Check to see that no amplicons and their reverse complement exist in …

…the input regions

CRISPResso2/CRISPRessoPooledCORE.py

@@ -735,6 +735,13 @@ def main():
                 duplicated_entries = df_template.amplicon_seq[df_template.amplicon_seq.duplicated()]
                 raise Exception('The amplicon sequences must be distinct! (Duplicated entries: ' + str(duplicated_entries.values) + ')')
 
+            #check to see that no sequences and their reverse complements are present
+            amp_seqs = df_template.amplicon_seq.values #Beware, this is a numpy array of dtype str and if you add these arrays amp_seqs + rc_amp_seqs, it will concat the strings, not the arrays....
+            rc_amp_seqs = [CRISPRessoShared.reverse_complement(amp_seq) for amp_seq in amp_seqs]
+            for seq in amp_seqs:
+                if seq in rc_amp_seqs:
+                    raise Exception('Amplicon sequences must be distinct! The amplicon sequence %s is the reverse complement of another amplicon sequence in the region file. Please provide only one of the two sequences.' % seq)
+
             if not len(df_template.amplicon_name.unique())==df_template.shape[0]:
                 duplicated_entries = df_template.amplicon_name[df_template.amplicon_name.duplicated()]
                 raise Exception('The amplicon names must be distinct! (Duplicated names: ' + str(duplicated_entries.values) + ')')