Mercurial > repos > charles_s_test > seqsero2

comparison run_seqsero_batch_galaxy.py @ 0:6895de35a263 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 844a891e4eaf732830043204ac636907eefb011d-dirty
author charles_s_test
date Thu, 19 Oct 2017 18:16:51 -0400
parents
children 0d65b71ff8df
comparison
equal deleted inserted replaced
-1:000000000000 0:6895de35a263
1 #!/usr/bin/python
2
3 print 'monkey wonders where he is'
4
5 import os
6
7 # os.system('source /nfs/sw/apps/galaxy-dev/galaxy/.venv/bin/activate')
8
9 import re, sys, time, datetime
10 import subprocess, psycopg2, sqlalchemy
11 from subprocess import Popen, PIPE
12 from sqlalchemy import *
13 from datetime import datetime
14
15 print 'monkey found some files', sys.argv
16 engine = create_engine('postgresql+psycopg2://galaxy:cF$cl0udh9c@galaxyprod.cvkyaz9id4ml.us-east-1.rds.amazonaws.com:5432/galaxy')
17 print 'monkey says "vroom vroom"'
18 connection = engine.connect()
19 print "monkey made a connection!"
20
21 # database = '/nfs/sw/apps/galaxy-dev/galaxy/database/universe.sqlite'
22 seqsero = '/nfs/sw/apps/galaxy-dev/galaxy/tools/seqsero/SeqSero.py'
23 test_out = open("/nfs/sw/apps/galaxy-dev/galaxy/tools/seqsero/test.txt", 'w')
24 out_path = '/nfs/sw/apps/galaxy-dev/galaxy/database/files/000'
25 test_out2 = open("/nfs/sw/apps/galaxy-dev/galaxy/tools/seqsero/test2.txt", 'w')
26
27 path2sample = '/nfs/sw/apps/galaxy-dev/galaxy/tools/seqsero/fastq_tmp'
28
29 test_out.write("monkey ");
30 test_out.write("\t".join(sys.argv)+'\n')
31
32 fq_list1 = []
33
34 test_out.write(str(len(sys.argv))+"\n")
35 if len(sys.argv) >= 2:
36 test_out.write("\t".join(sys.argv)+'\n')
37 fq_list1 = sys.argv[1:]
38
39 test_out.write(str(len(sys.argv))+"\n")
40
41 fastq_files = re.split(",", fq_list1[0]) # fq_list1[0] is a string with commas between the path/filenames.
42
43 def print_time():
44 test_out.write(time.asctime( time.localtime(time.time())))
45
46 tmp_path = path2sample
47 if not os.path.exists(tmp_path):
48 os.system('mkdir '+tmp_path)
49
50 test_out.write(str(len(fastq_files))+"\n")
51
52 def list_runs(fastq_files):
53 '''
54 Creates dict with runs as keys and list with filenames as values.
55 '''
56 run2fastqs = {}
57 is_fastq = 'yes'
58 for file in fastq_files:
59 print 'monkey found', file
60 run = ''
61 try:
62 fastq = open(file, 'r')
63 i = 0
64 for line in fastq:
65 line = line.rstrip("\n")
66 if i == 0:
67 run = re.split("\s", line)[0]
68 run = re.sub('@', '', run)
69 run = re.split("\.", run)[0]
70 if not re.search('^@', line):
71 is_fastq = 'no'
72 else:
73 break
74 i += 1
75 file1 = re.split('/', file)[-1]
76 dataset_id = re.split('_', file1)
77 dataset_id = re.sub('.dat', '', dataset_id[-1])
78 print dataset_id, type(dataset_id)
79 result = connection.execute('SELECT name FROM history_dataset_association WHERE dataset_id = '+dataset_id+';')
80 original_filename = ''
81 for row in result:
82 print 'monkey says the original_filename is something like', row[0]
83 original_filename = row[0]
84 if re.search('fasta$', original_filename):
85 if is_fastq == 'yes':
86 original_filename = re.sub('fasta', 'fastq', original_filename)
87 else:
88 print 'The input file is not a fastq file.'
89 file2 = re.sub('.dat$', '_'+original_filename, file1)
90 print 'monkey renamed the file', file2
91 new_path_file = tmp_path+'/'+file2
92 if file2 not in os.listdir(tmp_path):
93 print file, new_path_file
94 os.system('cp '+file+' '+new_path_file)
95 if run in run2fastqs.keys():
96 if file not in run2fastqs[run]:
97 run2fastqs[run].append(new_path_file)
98 else:
99 run2fastqs[run] = [new_path_file]
100 except IOError:
101 print "Data not found. It is possible for a deleted file to still be listed "\
102 "in a Galaxy library. Please confirm that the data still exists on this "\
103 "server. You may need to upload it again."
104 return run2fastqs
105
106 def run_seqsero(run2fastqs):
107 '''
108 Takes files from run2fastqs and runs SeqSero.
109 '''
110 outputs = []
111 for run in run2fastqs:
112 print run, run2fastqs[run]
113 seqsero_cmd = []
114 if len(run2fastqs[run]) == 2:
115 seqsero_cmd = ['python', seqsero, '-m', '2', '-i', run2fastqs[run][0], run2fastqs[run][1]]
116 elif len(run2fastqs[run]) == 1:
117 seqsero_cmd = ['python', seqsero, '-m', '1', '-i', run2fastqs[run][0]]
118 print seqsero_cmd
119 p = Popen(seqsero_cmd, stdout=PIPE)
120 output = p.communicate()
121 outputs.append(output)
122 return outputs
123
124 def get_serotypes(outputs):
125 '''
126 '''
127 fastq2comment = {}
128 fastq2serotype = {}
129 for sample in outputs:
130 fastqs = ''
131 lines_used = []
132 for line in sample: # line is actually the entire seqsero output.
133 line = str(line)
134 linel = re.split("\n", line)
135 # print linel
136 #lines_used = []
137 for element in linel: # element is a line of seqsero output.
138 element = element.rstrip("\n")
139 test_out.write(element+"\n")
140 elementl = re.split("\t", element)
141 if elementl[0] == 'Input files:':
142 fastqs = elementl[1]
143 lines_used.append(element)
144 if elementl[1] not in fastq2serotype.keys():
145 fastq2serotype[fastqs] = ['']*5
146 fastq2comment[fastqs] = []
147 elif elementl[0] == 'O antigen prediction:':
148 lines_used.append(element)
149 fastq2serotype[fastqs][0] = elementl[1] # add predicted profile
150 elif elementl[0] == 'H1 antigen prediction(fliC):':
151 lines_used.append(element)
152 fastq2serotype[fastqs][1] = elementl[1] # add predicted profile
153 elif elementl[0] == 'H2 antigen prediction(fljB):':
154 lines_used.append(element)
155 fastq2serotype[fastqs][2] = elementl[1] # add predicted profile
156 elif elementl[0] == 'Predicted antigenic profile:':
157 lines_used.append(element)
158 fastq2serotype[fastqs][3] = elementl[1] # add predicted profile
159 elif elementl[0] == 'Predicted serotype(s):':
160 lines_used.append(element)
161 fastq2serotype[fastqs][4] = elementl[1] # add predicted serotype
162 if element not in lines_used and re.search("\w", fastqs) and len(element) > 7:
163 fastq2comment[fastqs].append(element)
164 #print "\n"
165 return fastq2serotype, fastq2comment
166
167 def print_html(fastq2serotype, fastq2comment):
168 '''
169 Takes dict and prints to html file.
170 '''
171 tab_out = open('Seqsero_result.txt', 'w');
172 html_out = open('Seqsero_result.html', 'w')
173 html_out.write('<!DOCTYPE html>\n')
174 html_out.write('<html>\n')
175 html_out.write('<head>\n')
176 html_out.write('<title>SeqSero Results</title>\n')
177 html_out.write('</head>\n')
178 html_out.write('<body>\n')
179 html_out.write('<body style="font-family:Helvetica;">\n')
180 html_out.write('<p style="font-size:10px">\n')
181 html_out.write('<table border=1>\n')
182 header = 'Input Files\tO antigen prediction\tH1 antigen prediction(fliC)\tH2 antigen prediction(fljB)\tPredicted antigenic profile\tPredicted serotype(s)'
183 header = re.sub(' ', '_', header)
184 header_l = ['Input Files', 'O antigen prediction', 'H1 antigen prediction(fliC)', 'H2 antigen prediction(fljB)', 'Predicted antigenic profile', 'Predicted serotype(s)']
185 html_out.write('<tr>\n')
186 for element in header_l:
187 html_out.write('<td>'+element+'</td>\n')
188 html_out.write('</tr>\n')
189 tab_out.write(header+"\n")
190 print "\n\n", header
191 for fastq in fastq2serotype:
192 # print fastq, fastq2serotype[fastq]
193 line_to_print = fastq+'\t'+"\t".join(fastq2serotype[fastq])
194 tab_out.write(line_to_print+"\n")
195 html_out.write('<tr>\n')
196 html_out.write('<td>'+fastq+'</td>\n')
197 for antigen in fastq2serotype[fastq]:
198 html_out.write('<td>'+antigen+'</td>\n')
199 html_out.write('</tr>\n')
200 print line_to_print
201 html_out.write('</table>\n')
202 print "\n"
203 for fastq in fastq2comment:
204 tab_out.write("\n"+fastq+"\n")
205 html_out.write('<tr>\n')
206 html_out.write('<p>\n')
207 html_out.write('<td>'+fastq+"<br></td>\n")
208 for line in fastq2comment[fastq]:
209 #if len(line) > 7:
210 html_out.write('<td>'+line+'</td>\n')
211 tab_out.write(line+"\n")
212 print line
213 print "\n"
214 html_out.write('</p>\n')
215 html_out.write('</tr>\n')
216 html_out.write('</body>\n')
217 html_out.write('</html>\n')
218 html_out.close()
219
220 run2fastqs = list_runs(fastq_files)
221 #print run2fastqs
222 outputs = run_seqsero(run2fastqs)
223 fastq2serotype, fastq2comment = get_serotypes(outputs)
224 print_html(fastq2serotype, fastq2comment)
225 print_time()
226
227