diff run_seqsero_batch_galaxy_no_comment.py @ 0:6895de35a263 draft

planemo upload commit 844a891e4eaf732830043204ac636907eefb011d-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/run_seqsero_batch_galaxy_no_comment.py	Thu Oct 19 18:16:51 2017 -0400
@@ -0,0 +1,198 @@
+#!/usr/bin/python
+
+import os, re, sys, time, sqlite3, datetime
+import subprocess
+from subprocess import Popen, PIPE
+
+database = '/nfs/sw/apps/galaxy/database/universe.sqlite'
+seqsero = '/nfs/sw/apps/galaxy/tools/seqsero/SeqSero.py'
+test_out = open("/nfs/sw/apps/galaxy/tools/seqsero/test.txt", 'w')
+out_path = '/nfs/sw/apps/galaxy/database/files/000'
+test_out2 = open("/nfs/sw/apps/galaxy/tools/seqsero/test2.txt", 'w')
+
+#tab_out = open('/nfs/sw/apps/galaxy/tools/seqsero/Seqsero_result.txt', 'w')
+#tab_out.write('super monkey')
+
+tab_out = open('Seqsero_result.txt', 'w');
+#tab_out.write('super monkey')
+#tab_out.close()
+
+#print 'super monkey'
+path2sample = '/nfs/sw/apps/galaxy/tools/seqsero/fastq_tmp'
+
+test_out2.write(" Test test test");
+
+test_out.write(" test test ");
+test_out.write("");
+test_out.write("\t".join(sys.argv)+'\n')
+
+fq_list1 = []
+fq_list2 = []
+
+test_out.write(str(len(sys.argv))+"\n")
+if len(sys.argv) >= 2:
+        test_out.write("\t".join(sys.argv)+'\n')
+        fq_list1 = sys.argv[1]
+#       fq_list2 = sys.argv[2]
+
+test_out.write(str(len(sys.argv))+"\n")
+
+fastq_files = re.split(",", fq_list1)#+re.split(",", fq_list2)
+
+def print_time():
+        test_out.write(time.asctime( time.localtime(time.time())))
+
+tmp_path = "/nfs/sw/apps/galaxy/tools/seqsero/fastq_tmp"
+if not os.path.exists(tmp_path):
+        os.system('mkdir '+tmp_path)
+
+test_out.write(str(len(fastq_files))+"\n")
+
+def list_runs(fastq_files):
+        '''
+        Creates dict with runs as keys and list with filenames as values.
+        '''
+#       print "monkey"
+        run2fastqs = {}
+        for file in fastq_files:
+                run = ''
+                try:
+                        fastq = open(file, 'r')
+                        i = 0
+                        for line in fastq:
+                                line = line.rstrip("\n")
+                                if i == 0:
+                                        run = re.split("\s", line)[0]
+                                        run = re.sub('@', '', run)
+                                        run = re.sub("\.1", '', run)
+                                else:
+                                        break
+                                i += 1
+                        file1 = re.split('/', file)[-1]
+                        file2 = re.sub('.dat$', '_'+run+'.fastq', file1)
+                        new_path_file = tmp_path+'/'+file2
+#                       print run, new_path_file
+                        if file2 not in os.listdir(tmp_path):
+                                os.system('cp '+file+' '+new_path_file)
+                        if run in run2fastqs.keys():
+                                if file not in run2fastqs[run]:
+                                        run2fastqs[run].append(new_path_file)
+                        else:
+                                run2fastqs[run] = [new_path_file]
+                except IOError:
+                        print "Data not found. It is possible for a deleted file to still be listed "\
+                                "in a Galaxy library. Please confirm that the data still exists on this "\
+                                "server. You may need to upload it again."
+        return run2fastqs
+
+def run_seqsero(run2fastqs):
+        '''
+        Takes files from run2fastqs and runs SeqSero.
+        '''
+        outputs = []
+        for run in run2fastqs:
+                seqsero_cmd = []
+                if len(run2fastqs[run]) == 2:
+                        seqsero_cmd = ['python', seqsero, '-m', '2', '-i', run2fastqs[run][0], run2fastqs[run][1]]
+                elif len(run2fastqs[run]) == 1:
+                        seqsero_cmd = ['python', seqsero, '-m', '1', '-i', run2fastqs[run][0]]
+                p = Popen(seqsero_cmd, stdout=PIPE)
+                output = p.communicate()
+                outputs.append(output)
+        return outputs
+
+
+def parse_output(runs_info, out_path):
+        '''
+        retrieve seqsero output into a list of lists.
+        '''
+        for run in runs_info:
+                running_path = out_path+'/'+run
+#               print 'monkey go running ', running_path
+                running_info = open(running_path, 'r')
+                for line in running_info:
+                        test_out.write(line, "\n")
+
+def get_serotypes(outputs):
+        '''
+        '''
+        fastq2serotype = {}
+        for sample in outputs:
+                for line in sample:
+                        line = str(line)
+                        linel = re.split("\n", line)
+#                       print linel
+                        for element in linel:
+                                elementl = re.split("\t", element)
+                                if elementl[0] == 'Input files:':
+                                        fastqs = elementl[1]
+                                        if elementl[1] not in fastq2serotype.keys():
+                                                fastq2serotype[fastqs] = ['']*5
+                                elif elementl[0] == 'O antigen prediction:':
+                                        predicted_profile = elementl[1]
+                                        fastq2serotype[fastqs][0] = elementl[1] # add predicted profile
+#                                       print elementl[1]
+                                elif elementl[0] == 'H1 antigen prediction(fliC):':
+                                        predicted_profile = elementl[1]
+                                        fastq2serotype[fastqs][1] = elementl[1] # add predicted profile
+#                                       print elementl[1]
+                                elif elementl[0] == 'H2 antigen prediction(fljB):':
+                                        predicted_profile = elementl[1]
+                                        fastq2serotype[fastqs][2] = elementl[1] # add predicted profile                                                                                                             
+#                                       print elementl[1]
+                                elif elementl[0] == 'Predicted antigenic profile:':
+                                        predicted_profile = elementl[1]
+                                        fastq2serotype[fastqs][3] = elementl[1] # add predicted profile
+#                                       print elementl[1]
+                                elif elementl[0] == 'Predicted serotype(s):':
+                                        fastq2serotype[fastqs][4] = elementl[1] # add predicted serotype
+#                                       print elementl[1]
+                print "\n"
+        return fastq2serotype
+
+def print_html(fastq2serotype):
+        '''
+        Takes dict and prints to html file.
+        '''
+        html_out = open('Seqsero_result.html', 'w')
+        html_out.write('<!DOCTYPE html>\n')
+        html_out.write('<html>\n')
+        html_out.write('<head>\n')
+        html_out.write('<title>SeqSero Results</title>\n')
+        html_out.write('</head>\n')
+        html_out.write('<body>\n')
+        html_out.write('<body style="font-family:Helvetica;">\n')
+        html_out.write('<p style="font-size:10px">\n')
+        html_out.write('<table border=1>\n')
+        header = 'Input Files\tO antigen prediction\tH1 antigen prediction(fliC)\tH2 antigen prediction(fljB)\tPredicted antigenic profile\tPredicted serotype(s)'
+        header = re.sub(' ', '_', header)
+        header_l = ['Input Files', 'O antigen prediction', 'H1 antigen prediction(fliC)', 'H2 antigen prediction(fljB)', 'Predicted antigenic profile', 'Predicted serotype(s)']
+        html_out.write('<tr>\n')
+        for element in header_l:
+                html_out.write('<td>'+element+'</td>\n')
+        html_out.write('</tr>\n')
+        tab_out.write(header+"\n")
+        print header
+        for fastq in fastq2serotype:
+#               print fastq, fastq2serotype[fastq]
+                line_to_print = fastq+'\t'+"\t".join(fastq2serotype[fastq])
+                tab_out.write(line_to_print+"\n")
+                html_out.write('<tr>\n')
+                html_out.write('<td>'+fastq+'</td>\n')
+                for antigen in fastq2serotype[fastq]:
+                        html_out.write('<td>'+antigen+'</td>\n')
+                html_out.write('</tr>\n')
+                print line_to_print
+        html_out.write('</table>\n')
+        html_out.write('</body>\n')
+        html_out.write('</html>\n')
+        html_out.close()
+
+run2fastqs = list_runs(fastq_files)
+outputs = run_seqsero(run2fastqs)
+fastq2serotype = get_serotypes(outputs)
+print_html(fastq2serotype)
+
+print_time()
+                                                                                                                                                                                                                          
+