annotate cravat_submit.py @ 0:7ebdd4ac13a2 draft

Uploaded

1 import requests
2 import json
3 import time
4 import urllib
5 import sys
6 import csv
7 import re
8 
9 try:
10     input_filename = sys.argv[1]
11     input_select_bar = sys.argv[2]
12     GRCh_build = sys.argv[3]
13     psm_filename = sys.argv[4]
14     output_filename = sys.argv[5]
15     file_3 = sys.argv[6]
16     file_4 = sys.argv[7]
17     file_5 = sys.argv[8]
18 except:
19     input_filename = '1.) Galaxy2-[Human_Vcf_MCF7]-minimum.vcf'
20     input_filename = 'input/[tgriffin_cguerrer_20160726_MCF7_RNAseq_01_S13_R1_001.vcf].vcf'
21     input_select_bar = 'VEST'
22     GRCh_build = 'GRCh38'
23     output_filename = 'combined_variants.tsv'
24     psm_filename = 'input/[ERLIC_MCF7_110kb_R123-CustomProDB_RNA-Seq_cRAP_DB.psm-report].tabular'
25     file_3 = 'output/' + time.strftime("%H:%M") + '_Z_Gene_Level_Analysis.tsv'
26     file_4 = 'output/' + time.strftime("%H:%M") + '_Z_Variant_Non-coding.Result.tsv'
27     file_5 = 'output/' + time.strftime("%H:%M") + '_Z_Input_Errors.Result.tsv'
28 
29 
30 #in_file = open('input_call.txt', "r")    
31 #out_file = open('output_call.txt', "w")
32 
33 write_header = True
34 
35 GRCh37hg19 = 'off'
36 if GRCh_build == 'GRCh37':
37     GRCh37hg19 = 'on'
38 
39 # http://staging.cravat.us/CRAVAT/rest/service/submit:
40 
41 #plugs in params to given URL
42 submit = requests.post('http://staging.cravat.us/CRAVAT/rest/service/submit', files={'inputfile':open(input_filename)}, data={'email':'[e-mail]', 'analyses': input_select_bar, 'hg19': GRCh37hg19})
43 
44 #Makes the data a json dictionary, takes out only the job ID
45 jobid = json.loads(submit.text)['jobid']
46 #out_file.write(jobid)    
47 submitted = json.loads(submit.text)['status']
48 #out_file.write('\t' + submitted)
49 
50 input_file = open(input_filename)
51 is_comment_line = re.compile(".*#+.*")
52 
53 
54 #loops until we find a status equal to Success, then breaks
55 while True:
56     check = requests.get('http://staging.cravat.us/CRAVAT/rest/service/status', params={'jobid': jobid})
57     status = json.loads(check.text)['status']
58     resultfileurl = json.loads(check.text)['resultfileurl']
59     #out_file.write(str(status) + ', ')
60     if status == 'Success':
61         #out_file.write('\t' + resultfileurl)
62         break
63     else:
64         time.sleep(2)
65 
66 #out_file.write('\n')
67 
68 #creates three files
69 file_1 = time.strftime("%H:%M") + '_Z_Variant_Result.tsv'
70 file_2 = time.strftime("%H:%M") + '_Z_Additional_Details.tsv'
71 #file_3 = time.strftime("%H:%M") + 'Combined_Variant_Results.tsv'
72 
73 #Download the two results
74 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant.Result.tsv", file_1)
75 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant_Additional_Details.Result.tsv", file_2)
76 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Gene_Level_Analysis.Result.tsv", file_3)
77 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Variant_Non-coding.Result.tsv", file_4)
78 urllib.urlretrieve("http://staging.cravat.us/CRAVAT/results/" + jobid + "/" + "Input_Errors.Result.tsv", file_5)
79 
80 headers = []
81 duplicates = []
82 
83 #opens the Variant Result file and the Variant Additional Details file as csv readers, then opens the output file (galaxy) as a writer
84 with open(file_1) as tsvin_1, open(file_2) as tsvin_2, open(output_filename, 'wb') as tsvout:
85     tsvreader_1 = csv.reader(tsvin_1, delimiter='\t')
86     tsvreader_2 = csv.reader(tsvin_2, delimiter='\t')
87     
88     tsvout = csv.writer(tsvout, delimiter='\t')
89 
90     # Processes the PSM report
91     if (psm_filename != 'None'):
92         tsvin_3 = open(psm_filename)
93         psmreader = csv.reader(tsvin_3, delimiter='\t')
94         
95         psmreader.next()
96         peptide_map = {}
97         s = re.compile('[A-Z][0-9]+[A-Z]')
98         for row in psmreader:
99             pro_name = row[1]
00             pep_seq = row[2]
01             
02             prot_seq_changes = s.findall(pro_name)
03         
04             for change in prot_seq_changes:
05                 if change in peptide_map:
06                     if pep_seq not in peptide_map[change].split(';'):
07                         peptide_map[change] = peptide_map[change] + ';' + pep_seq
08                 else:
09                     peptide_map[change] = pep_seq
10     
11     #loops through each row in the Variant Additional Details file
12 
13     print 'Checkpoint 3'
14     for row in tsvreader_2:
15         #sets row_2 equal to the same row in Variant Result file
16         row_2 = tsvreader_1.next()
17         #checks if row is empty or if the first term contains '#'
18         if row == [] or row[0][0] == '#':
19             tsvout.writerow(row)
20         else:
21         #checks if the row begins with input line
22             if row[0] == 'Input line':
23                 #Goes through each value in the headers list in VAD
24                 #print 'Original row'
25                 #print row
26                 #print row_2
27                 for value in row:   
28                     #Adds each value into headers 
29                     headers.append(value)
30                 #Loops through the Keys in VR
31                 for value in row_2:
32                     #Checks if the value is already in headers
33                     if value in headers:
34                         continue
35                     #else adds the header to headers
36                     else:
37                         headers.append(value)
38                 if (psm_filename != 'None'):
39                     headers.insert(1, 'Peptide')
40                 #print headers
41                 tsvout.writerow(headers)
42             else:
43                 
44                 cells = []
45                 #Inserts a peptide column into the row
46                 if (psm_filename != 'None'):
47                     if row[12] in peptide_map:
48                         row.insert(1, peptide_map[row[12]])
49                     else:
50                         row.insert(1, '')
51                     
52                 #Goes through each value in the next list
53                 for i,value in enumerate(row):
54                     #adds it to cells
55                     cells.append(value)
56                 #Goes through each value from the VR file after position 11 (After it is done repeating from VAD file)
57                 for i,value in enumerate(row_2[11:]):
58                     #adds in the rest of the values to cells
59 
60                     # Skips the 2nd VEST p-value
61                     if (i != 49 - 11):
62                         cells.append(value)
63                     
64                 print  cells
65                 tsvout.writerow(cells)
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 #a = 'col1\tcol2\tcol3'
97 #header_list = a.split('\t')
98 
99 #loop through the two results, when you first hit header you print out the headers in tabular form
00 #Print out each header only once
01 #Combine both headers into one output file
02 #loop through the rest of the data and assign each value to its assigned header
03 #combine this all into one output file
04 
05 
06 
07 
08