Merge pull request #216 from MannLabs/adapt_to_new_alphabase

Adapt to new alphabase

Author: mschwoer

peptdeep/psm_frag_reader/maxquant_frag_reader.py

@@ -77,8 +77,7 @@ def __init__(
     def fragment_intensity_df(self):
         return self._fragment_intensity_df
 
-    def _load_file(self, filename):
-        df = MaxQuantReader._load_file(self, filename)
+    def _pre_process(self, df):
         df = filter_phos(df, self._phos_prob)
         df = df[
             (df.Score >= self._score_thres) | ((df.Score >= 60) & (df.PhosProbs != ""))

peptdeep/psm_frag_reader/psmlabel_reader.py

@@ -29,11 +29,22 @@ def __init__(
         PSMReader_w_FragBase.__init__(
             self, frag_types=frag_types, max_frag_charge=max_frag_charge, **kwargs
         )
-        pFindReader.__init__(self)
+        pFindReader.__init__(
+            self,
+            column_mapping={
+                "sequence": "peptide",
+                "charge": "charge",
+                "rt": "RT",
+                "raw_name": "raw_name",
+                "query_id": "spec",
+                "scan_num": "scan_num",
+            },
+        )
 
-        psmlabel_columns = "b,b-NH3,b-H20,b-ModLoss,y,y-HN3,y-H20,y-ModLoss".split(",")
         self.psmlabel_frag_columns = []
         self.frag_df_columns = {}
+
+        psmlabel_columns = "b,b-NH3,b-H20,b-ModLoss,y,y-HN3,y-H20,y-ModLoss".split(",")
         for _type in psmlabel_columns:
             frag_idxes = [
                 i
@@ -44,18 +55,11 @@ def __init__(
                 self.psmlabel_frag_columns.append(_type)
                 self.frag_df_columns[_type] = np.array(frag_idxes, dtype=int)
 
-    def _init_column_mapping(self):
-        self.column_mapping = {
-            "sequence": "peptide",
-            "charge": "charge",
-            "rt": "RT",
-            "raw_name": "raw_name",
-            "query_id": "spec",
-            "scan_num": "scan_num",
-        }
-
     def _load_file(self, filename):
-        psmlabel_df = pd.read_csv(filename, sep="\t")
+        df = pd.read_csv(filename, sep="\t")
+        return df
+
+    def _pre_process(self, psmlabel_df: pd.DataFrame):
         psmlabel_df.fillna("", inplace=True)
 
         if psmlabel_df["spec"].values[0].count(".") >= 4:  # pfind
@@ -79,16 +83,16 @@ def _load_modifications(self, psmlabel_df: pd.DataFrame):
             *psmlabel_df["modinfo"].apply(get_pFind_mods)
         )
 
-    def _translate_decoy(self, df):
+    def _translate_decoy(self):
         pass
 
-    def _translate_score(self, df):
+    def _translate_score(self):
         pass
 
     def _translate_modifications(self):
         self._psm_df["mods"] = self._psm_df["mods"].apply(translate_pFind_mod)
 
-    def _post_process(self, psmlabel_df: pd.DataFrame):
+    def _post_process(self, psmlabel_df):
         psmlabel_df["nAA"] = psmlabel_df.peptide.str.len()
         self._psm_df["nAA"] = psmlabel_df.nAA
         psmlabel_df = psmlabel_df[~self._psm_df["mods"].isna()].reset_index(drop=True)

requirements/requirements.txt

@@ -16,5 +16,5 @@ lxml
 pyteomics
 
 streamlit>=1.23.0
-alphabase>=1.1.0
+alphabase>=1.5.0
 alpharaw>=0.2.0

requirements/requirements_loose.txt

@@ -16,5 +16,5 @@ lxml
 pyteomics
 
 streamlit>=1.23.0
-alphabase>=1.1.0
+alphabase>=1.5.0
 alpharaw>=0.2.0