Mercurial > repos > in_silico > cravat_score_and_annotate
comparison cravat_score_and_annotate-9c6b7291c4e6/cravat_submit.py @ 2:cdd97b06c802 draft
Uploaded
author | in_silico |
---|---|
date | Wed, 19 Jul 2017 14:58:50 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
1:9c6b7291c4e6 | 2:cdd97b06c802 |
---|---|
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 #in_file = open('input_call.txt', "r") | |
13 #out_file = open('output_call.txt', "w") | |
14 | |
15 write_header = True | |
16 | |
17 #plugs in params to given URL | |
18 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}) | |
19 #,'analysis':input_select_bar,'functionalannotation': "on"}) | |
20 #Makes the data a json dictionary, takes out only the job ID | |
21 jobid = json.loads(submit.text)['jobid'] | |
22 #out_file.write(jobid) | |
23 submitted = json.loads(submit.text)['status'] | |
24 #out_file.write('\t' + submitted) | |
25 | |
26 #loops until we find a status equal to Success, then breaks | |
27 while True: | |
28 check = requests.get('http://staging.cravat.us/CRAVAT/rest/service/status', params={'jobid': jobid}) | |
29 status = json.loads(check.text)['status'] | |
30 resultfileurl = json.loads(check.text)['resultfileurl'] | |
31 #out_file.write(str(status) + ', ') | |
32 if status == 'Success': | |
33 #out_file.write('\t' + resultfileurl) | |
34 break | |
35 else: | |
36 time.sleep(2) | |
37 | |
38 #out_file.write('\n') | |
39 | |
40 #creates three files | |
41 file_1 = time.strftime("%H:%M") + '_Z_Variant_Result.tsv' | |
42 file_2 = time.strftime("%H:%M") + '_Z_Additional_Details.tsv' | |
43 file_3 = time.strftime("%H:%M") + 'Combined_Variant_Results.tsv' | |
44 | |
45 | |
46 #Download the two results | |
47 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant.Result.tsv", file_1) | |
48 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant_Additional_Details.Result.tsv", file_2) | |
49 | |
50 headers = [] | |
51 duplicates = [] | |
52 | |
53 #opens the Variant Result file and the Variant Additional Details file as csv readers, then opens the output file (galaxy) as a writer | |
54 with open(file_1) as tsvin_1, open(file_2) as tsvin_2, open(output_filename, 'wb') as tsvout: | |
55 tsvreader_1 = csv.reader(tsvin_1, delimiter='\t') | |
56 tsvreader_2 = csv.reader(tsvin_2, delimiter='\t') | |
57 tsvout = csv.writer(tsvout, delimiter='\t') | |
58 | |
59 #loops through each row in the Variant Additional Details file | |
60 for row in tsvreader_2: | |
61 #sets row_2 equal to the same row in Variant Result file | |
62 row_2 = tsvreader_1.next() | |
63 #checks if row is empty or if the first term contains '#' | |
64 if row == [] or row[0][0] == '#': | |
65 continue | |
66 #checks if the row begins with input line | |
67 if row[0] == 'Input line': | |
68 #Goes through each value in the headers list in VAD | |
69 for value in row: | |
70 #Adds each value into headers | |
71 headers.append(value) | |
72 #Loops through the Keys in VR | |
73 for value in row_2: | |
74 #Checks if the value is already in headers | |
75 if value in headers: | |
76 continue | |
77 #else adds the header to headers | |
78 else: | |
79 headers.append(value) | |
80 | |
81 print headers | |
82 tsvout.writerow(headers) | |
83 | |
84 | |
85 else: | |
86 | |
87 cells = [] | |
88 #Goes through each value in the next list | |
89 for value in row: | |
90 #adds it to cells | |
91 cells.append(value) | |
92 #Goes through each value from the VR file after position 11 (After it is done repeating from VAD file) | |
93 for value in row_2[11:]: | |
94 #adds in the rest of the values to cells | |
95 cells.append(value) | |
96 | |
97 print cells | |
98 tsvout.writerow(cells) | |
99 | |
100 | |
101 | |
102 | |
103 | |
104 | |
105 | |
106 | |
107 | |
108 | |
109 | |
110 | |
111 | |
112 | |
113 | |
114 | |
115 | |
116 | |
117 | |
118 | |
119 | |
120 | |
121 | |
122 #a = 'col1\tcol2\tcol3' | |
123 #header_list = a.split('\t') | |
124 | |
125 #loop through the two results, when you first hit header you print out the headers in tabular form | |
126 #Print out each header only once | |
127 #Combine both headers into one output file | |
128 #loop through the rest of the data and assign each value to its assigned header | |
129 #combine this all into one output file | |
130 | |
131 | |
132 | |
133 | |
134 |