Remove longest_perfect_match_length from dataframe

crisprbact/off_target.py

@@ -47,8 +47,7 @@ def get_off_target_pos(guide, records, seed_size):
                     "pampos",
                     "strand",
                     "recid",
-                    "max_matching_len",
-                    "max_matching_seq",
+                    "longest_perfect_match",
                     "pam_seq",
                 ],
                 zip(*offs),
@@ -81,12 +80,12 @@ def gen_extract_off_target_strand_plus(
         sub_sequence_to_match = sequence_string[start_pos_seq:end_pos_seq][::-1]
         matching_chars = list(common_start(sub_sequence_to_match, guide_subseq))
         matching_substr = "".join(matching_chars)
+        longest_perfect_match = matching_substr[::-1] + match.group(0)[:-3]
         yield match.span() + (
             match.end(),
             "+",
             seqid,
-            seed_size + len(matching_chars),
-            matching_substr[::-1] + match.group(0)[:-3],
+            longest_perfect_match,
             match.group(0)[-3:],
         )
 
@@ -114,12 +113,13 @@ def gen_extract_off_target_strand_minus(
         guide_subseq = rev_comp(guide[: 20 - seed_size])
         matching_chars = list(common_start(sub_sequence_to_match, guide_subseq))
         matching_substr = "".join(matching_chars)
+        longest_perfect_match = match.group(0)[3:] + matching_substr
+
         yield match.span() + (
             match.start(),
             "-",
             seqid,
-            seed_size + len(matching_chars),
-            match.group(0)[3:] + matching_substr,
+            longest_perfect_match,
             match.group(0)[:3],
         )