# HG changeset patch # User charles_s_test # Date 1510495956 18000 # Node ID 500ceb70e4bdae8d14e901021ac986d21dd6dbd2 planemo upload commit d4d558b27a09f684be8311f3cfb659b16545e167-dirty diff -r 000000000000 -r 500ceb70e4bd aln-pe.sam diff -r 000000000000 -r 500ceb70e4bd fastq_dump_paired.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/fastq_dump_paired.xml Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,54 @@ + + Downloads a set of paired reads by their accession number using fastq-dump tool from sra-toolkit. + + + fastq-dump + + + + testdep.py ${input1} + + + + + + + + + + + + + + + +.. class:: infomark + +**What it does** + +Performs a fastq-dump with the split-3 option. + +:: + + fastq-dump —log-level fatal --split-3 --accession accession_number --ncbi_error_report never + + +Data is stored in format fastqsanger. + +The metadata is now named to make it easier for collection lists to +fetch when you search for reads in your history. + +------ + +.. class:: infomark + +Modifed By +Charles Strittmatter + + +**Original Tool Author** + +Mando Rodriguez + + + diff -r 000000000000 -r 500ceb70e4bd runfastq_dump.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/runfastq_dump.py Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,38 @@ +import sys, os + +input = sys.argv[1] + +print(input) + +import re, os + +def fix_seq_ids(filename): + ''' + make sequence ids the same for paired reads. + ''' + file = list(open(filename, 'r')) + new_file = open(filename, 'w') + for line in file: + if re.search('^@', line) or re.search('^\+', line) and re.search(' ', line): + linel = re.split(' ', line) + linel[0] = re.sub('.\d$', '', 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') + + + diff -r 000000000000 -r 500ceb70e4bd test.bam Binary file test.bam has changed diff -r 000000000000 -r 500ceb70e4bd test.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test.txt Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,1 @@ +Hello World \ No newline at end of file diff -r 000000000000 -r 500ceb70e4bd testdep.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/testdep.py Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,54 @@ + +import sys, os, io + +#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('bwa index -a bwtsw /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_454.dat') +os.system('samtools view -bS /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_472.dat > test.bam') + +os.system('blastx -query /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_454.dat -out output.blast.txt') + + +file = open("test.txt","w") + +file.write("Hello World") + +file.close() + +#os.system('/nfs/sw/apps/bwa/bwa-0.7.15/bwa index -a bwtsw /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_454.dat') + + + +#os.system('bwa mem /nfs/sw/apps/galaxy-dev/galaxy/tools/seqsero/database/fliC_b_whole.fasta /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_445.dat /nfs/sw/apps/galaxy-dev/galaxy/database/files/000/dataset_446.dat > aln-pe.sam') + +#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') diff -r 000000000000 -r 500ceb70e4bd testdep.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/testdep.xml Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,72 @@ + + Downloads a set of paired reads by their accession number using fastq-dump tool from sra-toolkit. + + bwa + samtools + blast + sra_toolkit + + + + testdep.py + + + + + + + + + + + + + + + + +.. class:: infomark + +**What it does** + +Performs a fastq-dump with the split-3 option. + +:: + + fastq-dump —log-level fatal --split-3 --accession accession_number --ncbi_error_report never + + +Data is stored in format fastqsanger. + +The metadata is now named to make it easier for collection lists to +fetch when you search for reads in your history. + +------ + +.. class:: infomark + +Modifed By +Charles Strittmatter + + +**Original Tool Author** + +Mando Rodriguez + + + + + @Article{pmid25762776, + Author="Zhang, S. and Yin, Y. and Jones, M. B. and Zhang, Z. and Deatherage Kaiser, B. L. and Dinsmore, B. A. and Fitzgerald, C. and Fields, P. I. and Deng, X. ", + Title="{{S}almonella serotype determination utilizing high-throughput genome sequencing data}", + Journal="J. Clin. Microbiol.", + Year="2015", + Volume="53", + Number="5", + Pages="1685--1692", + Month="May" + } + + + + diff -r 000000000000 -r 500ceb70e4bd tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Sun Nov 12 09:12:36 2017 -0500 @@ -0,0 +1,7 @@ + + + + + + +