changeset 0:500ceb70e4bd draft

planemo upload commit d4d558b27a09f684be8311f3cfb659b16545e167-dirty
author charles_s_test
date Sun, 12 Nov 2017 09:12:36 -0500
parents
children 09e4f955e00a
files aln-pe.sam fastq_dump_paired.xml runfastq_dump.py test.bam test.txt testdep.py testdep.xml tool_dependencies.xml
diffstat 7 files changed, 226 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /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 @@
+<tool id="testdep" name="Test Dep" version="1.1.4">
+    <description>Downloads a set of paired reads by their accession number using fastq-dump tool from sra-toolkit.</description>
+    <requirements>
+       <!-- Should just use the samtools that's installed in the path -->
+       <requirement type="binary">fastq-dump</requirement>
+    </requirements>
+  <command interpreter="python2.7">    
+
+	testdep.py ${input1}
+
+   </command>
+    <inputs>
+      <param format="fastq,fastqsanger" name="input1" multiple="true" type="data" label="Source file"/>
+	</inputs>
+    <outputs>
+	 <data name="text_file" format="txt" from_work_dir="dep_result.txt"/>   
+
+	</outputs> 
+    <tests>
+    <!-- Empty -->
+    </tests>
+
+    <help>
+
+.. class:: infomark
+
+**What it does**
+
+Performs a fastq-dump with the split-3 option.
+
+::
+
+  fastq-dump —log-level fatal --split-3 --accession accession_number --ncbi_error_report never
+
+
+Data is stored in format fastqsanger. 
+
+The metadata is now named to make it easier for collection lists to
+fetch when you search for reads in your history. 
+
+------
+
+.. class:: infomark
+
+Modifed By 
+Charles Strittmatter
+
+
+**Original Tool Author**
+
+Mando Rodriguez
+
+    </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/runfastq_dump.py	Sun Nov 12 09:12:36 2017 -0500
@@ -0,0 +1,38 @@
+import sys, os
+
+input = sys.argv[1]
+
+print(input)
+
+import re, os
+
+def fix_seq_ids(filename):
+	'''
+	make sequence ids the same for paired reads.
+	'''
+	file = list(open(filename, 'r'))
+	new_file = open(filename, 'w')
+	for line in file:
+		if re.search('^@', line) or re.search('^\+', line) and re.search(' ', line):
+			linel = re.split(' ', line)
+			linel[0] = re.sub('.\d$', '', 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')
+
+
+
Binary file test.bam has changed
--- /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
--- /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')
--- /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 @@
+<tool id="testdep" name="Test Dep" version="1.1.4">
+    <description>Downloads a set of paired reads by their accession number using fastq-dump tool from sra-toolkit.</description>
+    <requirements>
+	<requirement type="package" version="0.5.9">bwa</requirement>  
+  	<requirement type="package" version="1.3.1">samtools</requirement>
+    	<requirement type="package" version="2.7.1">blast</requirement>
+        <requirement type="package" version="2.6.2">sra_toolkit</requirement>
+  </requirements>
+  <command interpreter="python2.7">    
+
+	testdep.py 
+
+   </command>
+    <inputs>
+      <param format="fastq,fastqsanger" name="input1" multiple="true" type="data" label="Source file"/>
+	</inputs>
+    <outputs>
+	 <data name="text_txt" format="txt" from_work_dir="test.txt"/>   
+
+	</outputs> 
+    <tests>
+         <test>    
+	<output name="text_txt" file="test.txt"/>
+	 </test>     
+    </tests>
+<help>
+
+.. 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
+
+    </help>
+<citations>
+          <citation type="bibtex">
+          @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"
+          }
+          </citation>
+     </citations>
+    
+</tool>
--- /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 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="bwa" version="0.5.9">
+        <repository changeset_revision="0eb3d3c40344" name="package_bwa_0_5_9" owner="devteam" toolshed="http://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
+