Fastq_output report inserted bases

when the `--fastq_output` parameter is provided, the inserted bases will be written to the output fastq file. Previously, a string like "DEL= INS=78(1) SUB= " would indicate a 1bp insertion at site 78. This update outputs strings like "DEL= INS=78(1+G) SUB= " with a plus character followed by the inserted bases.
pinellolab · Dec 10, 2021 · 2f84dd0 · 2f84dd0
1 parent ba742bb
commit 2f84dd0
Showing 1 changed file with 6 additions and 1 deletion.
diff --git a/CRISPResso2/CRISPRessoCORE.py b/CRISPResso2/CRISPRessoCORE.py
@@ -690,7 +690,12 @@ def process_fastq_write_out(fastq_input, fastq_output, variantCache, ref_names,
                     payload=new_variant['variant_'+best_match_name]
 
                     del_inds.append([str(x[0][0])+"("+str(x[1])+")" for x in zip(payload['deletion_coordinates'], payload['deletion_sizes'])])
-                    ins_inds.append([str(x[0][0])+"("+str(x[1])+")" for x in zip(payload['insertion_coordinates'], payload['insertion_sizes'])])
+
+                    ins_vals = []
+                    for ins_coord,ins_size in zip(payload['insertion_coordinates'],payload['insertion_sizes']):
+                        ins_start = payload['ref_positions'].index(ins_coord[0])
+                        ins_vals.append(payload['aln_seq'][ins_start:ins_start+ins_size])
+                    ins_inds.append([str(x[0][0])+"("+str(x[1])+"+"+x[2]+")" for x in zip(payload['insertion_coordinates'], payload['insertion_sizes'], ins_vals)])
                     sub_inds.append(payload['substitution_positions'])
                     edit_strings.append('D'+str(int(payload['deletion_n']))+';I'+str(int(payload['insertion_n']))+';S'+str(int(payload['substitution_n'])))