Mercurial > repos > in_silico > cravat_vcf_convert

comparison cravat_submit/cravat_submit.py @ 11:338d106513fd draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author in_silico
date Tue, 12 Jun 2018 12:06:54 -0400
parents
children
comparison
equal deleted inserted replaced
10:e6c1dc59a01f 11:338d106513fd
1 import requests
2 import json
3 import time
4 import urllib
5 import sys
6 import csv
7
8 input_filename = sys.argv[1]
9 input_select_bar = sys.argv[2]
10 output_filename = sys.argv[3]
11
12 # HACK: Input args corrections.
13 if input_select_bar == "None":
14 # The server represents an analyses of None as ""; however, submitting a blank string on command line throws off arg position
15 input_select_bar = ""
16 # The server represents the "Vest and Chasm" analyses as "VEST;CHASM; however, galaxy converts the semi-colon to an 'X'. Switch it back.
17 elif input_select_bar == "VESTXCHASM":
18 input_select_bar = "VEST;CHASM"
19
20 write_header = True
21
22 #plugs in params to given URL
23 submit = requests.post('http://staging.cravat.us/CRAVAT/rest/service/submit', files={'inputfile':open(input_filename)}, data={'email':'znylund@insilico.us.com', 'analyses': input_select_bar})
24 #,'analysis':input_select_bar,'functionalannotation': "on"})
25 #Makes the data a json dictionary, takes out only the job ID
26 jobid = json.loads(submit.text)['jobid']
27 #out_file.write(jobid)
28 submitted = json.loads(submit.text)['status']
29 #out_file.write('\t' + submitted)
30
31 #loops until we find a status equal to Success, then breaks
32 while True:
33 check = requests.get('http://staging.cravat.us/CRAVAT/rest/service/status', params={'jobid': jobid})
34 status = json.loads(check.text)['status']
35 resultfileurl = json.loads(check.text)['resultfileurl']
36 #out_file.write(str(status) + ', ')
37 if status == 'Success':
38 #out_file.write('\t' + resultfileurl)
39 break
40 else:
41 time.sleep(2)
42
43 #out_file.write('\n')
44
45 #creates three files
46 file_1 = time.strftime("%H:%M") + '_Z_Variant_Result.tsv'
47 file_2 = time.strftime("%H:%M") + '_Z_Additional_Details.tsv'
48 file_3 = time.strftime("%H:%M") + 'Combined_Variant_Results.tsv'
49
50
51 #Download the two results
52 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant.Result.tsv", file_1)
53 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant_Additional_Details.Result.tsv", file_2)
54
55 headers = []
56 duplicates = []
57
58 #opens the Variant Result file and the Variant Additional Details file as csv readers, then opens the output file (galaxy) as a writer
59 with open(file_1) as tsvin_1, open(file_2) as tsvin_2, open(output_filename, 'wb') as tsvout:
60 tsvreader_1 = csv.reader(tsvin_1, delimiter='\t')
61 tsvreader_2 = csv.reader(tsvin_2, delimiter='\t')
62 tsvout = csv.writer(tsvout, delimiter='\t')
63
64 #loops through each row in the Variant Additional Details file
65 for row in tsvreader_2:
66 #sets row_2 equal to the same row in Variant Result file
67 row_2 = tsvreader_1.next()
68 #checks if row is empty or if the first term contains '#'
69 if row == [] or row[0][0] == '#':
70 continue
71 #checks if the row begins with input line
72 if row[0] == 'Input line':
73 #Goes through each value in the headers list in VAD
74 for value in row:
75 #Adds each value into headers
76 headers.append(value)
77 #Loops through the Keys in VR
78 for value in row_2:
79 #Checks if the value is already in headers
80 if value in headers:
81 continue
82 #else adds the header to headers
83 else:
84 headers.append(value)
85
86 print headers
87 tsvout.writerow(headers)
88
89
90 else:
91
92 cells = []
93 #Goes through each value in the next list
94 for value in row:
95 #adds it to cells
96 cells.append(value)
97 #Goes through each value from the VR file after position 11 (After it is done repeating from VAD file)
98 for value in row_2[11:]:
99 #adds in the rest of the values to cells
100 cells.append(value)
101
102 print cells
103 tsvout.writerow(cells)