v2.0.30 case-insensitive guides, fix #17

pinellolab · Jul 2, 2019 · 60f9005 · 60f9005
1 parent 702b9dc
commit 60f9005
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 13 deletions.
diff --git a/CRISPResso2/CRISPRessoCORE.py b/CRISPResso2/CRISPRessoCORE.py
@@ -600,7 +600,8 @@ def print_stacktrace_if_debug():
                 this_contains_guide = True
 
             for guide_idx, guide_seq in enumerate(guides):
-                if guide_seq in this_sgRNA_sequences:
+                #this_sgRNA_sequences contains all good guides contained in this amplicon
+                if guide_seq.upper() in this_sgRNA_sequences:
                     found_guide_seq[guide_idx] = True
 
             # Calculate coding sequence for this reference
@@ -1803,11 +1804,11 @@ def calculate_range(l):
                 unmod_pct = "NA"
                 mod_pct = "NA"
                 if n_aligned > 0:
-                    unmod_pct = 100*n_unmod/float(n_aligned)
-                    mod_pct = 100*n_mod/float(n_aligned)
+                    unmod_pct = round(100*n_unmod/float(n_aligned),8)
+                    mod_pct = round(100*n_mod/float(n_aligned),8)
 
                 vals = [ref_name]
-                vals.extend([str(x) for x in [round(unmod_pct,8),round(mod_pct,8),n_aligned,N_TOTAL,n_unmod,n_mod,n_discarded,n_insertion,n_deletion,n_substitution,n_only_insertion,n_only_deletion,n_only_substitution,n_insertion_and_deletion,n_insertion_and_substitution,n_deletion_and_substitution,n_insertion_and_deletion_and_substitution]])
+                vals.extend([str(x) for x in [unmod_pct,mod_pct,n_aligned,N_TOTAL,n_unmod,n_mod,n_discarded,n_insertion,n_deletion,n_substitution,n_only_insertion,n_only_deletion,n_only_substitution,n_insertion_and_deletion,n_insertion_and_substitution,n_deletion_and_substitution,n_insertion_and_deletion_and_substitution]])
                 outfile.write("\t".join(vals) + "\n")
 
         crispresso2_info['quant_of_editing_freq_filename'] = os.path.basename(quant_of_editing_freq_filename)

diff --git a/CRISPResso2/CRISPRessoPooledCORE.py b/CRISPResso2/CRISPRessoPooledCORE.py
@@ -269,7 +269,7 @@ def main():
         info('Checking dependencies...')
 
         if check_samtools() and check_bowtie2():
-            info('\n All the required dependencies are present!')
+            info('All the required dependencies are present!')
         else:
             sys.exit(1)
 
@@ -463,10 +463,12 @@ def main():
             df_template.Coding_sequence=df_template.Coding_sequence.apply(capitalize_sequence)
 
             if not len(df_template.Amplicon_Sequence.unique())==df_template.shape[0]:
-                raise Exception('The amplicons should be all distinct!')
+                duplicated_entries = df_template.Amplicon_Sequence[df_template.Amplicon_Sequence.duplicated()]
+                raise Exception('The amplicon sequences must be distinct! (Duplicated entries: ' + str(duplicated_entries.values) + ')')
 
             if not len(df_template.Name.unique())==df_template.shape[0]:
-                raise Exception('The amplicon names should be all distinct!')
+                duplicated_entries = df_template.Name[df_template.Name.duplicated()]
+                raise Exception('The amplicon names must be distinct! (Duplicated names: ' + str(duplicated_entries.values) + ')')
 
             df_template=df_template.set_index('Name')
             df_template.index=df_template.index.to_series().str.replace(' ','_')

diff --git a/CRISPResso2/CRISPRessoShared.py b/CRISPResso2/CRISPRessoShared.py
@@ -29,7 +29,7 @@
 else:
     import cPickle as cp #python 2.7
 
-__version__ = "2.0.29"
+__version__ = "2.0.30"
 
 ###EXCEPTIONS############################
 class FlashException(Exception):
@@ -638,14 +638,14 @@ def get_amplicon_info_for_guides(ref_seq,guides,quantification_window_center,qua
     for guide_idx, current_guide_seq in enumerate(guides):
         offset_fw=quantification_window_center+len(current_guide_seq)-1
         offset_rc=(-quantification_window_center)-1
-        new_cut_points=[m.start() + offset_fw for m in re.finditer(current_guide_seq, ref_seq)]+\
-                         [m.start() + offset_rc for m in re.finditer(reverse_complement(current_guide_seq), ref_seq)]
+        new_cut_points=[m.start() + offset_fw for m in re.finditer(current_guide_seq, ref_seq, flags=re.IGNORECASE)]+\
+                         [m.start() + offset_rc for m in re.finditer(reverse_complement(current_guide_seq), ref_seq, flags=re.IGNORECASE)]
 
         if (new_cut_points):
             this_sgRNA_cut_points += new_cut_points
-            this_sgRNA_intervals+=[(m.start(),m.start()+len(current_guide_seq)-1) for m in re.finditer(current_guide_seq, ref_seq)]+\
-                                  [(m.start(),m.start()+len(current_guide_seq)-1) for m in re.finditer(reverse_complement(current_guide_seq), ref_seq)]
-            this_sgRNA_sequences.append(current_guide_seq)
+            this_sgRNA_intervals+=[(m.start(),m.start()+len(current_guide_seq)-1) for m in re.finditer(current_guide_seq, ref_seq, flags=re.IGNORECASE)]+\
+                                  [(m.start(),m.start()+len(current_guide_seq)-1) for m in re.finditer(reverse_complement(current_guide_seq), ref_seq, flags=re.IGNORECASE)]
+            this_sgRNA_sequences.append(current_guide_seq.upper())
 
     #create mask of positions in which to include/exclude indels for the quantification window
     #first, if exact coordinates have been given, set those