adding func to provide xifdr input

wilhelm-lab · Oct 17, 2024 · bc10316 · bc10316
1 parent 97c00f0
commit bc10316
Show file tree

Hide file tree

Showing 3 changed files with 176 additions and 139 deletions.
diff --git a/oktoberfest/data/spectra.py b/oktoberfest/data/spectra.py
@@ -229,20 +229,9 @@ def add_intensities(self, intensities: np.ndarray, annotation: np.ndarray, fragm
         """
         intensities[intensities == 0] = c.EPSILON
         intensities[intensities == -1] = 0.0
-
-        annotation_cleaned = np.array([s.decode('utf-8') if isinstance(s, bytes) else str(s) for s in annotation[0]])
-        annotation_cleaned = np.where(annotation_cleaned == 'None', 'no_fragment', annotation_cleaned)
-        annotation_cleaned = np.where(annotation_cleaned == None, 'no_fragment', annotation_cleaned) 
-
-
+
         annotation_to_index = {annot: index for index, annot in enumerate(self.var_names)}
-        print(annotation_to_index)
-        print("Original Annotation:", annotation[0])
-        print("Cleaned Annotation:", annotation_cleaned)
-
-        col_index = np.vectorize(annotation_to_index.get)(annotation_cleaned.astype(str))
-
-
+        col_index = np.vectorize(annotation_to_index.get)(annotation[0].astype(str))
         sparse_intensity_matrix = dok_matrix(self.shape)
         sparse_intensity_matrix[:, col_index] = intensities
 

diff --git a/oktoberfest/predict/predictor.py b/oktoberfest/predict/predictor.py
@@ -151,7 +151,6 @@ def predict_intensities(self, data: Spectra, xl: bool = False, chunk_idx: Option
         if chunk_idx is None:
             if xl:
                 intensities_a, intensities_b  = self.predict_at_once(data=data, xl=xl, **kwargs)
-                #print(intensities_a["annotation"][0])
                 data.add_intensities_without_mapping(intensities_a["intensities"], fragment_type=FragmentType.PRED_A)
                 data.add_intensities_without_mapping(intensities_b["intensities"], fragment_type=FragmentType.PRED_B)   
             else:
@@ -388,7 +387,7 @@ def ce_calibration(self, library: Spectra, ce_range: tuple[int, int], group_by_c
             chunk_idx = list(group_iterator(df=alignment_library.obs, group_by_column="PEPTIDE_LENGTH"))
         else:
             chunk_idx = None
-        print("XL!!!!!!!!!!!!!!!!!!!!")
+
         self.predict_intensities(data=alignment_library, chunk_idx=chunk_idx, keep_dataset=False, xl=xl, **kwargs)
         _alignment(alignment_library, xl=xl)
         return alignment_library