Update cas12.py (#5)

- Update cas12.py (a5a7472cbc5fea41f3f151cb51ef3137c6c66ea7)


Co-authored-by: Qingyang Liu <LfOreVEr@users.noreply.huggingface.co>

cas12.py

@@ -87,20 +87,23 @@ def fetch_ensembl_sequence(transcript_id):
         print(f"Error fetching sequence data from Ensembl: {response.text}")
         return None
 
-def find_crispr_targets(sequence, chr, start, strand, transcript_id, exon_id, pam="TTTN", target_length=34):
+def find_crispr_targets(sequence, chr, start, end, strand, transcript_id, exon_id, pam="TTTN", target_length=34):
     targets = []
     len_sequence = len(sequence)
     complement = {'A': 'T', 'T': 'A', 'C': 'G', 'G': 'C'}
     dnatorna = {'A': 'A', 'T': 'U', 'C': 'C', 'G': 'G'}
 
-    if strand == -1:
-        sequence = ''.join([complement[base] for base in sequence])
-
     for i in range(len_sequence - target_length + 1):
         target_seq = sequence[i:i + target_length]
         if target_seq[4:7] == 'TTT':
-            tar_start = start + i
-            tar_end = start + i + target_length
+            if strand == -1:
+                tar_start = end - i - target_length + 1
+                tar_end = end -i
+                #seq_in_ref = ''.join([complement[base] for base in target_seq])[::-1]
+            else:
+                tar_start = start + i
+                tar_end = start + i + target_length - 1
+                #seq_in_ref = target_seq
             gRNA = ''.join([dnatorna[base] for base in target_seq[8:28]])
             targets.append([target_seq, gRNA, chr, str(tar_start), str(tar_end), str(strand), transcript_id, exon_id])
     return targets
@@ -142,9 +145,10 @@ def process_gene(gene_symbol, model_path):
                 gene_sequence = fetch_ensembl_sequence(exon_id)
                 if gene_sequence:
                     start = Exons[j]['start']
+                    end = Exons[j]['end']
                     strand = Exons[j]['strand']
                     chr = Exons[j]['seq_region_name']
-                    targets = find_crispr_targets(gene_sequence, chr, start, strand, transcript_id, exon_id)
+                    targets = find_crispr_targets(gene_sequence, chr, start, end, strand, transcript_id, exon_id)
                     if targets:
                         formatted_data = format_prediction_output(targets, model_path)
                         results.append(formatted_data)