analysis updated to handle dot values in for phase in CDS feature

reneshbedre · Dec 22, 2020 · 8591554 · 8591554
1 parent e32f47a
commit 8591554
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/bioinfokit/__init__.py b/bioinfokit/__init__.py
@@ -1,5 +1,5 @@
 name = "bioinfokit"
-__version__ = "1.0.4"
+__version__ = "1.0.5"
 __author__ = "Renesh Bedre"
 
 
diff --git a/bioinfokit/analys.py b/bioinfokit/analys.py
@@ -1471,8 +1471,14 @@ def gff_to_gtf(file='gff_file', trn_feature_name=None, parent_attr='Parent'):
                     cds_ct += 1
                     cds_dict_st[transcript_id_cds].append(line[3])
                     cds_dict_end[transcript_id_cds].append(line[4])
-                    cds_dict_st_phase[(transcript_id_cds, line[3])] = line[7]
-                    cds_dict_end_phase[(transcript_id_cds, line[4])] = line[7]
+                    # if CDS phase contains dot values
+                    if line[7] == '.':
+                        print('Warning: No valid phase values for CDS feature. making phase value to zero')
+                        cds_dict_st_phase[(transcript_id_cds, line[3])] = 0
+                        cds_dict_end_phase[(transcript_id_cds, line[4])] = 0
+                    else:
+                        cds_dict_st_phase[(transcript_id_cds, line[3])] = line[7]
+                        cds_dict_end_phase[(transcript_id_cds, line[4])] = line[7]
 
         read_gff_file_cds.close()