Mercurial > repos > charles_s_test > seqsero2

comparison run_seqsero.py @ 9:acc5cd06a36a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit a4fb57231f274270afbfebd47f67df05babffa4a-dirty
author charles_s_test
date Tue, 28 Nov 2017 21:16:36 -0500
parents 3d6680af0bec
children 53efef402c51
comparison
equal deleted inserted replaced
8:b04931a9fe71 9:acc5cd06a36a
105 return outputs 105 return outputs
106 106
107 def get_serotypes(outputs): 107 def get_serotypes(outputs):
108 ''' 108 '''
109 ''' 109 '''
110 fastq2comment = {} 110 fastq2comment = {}
111 fastq2serotype = {} 111 fastq2serotype = {}
112
112 for sample in outputs: 113 for sample in outputs:
113 fastqs = '' 114 fastqs = ''
114 lines_used = [] 115 lines_used = []
115 for line in sample: # line is actually the entire seqsero output. 116 for line in sample: # line is actually the entire seqsero output.
116 line = str(line) 117 line = str(line)
117 linel = re.split("\n", line) 118 linel = re.split("\n", line)
118 # print(linel) 119 # print(linel)
119 #lines_used = [] 120 #lines_used = []
120 for element in linel: # element is a line of seqsero output. 121 for element in linel: # element is a line of seqsero output.
121 element = element.rstrip("\n") 122 element = element.rstrip("\n")
122 test_out.write(element+"\n") 123 test_out.write(element+"\n")
123 elementl = re.split("\t", element) 124 elementl = re.split("\t", element)
124 if elementl[0] == 'Input files:': 125 if elementl[0] == 'Input files:':
125 fastqs = elementl[1] 126 fastqs = elementl[1]
126 lines_used.append(element) 127 lines_used.append(element)
127 if elementl[1] not in fastq2serotype.keys(): 128 if elementl[1] not in fastq2serotype.keys():
128 fastq2serotype[fastqs] = ['']*5 129 fastq2serotype[fastqs] = ['']*5
129 fastq2comment[fastqs] = [] 130 fastq2comment[fastqs] = []
130 elif elementl[0] == 'O antigen prediction:': 131 elif elementl[0] == 'O antigen prediction:':
131 lines_used.append(element) 132 lines_used.append(element)
132 fastq2serotype[fastqs][0] = elementl[1] # add predicted profile 133 fastq2serotype[fastqs][0] = elementl[1] # add predicted profile
133 elif elementl[0] == 'H1 antigen prediction(fliC):': 134 elif elementl[0] == 'H1 antigen prediction(fliC):':
134 lines_used.append(element) 135 lines_used.append(element)
135 fastq2serotype[fastqs][1] = elementl[1] # add predicted profile 136 fastq2serotype[fastqs][1] = elementl[1] # add predicted profile
136 elif elementl[0] == 'H2 antigen prediction(fljB):': 137 elif elementl[0] == 'H2 antigen prediction(fljB):':
137 lines_used.append(element) 138 lines_used.append(element)
138 fastq2serotype[fastqs][2] = elementl[1] # add predicted profile 139 fastq2serotype[fastqs][2] = elementl[1] # add predicted profile
139 elif elementl[0] == 'Predicted antigenic profile:': 140 elif elementl[0] == 'Predicted antigenic profile:':
140 lines_used.append(element) 141 lines_used.append(element)
141 fastq2serotype[fastqs][3] = elementl[1] # add predicted profile 142 fastq2serotype[fastqs][3] = elementl[1] # add predicted profile
142 elif elementl[0] == 'Predicted serotype(s):': 143 elif elementl[0] == 'Predicted serotype(s):':
143 lines_used.append(element) 144 lines_used.append(element)
144 fastq2serotype[fastqs][4] = elementl[1] # add predicted serotype 145 fastq2serotype[fastqs][4] = elementl[1] # add predicted serotype
145 if element not in lines_used and re.search("\w", fastqs) and len(element) > 7: 146 if element not in lines_used and re.search("\w", fastqs) and len(element) > 7:
146 fastq2comment[fastqs].append(element) 147 fastq2comment[fastqs].append(element)
147 #print("\n" 148 #print("\n"
148 return fastq2serotype, fastq2comment 149 return fastq2serotype, fastq2comment
149 150
150 def print_html(fastq2serotype, fastq2comment): 151 def print_html(fastq2serotype, fastq2comment):
151 ''' 152 '''
152 Takes dict and prints to html file. 153 Takes dict and prints to html file.
153 ''' 154 '''
154 tab_out = open('Seqsero_result.txt', 'w'); 155 tab_out = open('Seqsero_result.txt', 'w');
155 html_out = open('Seqsero_result.html', 'w') 156 html_out = open('Seqsero_result.html', 'w')
156 html_out.write('<!DOCTYPE html>\n') 157 html_out.write('<!DOCTYPE html>\n')
157 html_out.write('<html>\n') 158 html_out.write('<html>\n')
158 html_out.write('<head>\n') 159 html_out.write('<head>\n')
159 html_out.write('<title>SeqSero Results</title>\n') 160 html_out.write('<title>SeqSero Results</title>\n')
180 for antigen in fastq2serotype[fastq]: 181 for antigen in fastq2serotype[fastq]:
181 html_out.write('<td>'+antigen+'</td>\n') 182 html_out.write('<td>'+antigen+'</td>\n')
182 html_out.write('</tr>\n') 183 html_out.write('</tr>\n')
183 print(line_to_print) 184 print(line_to_print)
184 html_out.write('</table>\n') 185 html_out.write('</table>\n')
185 print("\n") 186 print("\n")
186 for fastq in fastq2comment: 187 for fastq in fastq2comment:
187 tab_out.write("\n"+fastq+"\n") 188 tab_out.write("\n"+fastq+"\n")
188 html_out.write('<tr>\n') 189 html_out.write('<tr>\n')
189 html_out.write('<p>\n') 190 html_out.write('<p>\n')
190 html_out.write('<td>'+fastq+"<br></td>\n") 191 html_out.write('<td>'+fastq+"<br></td>\n")
191 for line in fastq2comment[fastq]: 192 for line in fastq2comment[fastq]:
192 #if len(line) > 7: 193 #if len(line) > 7:
193 html_out.write('<td>'+line+'</td>\n') 194 html_out.write('<td>'+line+'</td>\n')
194 tab_out.write(line+"\n") 195 tab_out.write(line+"\n")
195 print(line) 196 print(line)
196 print("\n") 197 print("\n")
197 html_out.write('</p>\n') 198 html_out.write('</p>\n')
198 html_out.write('</tr>\n') 199 html_out.write('</tr>\n')
199 html_out.write('</body>\n') 200 html_out.write('</body>\n')
200 html_out.write('</html>\n') 201 html_out.write('</html>\n')
201 html_out.close() 202 html_out.close()
202 203