"git@forge.ird.fr:us191/TSG-QC.git" did not exist on "22d0258ec25bc602ed6fa1a44df15befdb81eb21"
Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
from .intersect import Features
# functions to output the stats on the transfer
# stats about missing segments and feature type, not used, will change.
def stats_feature_missing_segment(feature_missing_segments,first_seg,last_seg,list_seg,feature_id,walk,segments_on_target_genome):
# [feature_missing_first,feature_missing_middle,feature_missing_last,feature_missing_all,feature_missing_total,feature_total,feature_ok]
feature_missing_segments[5].append(feature_id)
if first_seg=='' : # no segment of the feature is in the genome, the feature is missing entirely
feature_missing_segments[3].append(feature_id)
elif first_seg != list_seg[0]: # the first segment is missing
feature_missing_segments[0].append(feature_id)
elif last_seg!=list_seg[-1]: # the last segment is missing
feature_missing_segments[2].append(feature_id)
# go through all the segments, check if some are missing in the middle of the feature
elif (len(list_seg)!=1) and (feature_id not in feature_missing_segments[3]): # to access the second to last element
for segment in list_seg[1-(len(list_seg)-2)]:
if (segment not in segments_on_target_genome) or (walk not in segments_on_target_genome[segment]):
feature_missing_segments[1].append(feature_id)
break
# go through the segments, to see if one is missing anywhere on the feature
for segment in list_seg:
if (segment not in segments_on_target_genome) or (walk not in segments_on_target_genome[segment]):
if feature_id not in feature_missing_segments[4]:
feature_missing_segments[4].append(feature_id)
break
# if the feature doesnt have a missing segment, it is complete. ADD THE PATH CHECK FOR INSERTIONS !!
if feature_id not in feature_missing_segments[4]:
feature_missing_segments[6].append(feature_id)
def get_annot_features(list_features):
list_annot_features=[]
for feature in list_features:
list_annot_features.append(Features[feature].note)
return list_annot_features
def count_hypput_total(list_annot_first):
total=len(list_annot_first)
count_hypput=0
for annot in list_annot_first:
if ("hypothetical" in annot) or ("putative" in annot):
count_hypput+=1
return [count_hypput,total]
# print stats on the transfer : number of feature that have segments in different positions missing.
def stats_features(feature_missing_segments):
# [feature_missing_first,feature_missing_middle,feature_missing_last,feature_missing_all,feature_missing_total,feature_total,feature_ok]
list_annot_first=get_annot_features(feature_missing_segments[0])
[hyp_put,total]=count_hypput_total(list_annot_first)
print("\nthe first segment is missing for", total,"features, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_middle=get_annot_features(feature_missing_segments[1])
[hyp_put,total]=count_hypput_total(list_annot_middle)
print("a middle segment is missing for", total,"features, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_last=get_annot_features(feature_missing_segments[2])
[hyp_put,total]=count_hypput_total(list_annot_last)
print("the last segment is missing for", total,"features, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_all=get_annot_features(feature_missing_segments[3])
[hyp_put,total]=count_hypput_total(list_annot_all)
print(total,"features are entirely missing, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_total=get_annot_features(feature_missing_segments[4])
[hyp_put,total]=count_hypput_total(list_annot_total)
print("there is at least one segment missing for", total,"features, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_ok=get_annot_features(feature_missing_segments[6])
[hyp_put,total]=count_hypput_total(list_annot_ok)
print(total ,"features are entirely present in the new genome, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")
list_annot_features=get_annot_features(feature_missing_segments[5])
[hyp_put,total]=count_hypput_total(list_annot_features)
print("there is", total,"features in total, including",round(100*(hyp_put)/total,2),"% hypothetical or putative.")