Cleared a debug message

EI-CoreBioinformatics · Oct 15, 2018 · 24476e6 · 24476e6
1 parent ca951c2
commit 24476e6
Show file tree

Hide file tree

Showing 4 changed files with 19 additions and 11 deletions.
diff --git a/Mikado/preparation/annotation_parser.py b/Mikado/preparation/annotation_parser.py
@@ -303,7 +303,9 @@ def load_from_gff(shelf_name,
     to_ignore = set()
 
     for row in gff_handle:
-        if row.is_transcript is True or row.feature == "match":
+        if row.feature == "protein":
+            continue
+        elif row.is_transcript is True or row.feature == "match":
             if label != '':
                 row.id = "{0}_{1}".format(label, row.id)
                 row.source = label
@@ -364,12 +366,14 @@ def load_from_gff(shelf_name,
                     row.transcript = ["{0}_{1}".format(label, tid) for tid in row.transcript]
 
                 parents = row.transcript[:]
+                to_delete = set()
                 for tid in parents:
+
                     if tid in found_ids:
                         __raise_redundant(tid, gff_handle.name, label)
                     elif tid in to_ignore:
                         continue
-                    if tid not in exon_lines:
+                    if tid not in exon_lines and tid in transcript2genes:
                         exon_lines[tid] = dict()
                         exon_lines[tid]["attributes"] = row.attributes.copy()
                         if label:
@@ -382,6 +386,8 @@ def load_from_gff(shelf_name,
                         exon_lines[tid]["tid"] = tid
                         exon_lines[tid]["parent"] = transcript2genes[tid]
                         exon_lines[tid]["strand_specific"] = strand_specific
+                    elif tid not in exon_lines and tid not in transcript2genes:
+                        continue
                     else:
                         if "exon_number" in row.attributes:
                             del row.attributes["exon_number"]

diff --git a/Mikado/preparation/checking.py b/Mikado/preparation/checking.py
@@ -90,9 +90,9 @@ def create_transcript(lines,
                     lines["tid"])
         # logger.exception(exc)
         transcript_object = None
-    except exceptions.InvalidTranscript:
-        logger.info("Discarded generically invalid transcript %s",
-                    lines["tid"])
+    except exceptions.InvalidTranscript as exc:
+        logger.info("Discarded generically invalid transcript %s, exception: %s",
+                    lines["tid"], exc)
         transcript_object = None
     except KeyboardInterrupt:
         raise KeyboardInterrupt

diff --git a/Mikado/tests/test_system_calls.py b/Mikado/tests/test_system_calls.py
@@ -217,15 +217,15 @@ def test_prepare_with_cds(self):
                 with self.subTest(fname=fname, strip=strip):
                     self.conf["prepare"]["files"]["gff"] = [fname]
                     args.json_conf["prepare"]["strip_cds"] = strip
-                    prepare.prepare(args, self.logger)
-                    self.assertTrue(os.path.exists(os.path.join(self.conf["prepare"]["files"]["output_dir"],
-                                                                "mikado_prepared.fasta")))
-                    fa = pyfaidx.Fasta(os.path.join(self.conf["prepare"]["files"]["output_dir"],
-                                                    "mikado_prepared.fasta"))
+                    prepare.prepare(args, logger=self.logger)
+                    fasta = os.path.join(self.conf["prepare"]["files"]["output_dir"], "mikado_prepared.fasta")
+                    self.assertTrue(os.path.exists(fasta))
                     if strip is True or (strip is False and fname == ann_gff3):
+                        self.assertGreater(os.stat(fasta).st_size, 0)
+                        fa = pyfaidx.Fasta(fasta)
                         self.assertEqual(len(fa.keys()), 2)
                     else:
-                        self.assertEqual(len(fa.keys()), 0)
+                        self.assertEqual(os.stat(fasta).st_size, 0)
                     # Now verify that no model has CDS
                     gtf = os.path.join(self.conf["prepare"]["files"]["output_dir"], "mikado_prepared.gtf")
                     models = dict()

diff --git a/Mikado/transcripts/transcriptchecker.py b/Mikado/transcripts/transcriptchecker.py
@@ -248,6 +248,8 @@ def check_strand(self):
                             canonical_counter["+"])
 
             elif canonical_counter["-"] > 0:
+                self.logger.debug("Transcript %s only has negative splice junctions, (%s), reversing.",
+                                  self.id, canonical_counter)
                 self.reverse_strand()
                 self.reversed = True