diff --git a/inference.py b/inference.py
index 6e1a0a54b3b9714435f4499197a33385c64fa920..3c1cc00295a65cd742e810a1d6e09911aaa089bc 100644
--- a/inference.py
+++ b/inference.py
@@ -198,22 +198,6 @@ def get_sequence_after(last_seg,seg_seq,n,paths,feat):
current_index+=1
return sequence_after[len(sequence_after)-100:]
-
-
- '''
- first_strand=convert_strand(segments_on_target_genome[first_seg][3])
- first_seg_stranded=first_strand+first_seg
- last_strand=convert_strand(segments_on_target_genome[last_seg][3])
- last_seg_stranded=last_strand+last_seg
- index_first_seg=int(paths[target_genome_name].index(first_seg_stranded))
- index_last_seg=int(paths[target_genome_name].index(last_seg_stranded))
- first_index=min(index_first_seg,index_last_seg)
- last_index=max(index_last_seg,index_first_seg)
- list_segfeat_azu=paths[target_genome_name][first_index:last_index+1]
- list_segfeat_azu_corrected=[convert_strand(segment_stranded[0])+segment_stranded[1:] for segment_stranded in list_segfeat_azu]
- '''
-
-
def get_sequence_on_genome(feature,segments_on_target_genome):
list_seg=Features[feature].segments_list
first_seg=get_first_seg(list_seg,segments_on_target_genome)
@@ -279,6 +263,22 @@ def findOtherStart(cds,segments_on_target_genome):
return frame_shift
+
+# ajouter la vérification qu'on introduit/delete pas un codon stop
+def print_variation_change(deleted_sequence,inserted_sequence):
+ deleted_aa=traduction(get_rna(deleted_sequence))
+ inserted_aa=traduction(get_rna(inserted_sequence))
+ if (len(deleted_aa)!=0) & (len(inserted_aa)!=0):
+ if deleted_aa!=inserted_aa:
+ print("conséquence : changement de",",".join(deleted_aa),"en",",".join(inserted_aa))
+ else:
+ print("conséquence : mutation synonyme dans",",".join(deleted_aa))
+ elif len(inserted_aa)!=0:
+ print("conséquence : insertion de",",".join(inserted_aa))
+ else:
+ print("conséquence : deletion de",",".join(deleted_aa))
+
+
version="new"
import re
for feature in Features.values():
@@ -288,7 +288,8 @@ for cds_id in cds_var.keys():
cds=Features[cds_id]
print("analyse des variations dans le cds",cds_id)
frame_shift=0
- for var in cds_var[cds_id]:
+ #for var in cds_var[cds_id]:
+ for index, var in enumerate(cds_var[cds_id]):
type_var=var[8]
if type_var!="no_var": #Â if there is a variation
posVar=[int(var[12]),int(var[13])]
@@ -303,7 +304,7 @@ for cds_id in cds_var.keys():
else:
length_alt=len(var[10])
- print(var)
+ print("variation",index)
if abs(length_alt-length_ref)%3 == 0: # taille diff 3k -> pas de frame shift.
@@ -316,21 +317,10 @@ for cds_id in cds_var.keys():
else:
print(type_var,"de",var[9],"par",var[10])
-
len_fragment_after=(3-length_ref)%3
- deleted_aa=traduction(get_rna(cds.sequence[posVar[0]:posVar[0]+length_ref+len_fragment_after]))
- inserted_aa=traduction(get_rna(sequence_target[posVar[1]:posVar[1]+length_alt+len_fragment_after]))
-
- if (length_ref!=0) & (length_alt!=0):
- if deleted_aa!=inserted_aa:
- print("conséquence : changement de",",".join(deleted_aa),"en",",".join(inserted_aa))
- else:
- print("conséquence : mutation synonyme dans",",".join(deleted_aa))
- elif length_alt!=0:
- print("conséquence : insertion de",",".join(inserted_aa))
- else:
- print("conséquence : deletion de",",".join(deleted_aa))
-
+ deleted_sequence=cds.sequence[posVar[0]:posVar[0]+length_ref+len_fragment_after]
+ inserted_sequence=sequence_target[posVar[1]:posVar[1]+length_alt+len_fragment_after]
+ print_variation_change(deleted_sequence,inserted_sequence)
else: # taille diff 3k, position !=3k
print("variation au milieu d'un codon sans décalage du cadre de lecture")
@@ -347,13 +337,7 @@ for cds_id in cds_var.keys():
total_ins=sequence_target[posVar[1]-len_fragment_before:posVar[1]+length_alt+len_fragment_after]
total_del=cds.sequence[posVar[0]-len_fragment_before:posVar[0]+length_ref+len_fragment_after]
- deleted_aa=traduction(get_rna(total_del))
- inserted_aa=traduction(get_rna(total_ins))
- if deleted_aa!=inserted_aa:
- print("conséquence : changement de",",".join(deleted_aa),"en",",".join(inserted_aa))
- else:
- print("conséquence : mutation synonyme dans",",".join(deleted_aa))
-
+ print_variation_change(total_del,total_ins)
# possibilité que j'ai print en compte une variation de trop, si on a un snp sur la premiere et la derniere base d'un codon :
# pour le traitement de la première j'ai également considéré la dernière !
@@ -365,11 +349,6 @@ for cds_id in cds_var.keys():
# frameshift=0 -> cadre de lecture rétabli. peut nécessiter d'aller chercher une base en amont.
# frameshift=1 -> cadre de lecture décalé de 1 base vers la droite
# frameshift=2 -> cadre de lecture décalé de 2 bases vers la droite
- if old_frameshift==0:
- print("perte du cadre de lecture originel")
- elif frame_shift==0:
- print("rétablissement du cadre de lecture originel")
-
if type_var=="insertion":
print(type_var,"de",var[10])
@@ -378,13 +357,57 @@ for cds_id in cds_var.keys():
else:
print(type_var,"de",var[9],"par",var[10])
- print(frame_shift)
+ len_fragment_before_del=(posVar[0])%3
+ len_fragment_before_ins=(posVar[1])%3
+
+ if frame_shift==0:
+ # print only the local change.
+ len_fragment_after_del=(3-(len_fragment_before_del+length_ref))%3
+ len_fragment_after_ins=(3-(len_fragment_before_ins+length_alt))%3
+ total_ins=sequence_target[posVar[1]-len_fragment_before_ins:posVar[1]+length_alt+len_fragment_after_ins]
+ total_del=cds.sequence[posVar[0]-len_fragment_before_del:posVar[0]+length_ref+len_fragment_after_del]
+ print_variation_change(total_del,total_ins)
+ print("rétablissement du cadre de lecture originel")
+
+ else:
+ # print changes from local to next var
+ print("cadre de lecture décalé de",frame_shift,"base(s) vers la droite.")
+ if old_frameshift==0:
+ print("perte du cadre de lecture originel")
+ if index==len(cds_var[cds_id])-1: # on est sur la dernière variation. traduire jusqu'à la fin du cds
+ total_total_del=cds.sequence[posVar[0]-len_fragment_before_del:]
+ total_total_ins=sequence_target[posVar[1]-len_fragment_before_ins:]
+ print_variation_change(total_total_del,total_total_ins)
+ else:
+ nextVar=cds_var[cds_id][index+1]
+ posNextVar=[int(nextVar[12]),int(nextVar[13])]
+
+ if nextVar[8]=="insertion":
+ length_ref_nextvar=0
+ else:
+ length_ref_nextvar:len(nextVar[9])
+ if nextVar[8]=="deletion":
+ length_alt_nextvar=0
+ else:
+ length_alt_nextvar=len(nextVar[10])
+
+ len_fragment_before_del_nextvar=(posNextVar[0])%3
+ len_fragment_before_ins_nextvar=(posNextVar[1])%3
+ total_total_del=cds.sequence[posVar[0]-len_fragment_before_del:posNextVar[0]-len_fragment_before_del_nextvar]
+ total_total_ins=sequence_target[posVar[1]-len_fragment_before_ins:posNextVar[1]-len_fragment_before_ins_nextvar]
+ print_variation_change(total_total_del,total_total_ins)
+
+
+
+
+
+
if posVar[0]<=3: # pour l'instant on cherche pas d'autre start.
print("codon start touché donc gène non fonctionnel")
#findOtherStart(cds,segments_on_target_genome)
- #break
+ break