Striving for clarity in overlap arithmetic

sanger-tol · Oct 18, 2024 · 6f0ce23 · 6f0ce23
1 parent 6a93692
commit 6f0ce23
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 5 deletions.
diff --git a/src/tola/assembly/build_assembly.py b/src/tola/assembly/build_assembly.py
@@ -161,6 +161,7 @@ def qc_sub_fragments(
         abut_count = 0
         overlap_count = 0
         lgth = len(sub_fragments)
+        pairs_with_gaps = []
         for i in range(0, lgth):
             frag_a = sub_fragments[i]
             for j in range(i + 1, lgth):
@@ -169,6 +170,9 @@ def qc_sub_fragments(
                     abut_count += 1
                 if frag_a.overlaps(frag_b):
                     overlap_count += 1
+                if g := frag_a.gap_between(frag_b):
+                    pairs_with_gaps.append((frag_a, frag_b))
+
 
         sub_frags_length = sum(f.length for f in sub_fragments)
 

diff --git a/src/tola/assembly/fragment.py b/src/tola/assembly/fragment.py
@@ -112,12 +112,12 @@ def overlap_length(self, othr):
         if self.name != othr.name:
             return None
 
-        ovr_end = max(self.start, othr.start)
-        ovr_start = min(self.end, othr.end)
-        if ovr_start < ovr_end:
+        ovr_start = max(self.start, othr.start)
+        ovr_end = min(self.end, othr.end)
+        if ovr_start > ovr_end:
             return None
         else:
-            return ovr_start - ovr_end + 1
+            return ovr_end - ovr_start + 1
 
     def abuts(self, othr):
         if self.name != othr.name:
@@ -130,8 +130,8 @@ def gap_between(self, othr):
         if self.name != othr.name:
             return None
 
-        gap_end = max(self.start, othr.start)
         gap_start = min(self.end, othr.end)
+        gap_end = max(self.start, othr.start)
         if gap_start < gap_end:
             return gap_end - gap_start - 1
         else: