updated rest of files to pyfaidx. fixed int overflow error

TranscriptClean.py

@@ -332,14 +332,14 @@ def transcript_init(transcript_line, genome, sjAnnot):
     if logInfo.Mapping != "primary":
         return None, logInfo
 
-    try:
-        transcript = Transcript(sam_fields, genome, sjAnnot)
+    # try:
+    transcript = Transcript(sam_fields, genome, sjAnnot)
 
-    except Exception as e:
-        warnings.warn("Problem parsing transcript with ID '" +
-                      logInfo.TranscriptID + "'")
-        print(e)
-        return None, logInfo
+    # except Exception as e:
+    #     warnings.warn("Problem parsing transcript with ID '" +
+    #                   logInfo.TranscriptID + "'")
+    #     print(e)
+    #     return None, logInfo
 
     return transcript, logInfo
 
@@ -1365,7 +1365,9 @@ def combinedJunctionDist(dist_0, dist_1):
     """
     # If dist_0 and dist_1 have different signs, the combined distance is
     # the sum of their absolute values
-    if dist_0*dist_1 <= 0:
+    # https://stackoverflow.com/questions/66882/simplest-way-to-check-if-two-integers-have-same-sign
+    if ((dist_0<0)!=(dist_1<0)):
+    # if dist_0*dist_1 <= 0:
         combined_dist = abs(dist_0) + abs(dist_1)
     else:
         combined_dist = abs(abs(dist_0) - abs(dist_1))

intronBound.py

@@ -19,7 +19,7 @@ def __init__(self, transcriptID, jnNumber, ibNumber, chrom, pos, strand):
         self.strand = strand
 
     def getBED(self):
-        """ Format the intron boundary with 0-based start and end. 
+        """ Format the intron boundary with 0-based start and end.
          If mode == "start", we return a bed for the start position."""
 
         bedstr = "\t".join([self.chrom, str(self.pos - 1), str(self.pos),
@@ -31,9 +31,15 @@ def getSpliceMotif(self, genome):
             intron (first two if bound == 0 and last two if bound == 1) """
 
         if self.bound == 0:
-            motif = genome.sequence(
-                {'chr': self.chrom, 'start': self.pos, 'stop': self.pos + 1}, one_based=True)
+            # motif = genome.sequence(
+            #     {'chr': self.chrom, 'start': self.pos, 'stop': self.pos + 1}, one_based=True)
+            motif = genome.get_seq(self.chrom,
+                                   self.pos,
+                                   self.pos+1).seq
         else:
-            motif = genome.sequence(
-                {'chr': self.chrom, 'start': self.pos - 1, 'stop': self.pos}, one_based=True)
+            # motif = genome.sequence(
+            #     {'chr': self.chrom, 'start': self.pos - 1, 'stop': self.pos}, one_based=True)
+            motif = genome.get_seq(self.chrom,
+                                   self.pos-1,
+                                   self.pos).seq
         return motif

testing_suite/test_all_jns_annotated.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2
@@ -11,7 +11,7 @@ class TestAllSJsAnnot(object):
     def test_no_jns(self):
         """ Return transcript.allJnsAnnotated = True for a transcript without
             junctions"""
-        
+
         sam = "input_files/sams/perfectReferenceMatch_noIntrons.sam"
         genome = Fasta("input_files/hg38_chr1.fa")
 
@@ -56,7 +56,7 @@ def test_two_annotated_SJs_without_ref(self):
         assert transcript.isCanonical == True
 
     def test_noncanonical(self):
-        """ Transcript should be noncanonical and un-annotated prior to 
+        """ Transcript should be noncanonical and un-annotated prior to
             correction, but be canonical and annotated afterwards """
 
         sam = "input_files/sams/deletion_insertion_mismatch_nc.sam"
@@ -70,15 +70,14 @@ def test_noncanonical(self):
 
         with open(sam, 'r') as f:
             sam_line = f.readline().strip()
-            transcript, logInfo = TC.transcript_init(sam_line, refs.genome, 
+            transcript, logInfo = TC.transcript_init(sam_line, refs.genome,
                                                      refs.sjAnnot)
 
         assert transcript.allJnsAnnotated == False
         assert transcript.isCanonical == False
 
         # Now correct the junction and retest
-        upd_transcript, TE = TC.cleanNoncanonical(transcript, refs, 5, logInfo)        
+        upd_transcript, TE = TC.cleanNoncanonical(transcript, refs, 5, logInfo)
 
         assert upd_transcript.allJnsAnnotated == True
         assert upd_transcript.isCanonical == True
-

testing_suite/test_attempt_jn_correction.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_canonOnly_mode.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 import os
 import subprocess

testing_suite/test_combined_jn_dist.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import TranscriptClean as TC

testing_suite/test_compare_seq_cigar_lengths.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_compute_MD_NM.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_compute_jI_jM.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_correct_deletions.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_correct_insertions.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_correct_mismatches.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_example_transcripts.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 import os
 import subprocess

testing_suite/test_example_varDM_monoexon.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 import os
 import subprocess

testing_suite/test_fetch_donor_or_acceptor.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import spliceJunction as sj

testing_suite/test_find_closest_annotated_SJ.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import spliceJunction as sj

testing_suite/test_find_closest_annotated_bound.py

@@ -6,7 +6,7 @@
 import intronBound as ib
 import spliceJunction as sj
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 
 
 @pytest.mark.unit

testing_suite/test_find_ncsj.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_fix_one_side_of_junction.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2

testing_suite/test_full_dryrun.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 import os
 import subprocess

testing_suite/test_high_level_ncsj_correction.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import os
 import sys
 sys.path.append("..")

testing_suite/test_init_transcript_object.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import TranscriptClean as TC

testing_suite/test_print_fasta_seq.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as ts

testing_suite/test_rmTmp_option.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 import os
 import subprocess

testing_suite/test_update_post_ncsj_correction.py

@@ -1,5 +1,5 @@
 import pytest
-from pyfasta import Fasta
+from pyfaidx import Fasta
 import sys
 sys.path.append("..")
 import transcript as t2