-
Notifications
You must be signed in to change notification settings - Fork 1
/
PyFuncover.py
1340 lines (1182 loc) · 49.3 KB
/
PyFuncover.py
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#! /usr/bin/ python
# -*- coding: utf8 -*-
###########
# IMPORTS #
###########
from __future__ import division
import os
#in case if using in a server
import matplotlib
if os.environ.get('DISPLAY','') == '':
print('no display found. Using non-interactive Agg backend')
matplotlib.use('Agg')
import argparse
from Bio import SearchIO, SeqIO
from Bio.Blast.Applications import NcbiblastpCommandline
import ftplib
from ftplib import FTP
import gzip
import json
import matplotlib.pyplot as plt
from matplotlib import cm, colors
import numpy as np
import pandas as pd
import re
import requests
import shutil
import subprocess
import tarfile
from threading import Thread
import urllib
import textwrap
import sys
#get system
if sys.platform in ['win32']:
FLAG = True
else:
FLAG = False
#disable BioPython Warning about future deprecated Search.IO
import warnings
from Bio import BiopythonExperimentalWarning
with warnings.catch_warnings():
warnings.simplefilter('ignore', BiopythonExperimentalWarning)
from Bio import SearchIO
#############
# FUNCTIONS #
#############
def init():
"""
Download genomes references and taxonomic database
"""
print("Connection to the FTP NCBI Serveur...")
ftp = ftplib.FTP()
ftp.connect('ftp.ncbi.nlm.nih.gov')
ftp.login(user='anonymous',passwd='your.email@gmail.com')
print('Download the reference genomes list...')
with open(os.getcwd()+"/assembly_summary_refseq.txt", "w") as f:
ftp.retrbinary('RETR %s' % 'genomes/refseq/assembly_summary_refseq.txt', f.write)
print('Download the genomes assembly list for eukaryotes organisms...')
with open(os.getcwd()+"/eukaryotes.txt", "w") as f:
ftp.retrbinary('RETR %s' % 'genomes/GENOME_REPORTS/eukaryotes.txt', f.write)
print('Download the genomes assembly list for prokaryotes organisms...')
with open(os.getcwd()+"/prokaryotes.txt", "w") as f:
ftp.retrbinary('RETR %s' % 'genomes/GENOME_REPORTS/prokaryotes.txt', f.write)
ftp.close()
#check if folder dont already exist
if os.path.isdir(os.getcwd()+"/TAXONOMY") == False:
os.mkdir(os.getcwd()+"/TAXONOMY")
print('Download the Taxonomic database...')
with open(os.getcwd()+"/TAXONOMY/taxdump.tar.gz", "w") as f:
urllib.urlretrieve("ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz", os.getcwd()+"/TAXONOMY/taxdump.tar.gz")
urllib.urlcleanup()
print('Extracting Database...')
tfile = tarfile.open(os.getcwd()+"/TAXONOMY/taxdump.tar.gz", 'r:gz')
tfile.extract("nodes.dmp",os.getcwd()+"/TAXONOMY/.")
tfile.extract("names.dmp",os.getcwd()+"/TAXONOMY/.")
tfile.close()
os.remove(os.getcwd()+"/TAXONOMY/taxdump.tar.gz")
print('Finish ! Exit')
def dic_Name():
"""
Create the dicName and dicNameInverse
dicName :
key : Taxid : value : specie (scientific name)
dicNameInverse :
Key : Species (scientific name) : Value : Taxid
return : dicName, dicNameInverse
"""
#open file
names = open(os.getcwd()+"/TAXONOMY/names.dmp","r")
#create dict with names
dicName = dict()
dicNameInverse = dict()
for ligne in names:
ligne = ligne.replace("\t|\n","").split("\t|\t")
fin = ligne[len(ligne)-1]
if fin == 'scientific name':
dicName[ligne[0]]=ligne[1]
dicNameInverse[ligne[1]]=ligne[0]
return dicName, dicNameInverse
def dic_Node():
"""
return dicNode
"""
#open file
nodes = open(os.getcwd()+"/TAXONOMY/nodes.dmp","r")
#create a dict with nodes
dicNode = dict()
for ligne in nodes:
ligne = ligne.replace("\t|\n","").split("\t|\t")
dicNode[ligne[0]] = [ligne[1],ligne[2]]
return dicNode
def getLineage(specie,dic_Node,dic_Name):
#create dicNode and dicName
dicNode = dic_Node
dicName = dic_Name[0]
dicNameInverse = dic_Name[1]
sp = specie
for j in "[]":
sp = sp.replace(j,"")
i = dicNameInverse[sp]
genre = [specie]
id_type = dicNode[i][1] #controle la boucle while si "root"
id_parent = dicNode[i][0]
while genre[0] != "root":
parent = [dicName[id_parent]]
genre = parent + genre
id_type = dicNode[id_parent][1] #met a jour le controle
id_parent = dicNode[id_parent][0]
return genre
def lineage(dicName,dicNode):
"""
Create a dictionnary with all Lineage from self.nodes and self.name
"""
dicLineage = dict()
for i in dicNode.keys():
genre = [dicName[i]]
id_type = dicNode[i][1] #controle la boucle while si "root"
id_parent = dicNode[i][0]
while genre[0] != "root":
parent = [dicName[id_parent]]
genre = parent + genre
id_type = dicNode[id_parent][1] #met a jour le controle
id_parent = dicNode[id_parent][0]
dicLineage[genre[-1]]=genre
return dicLineage
def groupedTaxId(dicLineage, dicNameinverse):
"""
Create a dictionnary with all sub taxid for a given taxid
"""
dicGroupedTaxid = dict()
for species in dicLineage.keys():
lineage_liste = dicLineage[species]
taxid = dicNameinverse[species]
dicGroupedTaxid[taxid] = set([taxid])
for sub_rank in lineage_liste:
taxid_rank = dicNameinverse[sub_rank]
if taxid_rank not in dicGroupedTaxid:
dicGroupedTaxid[taxid_rank] = set()
dicGroupedTaxid[taxid_rank].add(taxid)
else:
dicGroupedTaxid[taxid_rank].add(taxid)
return dicGroupedTaxid
def chunks(l, n):
for i in xrange(0, len(l), n):
yield l[i:i + n]
def uniprot2ncbi_accession(l):
"""
l : liste of UNIPROT Accessions
"""
dico_data = dict()
headers = {
'Connection': 'keep-alive',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7',
}
params = {
'method': 'db2db',
'input': 'UniProt Accession',
'inputValues': '',
'outputs': 'GenBank Protein Accession',
'taxonId': '',
'format': 'row',
}
lol_accession = list(chunks(list(l),250))
cpt = 1
for l in lol_accession:
print("/".join([str(cpt),str(len(lol_accession))])+" (250 items)")
cpt += 1
json_data = bioDBnet_request(l, headers, params)
for i in json_data:
for key,data in i.items():
uniprot = i['InputValue']
genbank = i['GenBank Protein Accession'].split('//')
dico_data[uniprot] = genbank
return dico_data
def get_biodbnet_data(l,db,NB_PROT_DB):
"""
l : <list> liste of NCBI ref Seq Accessions
db : <list> list of output db
NB_PROT_DB : <int> Number of protein for each requests
"""
dico_data = dict()
headers = {
'Connection': 'keep-alive',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'fr-FR,fr;q=0.9,en-US;q=0.8,en;q=0.7',
}
params = {
'method': 'db2db',
'input': 'RefSeq Protein Accession',
'inputValues': '',
'outputs': ','.join(db),
'taxonId': '',
'format': 'row',
}
lol_accession = list(chunks(list(l),NB_PROT_DB))
cpt = 1
for l in lol_accession:
print("/".join([str(cpt),str(len(lol_accession))])+" ({} items)".format(NB_PROT_DB))
cpt += 1
json_data = bioDBnet_request(l, headers, params)
for i in json_data:
for key,data in i.items():
if key not in dico_data:
dico_data[key] = [data]
else:
dico_data[key] += [data]
return dico_data
def bioDBnet_database(id_list):
"""
Return the user choosen DB
Defaut, return GO-TERM DB
"""
data = {
1 : 'Affy ID',
2 : 'Agilent ID',
3 : 'Allergome Code',
4 : 'ApiDB_CryptoDB ID',
5 : 'Biocarta Pathway Name',
6 : 'BioCyc ID',
7 : 'CCDS ID',
8 : 'Chromosomal Location',
9 : 'CleanEx ID',
10 : 'CodeLink ID',
11 : 'COSMIC ID',
12 : 'CPDB Protein Interactor',
13 : 'CTD Disease Info',
14 : 'CTD Disease Name',
15 : 'CYGD ID',
16 : 'dbSNP ID',
17 : 'dictyBase ID',
18 : 'DIP ID',
19 : 'DisProt ID',
20 : 'DrugBank Drug ID',
21 : 'DrugBank Drug Info',
22 : 'DrugBank Drug Name',
23 : 'EC Number',
24 : 'EchoBASE ID',
25 : 'EcoGene ID',
26 : 'Ensembl Biotype',
27 : 'Ensembl Gene ID',
28 : 'Ensembl Gene Info',
29 : 'Ensembl Protein ID',
30 : 'Ensembl Transcript ID',
31 : 'FlyBase Gene ID',
32 : 'FlyBase Protein ID',
33 : 'FlyBase Transcript ID',
34 : 'GAD Disease Info',
35 : 'GAD Disease Name',
36 : 'GenBank Nucleotide Accession',
37 : 'GenBank Nucleotide GI',
38 : 'GenBank Protein Accession',
39 : 'GenBank Protein GI',
40 : 'Gene ID',
41 : 'Gene Info',
42 : 'Gene Symbol',
43 : 'Gene Symbol and Synonyms',
44 : 'Gene Symbol ORF',
45 : 'Gene Synonyms',
46 : 'GeneFarm ID',
47 : 'GO - Biological Process',
48 : 'GO - Cellular Component',
49 : 'GO - Molecular Function',
50 : 'GO ID',
51 : 'GSEA Standard Name',
52 : 'H-Inv Locus ID',
53 : 'HAMAP ID',
54 : 'HGNC ID',
55 : 'HMDB Metabolite',
56 : 'Homolog - All Ens Gene ID',
57 : 'Homolog - All Ens Protein ID',
58 : 'Homolog - All Gene ID',
59 : 'Homolog - Human Ens Gene ID',
60 : 'Homolog - Human Ens Protein ID',
61 : 'Homolog - Human Gene ID',
62 : 'Homolog - Mouse Ens Gene ID',
63 : 'Homolog - Mouse Ens Protein ID',
64 : 'Homolog - Mouse Gene ID',
65 : 'Homolog - Rat Ens Gene ID',
66 : 'Homolog - Rat Ens Protein ID',
67 : 'Homolog - Rat Gene ID',
68 : 'HomoloGene ID',
69 : 'HPA ID',
70 : 'HPRD ID',
71 : 'HPRD Protein Complex',
72 : 'HPRD Protein Interactor',
73 : 'Illumina ID',
74 : 'IMGT/GENE-DB ID',
75 : 'InterPro ID',
76 : 'IPI ID',
77 : 'KEGG Disease ID',
78 : 'KEGG Gene ID',
79 : 'KEGG Orthology ID',
80 : 'KEGG Pathway ID',
81 : 'KEGG Pathway Info',
82 : 'KEGG Pathway Title',
83 : 'LegioList ID',
84 : 'Leproma ID',
85 : 'Locus Tag',
86 : 'MaizeGDB ID',
87 : 'MEROPS ID',
88 : 'MGC(ZGC/XGC) ID',
89 : 'MGC(ZGC/XGC) Image ID',
90 : 'MGC(ZGC/XGC) Info',
91 : 'MGI ID',
92 : 'MIM ID',
93 : 'MIM Info',
94 : 'miRBase ID',
95 : 'NCIPID Pathway Name',
96 : 'NCIPID Protein Complex',
97 : 'NCIPID Protein Interactor',
98 : 'NCIPID PTM',
99 : 'Orphanet ID',
100 : 'PANTHER ID',
101 : 'Paralog - Ens Gene ID',
102 : 'PBR ID',
103 : 'PDB ID',
104 : 'PeroxiBase ID',
105 : 'Pfam ID',
106 : 'PharmGKB Drug Info',
107 : 'PharmGKB Gene ID',
108 : 'PIR ID',
109 : 'PIRSF ID',
110 : 'PptaseDB ID',
111 : 'PRINTS ID',
112 : 'ProDom ID',
113 : 'PROSITE ID',
114 : 'PseudoCAP ID',
115 : 'PubMed ID',
116 : 'Reactome ID',
117 : 'Reactome Pathway Name',
118 : 'REBASE ID',
119 : 'RefSeq Genomic Accession',
120 : 'RefSeq Genomic GI',
121 : 'RefSeq mRNA Accession',
122 : 'RefSeq ncRNA Accession',
123 : 'RefSeq Nucleotide GI',
124 : 'RefSeq Protein Accession',
125 : 'RefSeq Protein GI',
126 : 'Rfam ID',
127 : 'RGD ID',
128 : 'SGD ID',
129 : 'SMART ID',
130 : 'STRING Protein Interactor',
131 : 'TAIR ID',
132 : 'Taxon ID',
133 : 'TCDB ID',
134 : 'TIGRFAMs ID',
135 : 'TubercuList ID',
136 : 'UCSC ID',
137 : 'UniGene ID',
138 : 'UniProt Accession',
139 : 'UniProt Entry Name',
140 : 'UniProt Info',
141 : 'UniProt Protein Name',
142 : 'UniSTS ID',
143 : 'VectorBase Gene ID',
144 : 'VEGA Gene ID',
145 : 'VEGA Protein ID',
146 : 'VEGA Transcript ID',
147 : 'WormBase Gene ID',
148 : 'WormPep Protein ID',
149 : 'XenBase Gene ID',
150 : 'ZFIN ID',
}
if id_list:
return [data[i] for i in id_list]
else:
return ['UniProt Accession', 'GO - Biological Process', 'GO - Cellular Component', 'GO - Molecular Function']
def bioDBnet_request(l, headers, params, taxid=False):
"""
Make the request to the BioDBnet website
input :
l (liste) : list of the value to be converted
headers (dict) : parameter of the header of the URL request
params (dict) : parameter of the URL request
taxid (string) default = False : String of the taxid , default False
output :
json_data (dict) : JSON response as a dict of the response request
"""
s = ",".join(l)
params['inputValues'] = s
if taxid:
params['taxonId'] = taxid
r = requests.get('https://biodbnet-abcc.ncifcrf.gov/webServices/rest.php/biodbnetRestApi.json', headers=headers, params=params)
try:
json_data = json.loads(r.text)
return json_data
except:
print('ERROR ! :')
print('Response statue')
print(r)
print('Response content')
print(r.text)
print('Make the request one by one')
json_data_list = list()
for a in l:
print('{}/{}'.format(l.index(a),len(l)))
params['inputValues'] = a
r = requests.get('https://biodbnet-abcc.ncifcrf.gov/webServices/rest.php/biodbnetRestApi.json', headers=headers, params=params)
try:
json_data = json.loads(r.text)
json_data_list += json_data
except:
print('ERROR ! :')
print('Response statue')
print(r)
print('Response content')
print(r.text)
print('TOO MANY CROSS-REF EXCEPTION :\nThe reccord : {} failed ! Try a smaller number of cross-refs'.format(a))
print('JOB ABORTED ! Sorry...')
exit()
return json_data_list
def download_pfam(PFAMS):
"""
Download the MSA of the UNIPROT & NCBI sequence from the PFAM familly
input:
PFAMS (list) : List of PFAM accession number
output:
PFAMS_PATH (list) : List of file with NCBI & UNIPROT sequence per accession of the PFAM in FASTA
"""
#Cretae the PFAM Folder
PFAMS_PATH = list()
if os.path.isdir(os.path.join(os.getcwd(),"PFAMS")) == False:
os.mkdir(os.path.join(os.getcwd(),"PFAMS"))
#in case the list are empty
if PFAMS:
#request parameter
pfam_params = {'format':'fasta',
'alnType':'ncbi',
'order':'a',
'case':'u',
'gaps':'dashes',
'download':'0'}
for pfam in PFAMS:
#Create folder for the specific PFAM
path = os.path.join(os.getcwd(),"PFAMS",pfam)
if os.path.isdir(path) == False:
os.mkdir(path)
#NCBI
print('Download PFAM MSA alignment with NCBI sequences')
filename_NCBI = os.path.join(path,"PFAM_{}_NCBI.fasta".format(pfam))
if not os.path.isfile(filename_NCBI):
resp = requests.get("http://pfam.xfam.org/family/{}/alignment/ncbi/format?".format(pfam), params=pfam_params)
with open(filename_NCBI, "w") as f:
f.write(resp.content)
#UNIPROT
print('Download PFAM MSA alignment with UNIPROT sequences')
filename_UNIPROT = os.path.join(path,"PFAM_{}_UNIPROT.fasta".format(pfam))
if not os.path.isfile(filename_UNIPROT):
resp = requests.get("http://pfam.xfam.org/family/{}/alignment/uniprot/format?".format(pfam), params=pfam_params)
with open(filename_UNIPROT, "w") as f:
f.write(resp.content)
#READ THE ALIGNMENT TO EXTRACT ACCESSIONS (NCBI)
accession_PFAM_NCBI = set([record.id.split('/')[0] for record in SeqIO.parse(filename_NCBI,'fasta')])
accession_PFAM_UNIPROT = set([record.id.split('/')[0] for record in SeqIO.parse(filename_UNIPROT,'fasta')])
#convert the UNIPROT to NCBI accession
print('Convert the UNIPROT accession from the PFAM UNIPROT MSA to NCBI accessions')
dico_uniprot_to_genbank = uniprot2ncbi_accession(accession_PFAM_UNIPROT)
#check if UNIPROT = NCBI accesion inside the PFAM of NCBI
print("check the UNIPROT-NCBI converted accession into the NCBI PFAM")
uniprot_not_in_ncbi = list()
for uniprot in dico_uniprot_to_genbank:
list_genbank = dico_uniprot_to_genbank[uniprot]
inside = False
for gbk in list_genbank:
if gbk in accession_PFAM_NCBI:
inside = True
if not inside:
uniprot_not_in_ncbi += [uniprot]
print("Adding {} to the actual NCBI Accession".format(uniprot))
### GET THE SAME FILE AS FASTA ###
pfam_no_seq = os.path.join(path,'PFAM_{}_NOGAP_SEQ.fasta'.format(pfam))
PFAMS_PATH += [pfam_no_seq]
with open(pfam_no_seq, "w") as f:
for records in SeqIO.parse(filename_NCBI,'fasta'):
iD = records.id
seq = str(records.seq).replace('-','')
f.write('>'+iD+'\n')
f.write(seq+'\n')
for records in SeqIO.parse(filename_UNIPROT,'fasta'):
iD = records.id
iD_split = records.id.split('/')[0]
#case when common accession are in the UNIPROT and NCBI
if iD_split not in accession_PFAM_NCBI:
if iD_split in uniprot_not_in_ncbi:
seq = str(records.seq).replace('-','')
f.write('>'+iD+'\n')
f.write(seq+'\n')
print('Create BLAST DB')
make_blastdb([os.path.join(path,'PFAM_{}_NOGAP_SEQ.fasta'.format(pfam))])
return PFAMS_PATH
def acc_to_ftp_path(acc):
"""
from : https://github.com/ctSkennerton/scriptShed/blob/master/download_ncbi_assembly.py
Return the FTP Path given the GCA accession number of a genome assembly
input:
acc (string) : GCA number of the NCBI Genome Assembly
output:
prefix (string) : prefix of the FTP path
accp (string) : path of the GCA accession number
version (string) : version of the assembly
"""
match = re.search('(\w+)_(\d+)\.(\d)', acc)
if match:
prefix = match.group(1)
accn = match.group(2)
version = match.group(3)
accp = re.findall('.{3}', accn)
accp = '/'.join(accp)
return (prefix, accp, version)
else:
raise ValueError("could not get FTP path from ".format(acc))
def get_files_from_types(types, base_name, ftp, path, ftp_true=False):
"""
from https://github.com/ctSkennerton/scriptShed/blob/master/download_ncbi_assembly.py
Download the genome
input :
types (list) : List of NCBI type suffix file
bas_name (string) : Basename of the genome file
ftp (ftp object) : ftp session object to the NCBI FTP Server
path (string) : output folder
return:
out : path of the downloaded genome
"""
out = str()
if ftp_true:
#download
for t in types:
f = path+base_name+types[0]
try:
urllib.urlretrieve(ftp_true+'/'+base_name+t, f)
except IOError:
print('No proteomic file availlable for : {}'.format(base_name))
return False
urllib.urlcleanup()
#extract
with gzip.open(f, 'rb') as f_in:
out = f.replace('.gz','')
with open(out, 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
#remove file
os.remove(f)
return out
else:
for g in ftp.nlst():
for t in types:
if g == base_name + t:
#download
try:
urllib.urlretrieve("ftp://ftp.ncbi.nlm.nih.gov/{}/{}".format(ftp.pwd(), g), path+g)
except IOError:
print('No proteomic file availlable for : {}'.format(g))
return False
urllib.urlcleanup()
#extract
with gzip.open(path+g, 'rb') as f_in:
out = path+g.replace('.gz','')
with open(out, 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
#remove file
os.remove(path+g)
return out
def map_types_to_file_suffix(types):
"""
from https://github.com/ctSkennerton/scriptShed/blob/master/download_ncbi_assembly.py
Return a list of the NCBI type suffix file
input:
type (list) : List of type
output
List of NCBI type suffix file
"""
mapping = {'fna': '_genomic.fna.gz',
'faa': '_protein.faa.gz',
'ffn': '_cds_from_genomic.fna.gz',
'gb': '_genomic.gbff.gz',
'gff': '_genomic.gff.gz'
}
return [mapping[i] for i in types]
def download_genome(taxid, df_refseq, df_euk, df_prok):
"""
Download the Refseq Genome Taxid
If no refseq Download all the proteome for each assembly
input:
taxid (list) : list of taxid
df_refseq (DataFrame) : pandas DataFrame of the RefSeq Gneome
df_euk (DataFrame) : pandas DataFrame of the eukaryotes genomes
df_prok (DataFrame) : pandas DataFrame of the prokaryotes genomes
output:
Path of the proteome for each assembly of each taxid in fasta
"""
#get the taxid in the refseq genomes
set1 = set(taxid)
#get the reference genome by the given taxid
df_selection = df_refseq.loc[df_refseq['taxid'].isin(taxid)]
#convert the taxid into a set (can be have more than 1 assembly in ref seq for 1 taxid)
set2 = set(df_selection['taxid'].values.tolist())
#check if all the given taxid are in the refseq genome taxid
diff = set1.difference(set2)
PATH_LIST = list()
#check if the dataframe is empty
if not df_selection.empty :
#not empty (but can not contain all taxid)
#get the FTP path and download the genome
list_dict = df_selection.to_dict(orient='records')
taxid_list = df_selection['taxid'].values.tolist()
for d in list_dict:
#make link
path = d['ftp_path']
root = path.split('/')[-1]
f1 = path+"/"+root+'_protein.faa.gz'
org = d['organism_name']
strain = d['# assembly_accession']
print('Downloading {} - {} ...'.format(org,strain))
f2 = os.path.join(os.getcwd(),org.upper().replace(' ','_'),root+'_protein.faa.gz')
PATH_LIST += [f2.replace('.gz','')]
#create directory
if os.path.isdir(os.path.join(os.getcwd(),org.upper().replace(' ','_'))) == False:
os.mkdir(os.path.join(os.getcwd(),org.upper().replace(' ','_')))
#download
urllib.urlretrieve(f1, f2)
#extract
with gzip.open(f2, 'rb') as f_in:
with open(f2.replace('.gz',''), 'wb') as f_out:
shutil.copyfileobj(f_in, f_out)
#remove file
os.remove(f2)
#if df_selection dont have all taxid
if diff:
GCA_list = list()
org_list = list()
ftp_list = list()
df_selection_euk = df_euk.loc[df_euk['TaxID'].isin(diff)]
#eukaryotes.txt dont have same header as the prokaryote.txt, prokaryote have 'Strain', 'Pubmed ID', 'FTP Path', 'Reference' in more
if not df_selection_euk.empty :
GCA_list += df_selection_euk['Assembly Accession'].values.tolist()
org_list += df_selection_euk['#Organism/Name'].values.tolist()
ftp_list += [False] * len(df_selection_euk.index)
df_selection_prok = df_prok.loc[df_prok['TaxID'].isin(diff)]
if not df_selection_prok.empty :
GCA_list += df_selection_prok['Assembly Accession'].values.tolist()
org_list += df_selection_prok['#Organism/Name'].values.tolist()
ftp_list += df_selection_prok['FTP Path'].values.tolist()
GCA_ORG_list = zip(GCA_list, org_list, ftp_list)
if GCA_ORG_list:
#from : https://github.com/ctSkennerton/scriptShed/blob/master/download_ncbi_assembly.py
#Connection to the FTP server of NCBI - get only faa protein file
types = map_types_to_file_suffix(['faa'])
ftp = ftplib.FTP()
ftp.connect('ftp.ncbi.nlm.nih.gov')
ftp.login(user='anonymous',passwd='your.email@gmail.com')
for accession, organism, ftp_true in GCA_ORG_list:
#create folder
path = os.path.join(os.getcwd(),organism.upper().replace(' ','_'),'')
if os.path.isdir(path) == False:
os.mkdir(path)
prefix, accp, version = acc_to_ftp_path(accession)
base_path = "genomes/all/{}/{}".format(prefix,accp)
ftp.cwd(base_path)
for f in ftp.nlst():
if accession in f:
ftp.cwd(f)
out = get_files_from_types(types, f, ftp, path, ftp_true=ftp_true)
if out:
PATH_LIST += [out]
ftp.cwd("/")
else:
print('No proteome found for the choosen node or taxid, abort')
return PATH_LIST
def make_blastdb(PATH_LIST):
"""
Make the BLAST Database for each PFAM fasta file
"""
for i in PATH_LIST:
if FLAG:
CREATE_NO_WINDOW = 0x08000000
print("Make BLAST DB for {}".format(os.path.basename(i)))
a = subprocess.call('makeblastdb -in {} -dbtype prot'.format(i), creationflags=CREATE_NO_WINDOW)
else:
print("Make BLAST DB for {}".format(os.path.basename(i)))
a = subprocess.call('makeblastdb -in {} -dbtype prot'.format(i), shell=True)
def split_fasta(fasta):
"""
input : fasta file complete path
output : create individual file with the fasta sequence
"""
FASTA_PATH = list()
path, fasta_filename = os.path.split(fasta)
folder_name = fasta_filename.split('.')[0]
if os.path.isdir(os.path.join(path,folder_name+'_fasta')) == False:
os.mkdir(os.path.join(path,folder_name+'_fasta'))
for records in SeqIO.parse(fasta,'fasta'):
iD = records.id
seq = str(records.seq)
fasta = os.path.join(path,folder_name+'_fasta',iD.replace('.','_')+'.fasta')
FASTA_PATH += [fasta]
with open(fasta,"w") as f:
f.write('>'+records.description+'\n')
f.write(seq+'\n')
return FASTA_PATH
def blast(FASTA, PFAM, OUT):
"""
Make a blast with a evalue of 10000
FASTA = the path to FASTA file
PFAM = The BLAST DB PFAM Database (protein)
OUT = Output blast repport in XML format (outfmt = 5)
"""
size = False
cpt = 0
while size == False:
blastp_cline = NcbiblastpCommandline(query=FASTA, db=PFAM, evalue=10000,outfmt=5, out=OUT)
cmd = str(blastp_cline)
if FLAG:
CREATE_NO_WINDOW = 0x08000000
a = subprocess.call(cmd, creationflags=CREATE_NO_WINDOW)
else:
a = subprocess.call(cmd, shell=True)
#check the size
#if the file size is not correct the while loop will continue
if os.stat(OUT).st_size != 0:
break
cpt +=1
if cpt == 100:
print('Trying 100 iteration, not working, exit for '+FASTA)
###########
# RUNNING #
###########
def main():
parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter,
description=textwrap.dedent('''
Welcome to PyFuncover !
Python Function Uncover ( PyFuncover ) is a new bioinformatic tool
able to search for protein with a specific function in a full proteome.
The pipeline coded in python uses BLAST alignment and the sequences from
a PFAM family as search seed.
=== REQUIREMENT ===
BLAST
Python dependancies : BioPython, Numpy, Matplotlib, Pandas
USAGE :
python PyFuncover.py -taxid [TAXID ...] -pfam [PFAM ...] --db [DB ...] --out [OUT]
python PyFuncover.py --update
TO UPDATE THE DATABASES :
python PyFuncover.py --update
=== OBLIGATORY ARGUMENTS : ===
-pfam : List of PFAM familly ID : PF####
each separated by a blank space
PyFuncover.py -pfam PF14651 PF#### ...
-taxid: The list of TaxID for each organism you want to download a proteome
Each separated by a space (for example Human and Yeast (S299C) taxid)
PyFuncover.py -taxid 9606 559292
Can be a Taxid that represent a node in the phylogenetic tree
(Eukaryotes : 2759 ; Insecta : 50557, ...)
He will retrieve all availlable assembly for them
=== OPTIONAL : ===
--update :
Download the last release of the NCBI Taxonomic Database
Download the last RefSeq, Prokaryote and Eukaryote Genome Assembly List
PyFuncover.py --update
--out : Filename output
Format are in CSV format (pandas.to_csv output)
Default : result.csv
--db : The list of choosen cross-ref number to retrieve data from bioDBnet database :
default : 137 47 48 49 (UNIPROT ID, GO-TERMs Databases)
WARNING ! : Too high number of requested cross-refs will occur a slow-mode request 1 by 1.
If it get an error for 1 request with 1 protein in the mode 1 by 1,
the program will ABORT with a too high number of choosen cross-ref choosen exception !
1 : 'Affy ID',
2 : 'Agilent ID',
3 : 'Allergome Code',
4 : 'ApiDB_CryptoDB ID',
5 : 'Biocarta Pathway Name',
6 : 'BioCyc ID',
7 : 'CCDS ID',
8 : 'Chromosomal Location',
9 : 'CleanEx ID',
10 : 'CodeLink ID',
11 : 'COSMIC ID',
12 : 'CPDB Protein Interactor',
13 : 'CTD Disease Info',
14 : 'CTD Disease Name',
15 : 'CYGD ID',
16 : 'dbSNP ID',
17 : 'dictyBase ID',
18 : 'DIP ID',
19 : 'DisProt ID',
20 : 'DrugBank Drug ID',
21 : 'DrugBank Drug Info',
22 : 'DrugBank Drug Name',
23 : 'EC Number',
24 : 'EchoBASE ID',
25 : 'EcoGene ID',
26 : 'Ensembl Biotype',
27 : 'Ensembl Gene ID',
28 : 'Ensembl Gene Info',
29 : 'Ensembl Protein ID',
30 : 'Ensembl Transcript ID',
31 : 'FlyBase Gene ID',
32 : 'FlyBase Protein ID',
33 : 'FlyBase Transcript ID',
34 : 'GAD Disease Info',
35 : 'GAD Disease Name',
36 : 'GenBank Nucleotide Accession',
37 : 'GenBank Nucleotide GI',
38 : 'GenBank Protein Accession',
39 : 'GenBank Protein GI',
40 : 'Gene ID',
41 : 'Gene Info',
42 : 'Gene Symbol',
43 : 'Gene Symbol and Synonyms',
44 : 'Gene Symbol ORF',
45 : 'Gene Synonyms',
46 : 'GeneFarm ID',
47 : 'GO - Biological Process',
48 : 'GO - Cellular Component',
49 : 'GO - Molecular Function',
50 : 'GO ID',
51 : 'GSEA Standard Name',
52 : 'H-Inv Locus ID',
53 : 'HAMAP ID',
54 : 'HGNC ID',
55 : 'HMDB Metabolite',
56 : 'Homolog - All Ens Gene ID',
57 : 'Homolog - All Ens Protein ID',
58 : 'Homolog - All Gene ID',
59 : 'Homolog - Human Ens Gene ID',
60 : 'Homolog - Human Ens Protein ID',
61 : 'Homolog - Human Gene ID',
62 : 'Homolog - Mouse Ens Gene ID',
63 : 'Homolog - Mouse Ens Protein ID',
64 : 'Homolog - Mouse Gene ID',
65 : 'Homolog - Rat Ens Gene ID',
66 : 'Homolog - Rat Ens Protein ID',
67 : 'Homolog - Rat Gene ID',
68 : 'HomoloGene ID',
69 : 'HPA ID',
70 : 'HPRD ID',
71 : 'HPRD Protein Complex',
72 : 'HPRD Protein Interactor',
73 : 'Illumina ID',
74 : 'IMGT/GENE-DB ID',
75 : 'InterPro ID',
76 : 'IPI ID',
77 : 'KEGG Disease ID',
78 : 'KEGG Gene ID',
79 : 'KEGG Orthology ID',
80 : 'KEGG Pathway ID',
81 : 'KEGG Pathway Info',
82 : 'KEGG Pathway Title',
83 : 'LegioList ID',
84 : 'Leproma ID',
85 : 'Locus Tag',
86 : 'MaizeGDB ID',
87 : 'MEROPS ID',
88 : 'MGC(ZGC/XGC) ID',
89 : 'MGC(ZGC/XGC) Image ID',
90 : 'MGC(ZGC/XGC) Info',
91 : 'MGI ID',