diff runfastq_dump.py @ 0:500ceb70e4bd draft

planemo upload commit d4d558b27a09f684be8311f3cfb659b16545e167-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/runfastq_dump.py	Sun Nov 12 09:12:36 2017 -0500
@@ -0,0 +1,38 @@
+import sys, os
+
+input = sys.argv[1]
+
+print(input)
+
+import re, os
+
+def fix_seq_ids(filename):
+	'''
+	make sequence ids the same for paired reads.
+	'''
+	file = list(open(filename, 'r'))
+	new_file = open(filename, 'w')
+	for line in file:
+		if re.search('^@', line) or re.search('^\+', line) and re.search(' ', line):
+			linel = re.split(' ', line)
+			linel[0] = re.sub('.\d$', '', linel[0])
+			line = ' '.join(linel)
+		new_file.write(line)
+# fastq-dump --log-level fatal --split-3 --accession accession_number --ncbi_error_report never
+
+os.system('/nfs/sw/apps/sratoolkit/sratoolkit.2.8.0-centos_linux64/bin/fastq-dump --log-level fatal --split-3 --accession ' + input + ' --ncbi_error_report never')
+
+os.system('ls -lh | grep ' + input)
+
+#os.system('/nfs/sw/apps/sratoolkit/sratoolkit.2.8.0-centos_linux64/bin/fastq-dump -I --split-files ' + input)
+#mv_cmd = 'mv -v ' + input + '_1.fastq R1.fastq'
+#print(mv_cmd)
+
+#fix_seq_ids(input + '_1.fastq')
+#fix_seq_ids(input + '_2.fastq')
+
+os.system('mv -v ' + input + '_1.fastq R1.fastq')
+os.system('mv -v ' + input + '_2.fastq R2.fastq')
+
+
+