name: Check out the repository
-              uses: actions/checkout@v3
+              uses: actions/checkout@v4
 
             - name: Set up Python 3.8
               uses: actions/setup-python@v4

.github/workflows/sync_project.yml

@@ -17,7 +17,7 @@ jobs:
             - name: Install cookietemple
               run: pip install cookietemple
 
-            - uses: actions/checkout@v2
+            - uses: actions/checkout@v4
               with:
                   fetch-depth: 0
                   token: "${{ secrets.CT_SYNC_TOKEN }}"

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.2
+current_version = 0.4.3
 
 [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 = "0.4.2"
+version = "0.4.3"
 # The full version, including alpha/beta/rc tags.
-release = "0.4.2"
+release = "0.4.3"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

noxfile.py

@@ -108,6 +108,7 @@ def precommit(session: Session) -> None:
         "flake8",
         "flake8-bandit",
         "flake8-bugbear",
+        "darglint",
         "flake8-docstrings",
         "flake8-rst-docstrings",
         "isort",

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "spectrum_io"
-version = "0.4.2"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.4.3"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "IO related functionalities for oktoberfest."
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"
@@ -29,8 +29,7 @@ h5py = "^3.1.0"
 pymzml = "^2.5.0"
 pyteomics = "^4.3.3"
 lxml= '^4.5.2'
-tables = "^3.6.1"
-spectrum-fundamentals = ">=0.5.0,<0.6.0"
+spectrum-fundamentals = ">=0.5.2,<0.6.0"
 alphatims = "^1.0.8"
 sortedcontainers = "^2.4.0"
 

requirements.txt

@@ -1,11 +1,42 @@
-click>=8.0.0
-rich>=10.3.0
-PyYAML>=5.4.1
-numpy>=1.18.1
-pandas>=1.3.0
-h5py>=3.1.0
-pymzml>=2.5.0
-pyteomics>=4.3.3
-lxml>=4.5.2
-tables>=3.6.1
-spectrum-fundamentals>=0.3.0
+alphatims==1.0.8 ; python_version >= "3.8" and python_full_version < "3.11.0"
+click==8.1.7 ; python_version >= "3.8" and python_full_version < "3.11.0"
+colorama==0.4.6 ; python_version >= "3.8" 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"
+h5py==3.11.0 ; python_version >= "3.8" and python_full_version < "3.11.0"
+importlib-metadata==7.1.0 ; python_version >= "3.8" and python_version < "3.9"
+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"
+llvmlite==0.41.1 ; python_version >= "3.8" and python_full_version < "3.11.0"
+lxml==4.9.4 ; python_full_version >= "3.8.0" 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"
+numba==0.58.1 ; python_version >= "3.8" 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"
+psutil==5.9.8 ; 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"
+pymzml==2.5.9 ; 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"
+pyteomics==4.7.2 ; python_full_version >= "3.8.0" 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"
+pyzstd==0.15.10 ; python_version >= "3.8" and python_full_version < "3.11.0"
+regex==2024.4.16 ; 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"
+sortedcontainers==2.4.0 ; python_full_version >= "3.8.0" and python_full_version < "3.11.0"
+spectrum-fundamentals==0.5.2 ; python_full_version >= "3.8.0" 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_version >= "3.8" 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_io/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Mario Picciani"
 __email__ = "[email protected]"
-__version__ = "0.4.2"
+__version__ = "0.4.3"
 
 import logging
 import logging.handlers

spectrum_io/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.4.2", message=click.style("spectrum_io Version: 0.4.2"))
+@click.version_option(version="0.4.3", message=click.style("spectrum_io Version: 0.4.3"))
 def main() -> None:
     """spectrum_io."""
 

spectrum_io/d/bruker.py

@@ -114,6 +114,9 @@ def read_timstof(hdf_file: Path, scan_to_precursor_map: pd.DataFrame) -> pd.Data
     )
     df.columns = ["FRAME", "SCAN", "PRECURSOR", "RETENTION_TIME", "INV_ION_MOBILITY", "MZ", "INTENSITIES"]
 
+    # converting RETENTION TIME from seconds to minutes
+    df["RETENTION_TIME"] = df["RETENTION_TIME"].div(60)
+
     # aggregation
     df_combined_grouped = (
         df.merge(

spectrum_io/search_result/__init__.py

@@ -4,3 +4,4 @@
 from .maxquant import MaxQuant
 from .msfragger import MSFragger
 from .sage import Sage
+from .xisearch import Xisearch

spectrum_io/search_result/sage.py

@@ -21,13 +21,13 @@ def read_result(self, tmt_labeled: str = "") -> pd.DataFrame:
         :param tmt_labeled: tmt label as str
         :return: pd.DataFrame with the formatted data
         """
-        logger.info("Reading msms.tsv file")
+        logger.info(f"Reading {self.path}")
         df = pd.read_csv(
             self.path,
-            usecols=["filename", "scannr", "peptide", "charge", "hyperscore", "calcmass", "proteins"],
+            usecols=["filename", "scannr", "peptide", "charge", "hyperscore", "calcmass", "label", "proteins"],
             sep="\t",
         )
-        logger.info("Finished reading msms.tsv file")
+        logger.info(f"Finished reading {self.path}")
 
         # Standardize column names
         df.columns = df.columns.str.upper()
@@ -51,6 +51,9 @@ def update_columns_for_prosit(df: pd.DataFrame, tmt_labeled: str) -> pd.DataFram
                 "SCANNR": "SCAN_NUMBER",
                 "PEPTIDE": "MODIFIED_SEQUENCE",
                 "CHARGE": "PRECURSOR_CHARGE",
+                "CALCMASS": "MASS",
+                "HYPERSCORE": "SCORE",
+                "LABEL": "REVERSE",
             }
         )
 
@@ -59,18 +62,12 @@ def update_columns_for_prosit(df: pd.DataFrame, tmt_labeled: str) -> pd.DataFram
         # extracting only the scan number
         df["SCAN_NUMBER"] = [int(x.rsplit("=", 1)[-1]) for x in df["SCAN_NUMBER"]]
         # creating a column of decoys and targets
-        df["REVERSE"] = df["PROTEINS"].str.startswith("rev_")
+        df["REVERSE"] = df["REVERSE"] < 0
         # removing modification to create the unmodified sequences
-        df["SEQUENCE"] = df["MODIFIED_SEQUENCE"].str.replace(r"\[.*?\]", "", regex=True)
+        df["SEQUENCE"] = df["MODIFIED_SEQUENCE"].str.replace(r"\-|\[.*?\]", "", regex=True)
         # length of the peptide
         df["PEPTIDE_LENGTH"] = df["SEQUENCE"].str.len()
-        # mass of the peptide
-        df["MASS"] = df["CALCMASS"]
-        # score of the peptide
-        df["SCORE"] = df["HYPERSCORE"]
-        # converting proforma to unimode
-        print(df)
+        # converting sage to unimod
         df["MODIFIED_SEQUENCE"] = sage_to_internal(df["MODIFIED_SEQUENCE"])
 
-        print(df.columns)
         return df

spectrum_io/search_result/search_results.py

@@ -52,7 +52,11 @@ def __init__(self, path: Union[str, Path]):
 
     @abstractmethod
     def read_result(self, tmt_labeled: str):
-        """Read result."""
+        """Read result.
+
+        :param tmt_labeled: tmt label as str
+
+        """
         raise NotImplementedError
 
     def generate_internal(self, tmt_labeled: str, out_path: Optional[Union[str, Path]] = None) -> pd.DataFrame: