changeset 0:efe8f0e53d3e draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/snp-sites commit 3a0370239dd8ee753194be5c580b1d9b8ec98bee
author iuc
date Fri, 30 Jun 2017 16:43:26 -0400
parents
children 5804f786060d
files snp-sites.xml test-data/input.fasta test-data/output.fasta test-data/output.phylip test-data/output.vcf
diffstat 5 files changed, 111 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/snp-sites.xml	Fri Jun 30 16:43:26 2017 -0400
@@ -0,0 +1,88 @@
+<?xml version='1.0' encoding='UTF-8'?>
+<tool id='snp_sites' name='Finds SNP sites' version='0.1.0'>
+   <description>from a multi-FASTA alignment file</description>	
+   <requirements>
+      <requirement type='package' version='2.3.2'>snp-sites</requirement>
+   </requirements>
+   <version_command>snp-sites -V</version_command>
+   <command detect_errors='aggressive'><![CDATA[
+snp-sites 
+-mvp 
+-o output 
+'$input_fasta'
+]]></command>
+   <inputs>
+        <param name='input_fasta' format='fasta' type='data' label='FASTA file' />
+   </inputs>
+   <outputs>
+        <data name='output_fasta' format='fasta' label='${tool.name} on ${on_string}: FASTA' from_work_dir='output.snp_sites.aln'/>
+        <data name='output_vcf' format='vcf' label='${tool.name} on ${on_string}: VCF' from_work_dir='output.vcf'/>
+        <data name='output_phylip' format='phylip' label='${tool.name} on ${on_string}: phylip' from_work_dir='output.phylip'/>
+   </outputs>
+   <tests>
+      <test>
+         <param name='input_fasta' value='input.fasta' ftype='fasta' />
+         <output name='output_fasta' value='output.fasta' ftype='fasta' />
+         <output name='output_vcf' value='output.vcf' ftype='vcf' />
+         <output name='output_phylip' value='output.phylip' ftype='phylip' />
+      </test>
+   </tests>
+   <help>
+   <![CDATA[
+   
+**SNP-sites**
+
+This tool can rapidly extract SNPs from a multi-FASTA alignment using modest resources and can output results in multiple formats for downstream analysis. SNPs can be extracted from a 8.3 GB alignment file (1,842 taxa, 22,618 sites) in 267 seconds using 59 MB of RAM and 1 CPU core, making it feasible to run on modest computers. SNP-sites is implemented in C and is available under the open source license GNU GPL version 3.
+
+**Input FASTA format:**
+
+The first sequence will be taken as a reference.
+
+.. code-block::
+
+  >sample1
+  AGACACAGTCAC
+
+  >sample1
+  AGACAC----AC
+
+  >sample1
+  AAACGCATTCAN
+
+**Output files:**
+
+The output of the tool are three different files in following format:
+
+- a multi fasta alignment,
+- relaxed phylip format and,
+- VCF.
+
+The VCF file for the above specified input is
+
+The output of the tool are three different files in following format:
+
+- a multi fasta alignment,
+- relaxed phylip format and,
+- VCF.
+
+The VCF file for the above specified input is
+
+=====   === ==  === ===    ====    ======  ====    ======  ======= ======= =======
+CHROM   POS ID  REF ALT    QUAL    FILTER  INFO    FORMAT  sample1 sample1 sample1
+-----   --- --  --- ---    ----    ------  ----    ------  ------- ------- -------
+1       2   .   G   A      .       .       .       GT      0       0       1
+-----   --- --  --- ---    ----    ------  ----    ------  ------- ------- -------
+1       5   .   A   G      .       .       .       GT      0       0       1
+-----   --- --  --- ---    ----    ------  ----    ------  ------- ------- -------
+1       8   .   G   .,T    .       .       .       GT      0       1       2
+=====   === ==  === ===    ====    ======  ====    ======  ======= ======= =======
+
+Thus the tool identified three variations (SNPs): in 2nd, 5th, and 8th positions (A instead of G, G instead of A, and unknown nucleotide or T instead of G, respectively).
+
+
+	]]>
+    </help>
+	<citations>
+        <citation type="doi">10.1099/mgen.0.000056</citation>
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input.fasta	Fri Jun 30 16:43:26 2017 -0400
@@ -0,0 +1,6 @@
+>sample1
+AGACACAGTCAC
+>sample1
+AGACAC----AC
+>sample1
+AAACGCATTCAN
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output.fasta	Fri Jun 30 16:43:26 2017 -0400
@@ -0,0 +1,6 @@
+>sample1
+GAG
+>sample1
+GA-
+>sample1
+AGT
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output.phylip	Fri Jun 30 16:43:26 2017 -0400
@@ -0,0 +1,4 @@
+3 3
+sample1	GAG
+sample1	GA-
+sample1	AGT
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output.vcf	Fri Jun 30 16:43:26 2017 -0400
@@ -0,0 +1,7 @@
+##fileformat=VCFv4.1
+##contig=<ID=1,length=12>
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	sample1	sample1	sample1
+1	2	.	G	A	.	.	.	GT	0	0	1
+1	5	.	A	G	.	.	.	GT	0	0	1
+1	8	.	G	*,T	.	.	.	GT	0	1	2