Keep introns

lib/biocode/gff.py

@@ -344,6 +344,12 @@ def get_gff3_features(gff3_file, assemblies=None):
             parent_feat.add_exon(exon)
             features[feat_id] = exon
 
+        elif cols[2] == 'intron':
+            intron = biocode.things.Intron(id=feat_id, parent=parent_feat)
+            intron.locate_on(target=current_assembly, fmin=rfmin, fmin_partial=fmin_partial, fmax=rfmax, fmax_partial=fmax_partial, strand=rstrand)
+            parent_feat.add_intron(intron)
+            features[feat_id] = intron
+
         elif cols[2] == 'CDS':
             if phase == '.':
                 phase = 0
@@ -729,6 +735,23 @@ def print_biogene( gene=None, fh=None, source=None, on=None ):
             columns[8] = build_column_9( id=exon.id, parent=RNA.id, other=exon_annot_atts )
             fh.write( "\t".join(columns) + "\n" )
 
+        ## handle introns for this RNA
+        for intron in sorted(RNA.introns( on )):
+            intron_loc = intron.location_on( on )
+
+            if intron_loc is None:
+                raise Exception("ERROR: Expected intron {0} to be located on {1} but it wasn't".format(intron.id, on.id))
+
+            intron_partiality_string = _partiality_string(intron_loc)
+            intron_annot_atts = dict()
+            if intron_partiality_string is not None:
+                intron_annot_atts['Partial'] = intron_partiality_string
+
+            columns[2] = 'intron'
+            columns[3:5] = [str(intron_loc.fmin + 1), str(intron_loc.fmax)]
+            columns[8] = build_column_9( id=intron.id, parent=RNA.id, other=intron_annot_atts )
+            fh.write( "\t".join(columns) + "\n" )
+
         # are there polypeptides?
         for polypeptide in sorted(RNA.polypeptides()):
             if len(polypeptide.locations) == 0:

lib/biocode/things.py

@@ -1,6 +1,7 @@
 
 import itertools
 import sys
+import re
 import uuid
 
 #from biocode import utils, gff, tbl
@@ -842,9 +843,10 @@ class Intron( LocatableThing ):
     removed from within the transcript by splicing together the sequences (exons) on either
     side of it."
     '''
-    def __init__( self, id=None, locations=None, length=None ):
+    def __init__( self, id=None, locations=None, parent=None, length=None ):
         super().__init__(locations)
         self.id = id
+        self.parent = parent
         self.length = length
 
 
@@ -1029,6 +1031,7 @@ def __init__( self, id=None, locations=None, parent=None, locus_tag=None, childr
 
         ## initialize any types needed
         self.children = _initialize_type_list(self.children, 'exon')
+        self.children = _initialize_type_list(self.children, 'intron')
         self.children = _initialize_type_list(self.children, 'CDS')
         self.children = _initialize_type_list(self.children, 'polypeptide')
         self.children = _initialize_type_list(self.children, 'UTR')
@@ -1044,6 +1047,10 @@ def add_exon(self, exon):
         exon.parent = self
         self.children['exon'].append(exon)
 
+    def add_intron(self, intron):
+        intron.parent = self
+        self.children['intron'].append(intron)
+
     def add_five_prime_UTR(self, utr):
         utr.parent = self
         self.children['UTR'].append(utr)
@@ -1207,32 +1214,36 @@ def has_introns( self ):
             return False
 
     def introns(self, on=None):
-        '''
-        Dynamically generates Intron objects in order for the current RNA.  The coordinates of the
-        generated introns depend on the object passed via the 'on' argument
-        '''
-        if on is None:
-            raise Exception("ERROR: the introns() method requires a passed molecule using the 'on' argument")
-
-        mol_on = on
-
-        intron_objs = list()
-        last_exon = None
-        last_exon_loc = None
-
-        for exon in sorted(self.exons()):
-            exon_loc = exon.location_on( mol_on )
-
-            if last_exon is not None:
-                intron_id = uuid.uuid4()
-                intron = Intron( id=intron_id )
-                intron.locate_on( target=mol_on, fmin=last_exon_loc.fmax, fmax=exon_loc.fmin, strand=exon_loc.strand )
-                intron_objs.append( intron )
-
-            last_exon = exon
-            last_exon_loc = exon_loc
-
-        return intron_objs
+
+            '''
+            Dynamically generates Intron objects in order for the current RNA.  The coordinates of the
+            generated introns depend on the object passed via the 'on' argument
+            '''
+            if on is None:
+                raise Exception("ERROR: the introns() method requires a passed molecule using the 'on' argument")
+
+            mol_on = on
+
+            intron_objs = list()
+            last_exon = None
+            last_exon_loc = None
+
+            intron_count = 0
+            for exon in sorted(self.exons()):
+                exon_loc = exon.location_on( mol_on )
+
+                if last_exon is not None:
+                    intron_count = intron_count + 1
+                    intron_count_id = str(intron_count)
+                    intron_id = str(re.sub('exon[0-9]', 'intron' + intron_count_id, exon.id)) ## ## This is generating random id, need format such as "g1.t1.intron1"
+                    intron = Intron( id=intron_id )
+                    intron.locate_on( target=mol_on, fmin=last_exon_loc.fmax, fmax=exon_loc.fmin, strand=exon_loc.strand )
+                    intron_objs.append( intron )
+
+                last_exon = exon
+                last_exon_loc = exon_loc
+
+            return intron_objs
 
     def polypeptides(self):
         return self.children['polypeptide']