fix bug with reverse strand if pyrodigal overlap called

gbouras13 · Jan 30, 2024 · aead582 · aead582
1 parent 608d635
commit aead582
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 2 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dnaapler"
-version = "0.5.2" # change VERSION too
+version = "0.6.0" # change VERSION too
 description = "Reorients assembled microbial sequences"
 authors = ["George Bouras <[email protected]>"]
 license = "MIT"

diff --git a/src/dnaapler/utils/processing.py b/src/dnaapler/utils/processing.py
@@ -224,9 +224,17 @@ def reorient_sequence(
             # Find the gene with the max overlap
             closest_gene_index = max(overlap_dict, key=lambda key: overlap_dict[key])
 
-            start = genes[closest_gene_index].begin
+            # get strand
             strand = genes[closest_gene_index].strand
 
+            # susie error 30-01-24 - misorienting on the negative strand
+            # 'begin' just gives the lowest value, not the start, so was putting the terL at the end i.e. reorienting from the end of terL
+            # therefore need to take end
+            if strand == 1:
+                start = genes[closest_gene_index].begin
+            elif strand == -1:
+                start = genes[closest_gene_index].end
+
             if strand == 1:
                 strand_eng = "forward"
             else: