Merge pull request #143 from wilhelm-lab/fix/filter_search_result_col…

…umns

Fix/filter search result columns

.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: 0.6.0
+version: 0.6.1
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.6.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.6.0 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.6.1 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.6.1 # <<COOKIETEMPLE_FORCE_BUMP>>
 exclude-labels:
     - "skip-changelog"
 

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.0
+current_version = 0.6.1
 
 [bumpversion_files_whitelisted]
 init_file = spectrum_io/__init__.py

docs/conf.py

@@ -52,9 +52,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.6.0"
+version = "0.6.1"
 # The full version, including alpha/beta/rc tags.
-release = "0.6.0"
+release = "0.6.1"
 
 # 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_io"
-version = "0.6.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.6.1"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "IO related functionalities for oktoberfest."
 authors = ["Wilhelmlab at Technical University of Munich"]
 license = "MIT"

spectrum_io/__init__.py

@@ -5,7 +5,7 @@
 __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__ = "0.6.0"
+__version__ = "0.6.1"
 
 import logging
 import logging.handlers

spectrum_io/__main__.py

@@ -5,7 +5,7 @@
 
 
 @click.command()
-@click.version_option(version="0.6.0", message=click.style("spectrum_io Version: 0.6.0"))
+@click.version_option(version="0.6.1", message=click.style("spectrum_io Version: 0.6.1"))
 def main() -> None:
     """spectrum_io."""
 

spectrum_io/search_result/maxquant.py

@@ -71,7 +71,21 @@ def read_result(
             parsed_mods["^_"] = f"_{unimod_tag}-"
 
         logger.info("Reading msms.txt file")
-        self.results = pd.read_csv(self.path / "msms.txt", sep="\t")
+        self.results = pd.read_csv(
+            self.path / "msms.txt",
+            usecols=[
+                "Raw file",
+                "Scan number",
+                "Modified sequence",
+                "Charge",
+                "Scan event number",
+                "Mass",  # = Calculated Precursor mass; TODO get column with experimental Precursor mass instead
+                "Score",
+                "Reverse",
+                "Proteins",
+            ],
+            sep="\t",
+        )
 
         logger.info("Finished reading msms.txt file")
 

spectrum_io/search_result/search_results.py

@@ -11,6 +11,20 @@
 logger = logging.getLogger(__name__)
 
 
+COLUMNS = [
+    "RAW_FILE",
+    "SCAN_NUMBER",
+    "MODIFIED_SEQUENCE",
+    "PRECURSOR_CHARGE",
+    "MASS",
+    "SCORE",
+    "REVERSE",
+    "SEQUENCE",
+    "PEPTIDE_LENGTH",
+    "PROTEINS",
+]
+
+
 def filter_valid_prosit_sequences(df: pd.DataFrame) -> pd.DataFrame:
     """
     Filter valid Prosit sequences.
@@ -24,7 +38,6 @@ def filter_valid_prosit_sequences(df: pd.DataFrame) -> pd.DataFrame:
     # remove unsupported mods to exclude
     supported_pattern = re.compile(r"^(?:\[UNIMOD:\d+\]\-)?(?:[ACDEFGHIKLMNPQRSTVWY]+(?:\[UNIMOD:\d+\])?)*$")
     df = df[df["MODIFIED_SEQUENCE"].str.match(supported_pattern)]
-
     # remove precursor charges greater than 6
     df = df[df["PRECURSOR_CHARGE"] <= 6]
     logger.info(f"#sequences after filtering for valid prosit sequences: {len(df.index)}")
@@ -122,8 +135,8 @@ def generate_internal(
         """
         if out_path is None:
             # convert and return
-            return self.read_result(tmt_label, custom_mods=custom_mods)
-
+            filtered_df = self.read_result(tmt_label, custom_mods=custom_mods)
+            return filtered_df[COLUMNS]
         if isinstance(out_path, str):
             out_path = Path(out_path)
 
@@ -134,7 +147,7 @@ def generate_internal(
             return csv.read_file(out_path)
 
         # convert, save and return
-        df = self.read_result(tmt_label, custom_mods=custom_mods)
+        df = self.read_result(tmt_label, custom_mods=custom_mods)[COLUMNS]
         csv.write_file(df, out_path)
         return df