prepare for CCS prediction

compomics · Nov 9, 2023 · daa1e46 · daa1e46
1 parent df28ea6
commit daa1e46
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 3 deletions.
diff --git a/deeplc/deeplc.py b/deeplc/deeplc.py
@@ -193,6 +193,7 @@ class DeepLC:
 
     library = {}
 
+    # TODO have a CCS flag here
     def __init__(
         self,
         main_path=os.path.dirname(os.path.realpath(__file__)),
@@ -314,13 +315,14 @@ def do_f_extraction(self, seqs, mods, identifiers, charges=[]):
             feature matrix
         """
         list_of_psms = []
+        # TODO include charge here
         if len(charges) > 0:
             for seq,mod,ident in zip(seqs,mods,identifiers):
                 list_of_psms.append(PSM(peptide=peprec_to_proforma(seq,mod),spectrum_id=ident))
         else:
             for seq,mod,ident,z in zip(seqs,mods,identifiers,charges):
                 list_of_psms.append(PSM(peptide=peprec_to_proforma(seq,mod),spectrum_id=ident))
-
+        # TODO include charge here
         psm_list = PSMList(psm_list=list_of_psms)
 
         return self.f_extractor.full_feat_extract(psm_list)
@@ -352,6 +354,7 @@ def do_f_extraction_pd(self,
         else:
             for seq,mod,ident,z in zip(df_instances["seq"],df_instances["modifications"],df_instances.index,charges=df_instances["charges"]):
                 list_of_psms.append(PSM(peptide=peprec_to_proforma(seq,mod),spectrum_id=ident))
+        # TODO include charge here
         psm_list = PSMList(psm_list=list_of_psms)
 
         return self.f_extractor.full_feat_extract(psm_list)
@@ -627,12 +630,14 @@ def make_preds(self,
         """
         if type(seq_df) == pd.core.frame.DataFrame:
             list_of_psms = []
+            # TODO include charge here
             for seq,mod,ident in zip(seq_df["seq"],seq_df["modifications"],seq_df.index):
                 list_of_psms.append(PSM(peptidoform=peprec_to_proforma(seq,mod),spectrum_id=ident))
             psm_list = PSMList(psm_list=list_of_psms)
 
         if len(infile) > 0:
             psm_list = read_file(infile)
+            # TODO is charge included here?
             if "msms" in infile and ".txt" in infile:
                 mapper = pd.read_csv(os.path.join(os.path.dirname(os.path.realpath(__file__)), "unimod/map_mq_file.csv"),index_col=0)["value"].to_dict()
                 psm_list.rename_modifications(mapper)
@@ -703,6 +708,7 @@ def calibrate_preds_func_pygam(self,
         # TODO make sure either psm_list or seq_df is supplied
         if type(seq_df) == pd.core.frame.DataFrame:
             list_of_psms = []
+            # TODO include charge here
             for seq,mod,ident,tr in zip(seq_df["seq"],seq_df["modifications"],seq_df.index,seq_df["tr"]):
                 list_of_psms.append(PSM(peptidoform=peprec_to_proforma(seq,mod),spectrum_id=ident,retention_time=tr))
             psm_list = PSMList(psm_list=list_of_psms)
@@ -780,6 +786,7 @@ def calibrate_preds_func(self,
         """
         if type(seq_df) == pd.core.frame.DataFrame:
             list_of_psms = []
+            # TODO include charge here
             for seq,mod,tr,ident in zip(seq_df["seq"],seq_df["modifications"],seq_df["tr"],seq_df.index):
                 list_of_psms.append(PSM(peptidoform=peprec_to_proforma(seq,mod),spectrum_id=ident,retention_time=tr))
             psm_list = PSMList(psm_list=list_of_psms)
@@ -926,16 +933,19 @@ def calibrate_preds(self,
         """
         if type(seq_df) == pd.core.frame.DataFrame:
             list_of_psms = []
+            # TODO include charge here
             for seq,mod,ident,tr in zip(seq_df["seq"],seq_df["modifications"],seq_df.index,seq_df["tr"]):
                 list_of_psms.append(PSM(peptidoform=peprec_to_proforma(seq,mod),spectrum_id=ident,retention_time=tr))
             psm_list = PSMList(psm_list=list_of_psms)
         elif psm_utils_obj:
+            # TODO include charge here
             psm_list = psm_utils_obj    
 
         if isinstance(self.model, str):
             self.model = [self.model]
 
         if len(infile) > 0:
+            # TODO include charge here
             psm_list = read_file(infile)
             if "msms" in infile and ".txt" in infile:
                 mapper = pd.read_csv(os.path.join(os.path.dirname(os.path.realpath(__file__)), "unimod/map_mq_file.csv"),index_col=0)["value"].to_dict()
@@ -995,6 +1005,7 @@ def calibrate_preds(self,
             self.model = models
 
         if isinstance(sample_for_calibration_curve, int):
+            # TODO include charge here
             psm_list = random.sample(list(psm_list), sample_for_calibration_curve)
             measured_tr = [psm.retention_time for psm in psm_list]
 

diff --git a/deeplc/feat_extractor.py b/deeplc/feat_extractor.py
@@ -417,6 +417,7 @@ def encode_atoms(self,
         object :: pd.DataFrame
             feature matrix (np.matrix) of summed composition
         """
+        # TODO param flag for CCS prediction
         def rolling_sum(a, n=2):
             ret = np.cumsum(a, axis=1, dtype=np.float32)
             ret[:, n:] = ret[:, n:] - ret[:, :-n]
@@ -429,7 +430,7 @@ def rolling_sum(a, n=2):
         ret_list["pos_matrix"] = {}
         ret_list["matrix_hc"] = {}
 
-        # Reintroduce for CCS
+        # TODO Reintroduce for CCS, check CCS flag
         #if len(charges) == 0:
         #    charges = [-1] * len(indexes)
 
@@ -541,7 +542,7 @@ def rolling_sum(a, n=2):
             matrix_all = np.sum(matrix, axis=0)
             matrix_all = np.append(matrix_all, seq_len)
 
-            # Reintroduce for CCS
+            # TODO Reintroduce for CCS, check CCS flag
             #if charge != -1:
             #    matrix_all = np.append(matrix_all,(seq.count("H"))/float(seq_len))
             #    matrix_all = np.append(matrix_all,(seq.count("F")+seq.count("W")+seq.count("Y"))/float(seq_len))
@@ -584,6 +585,7 @@ def full_feat_extract(self,
         pd.DataFrame
             feature matrix
         """
+        # TODO Reintroduce for CCS, check CCS flag
         if len(seqs) > 0:
             list_of_psms = []
             for seq,mod,id in zip(seqs,mods,identifiers):
@@ -593,6 +595,7 @@ def full_feat_extract(self,
         if self.verbose:
             t0 = time.time()
 
+        # TODO pass CCS flag
         if self.add_sum_feat:
             if self.verbose:
                 logger.debug(