diff deseq-hts_2.0/galaxy/deseq2.xml @ 10:2fe512c7bfdf draft

DESeq2 version 1.0.19 added to the repo

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/galaxy/deseq2.xml	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,106 @@
+<tool id="deseq2-hts" name="DESeq2" version="1.0.19">
+  <description> Differential gene expression analysis based on the negative binomial distribution</description>
+  <command interpreter="bash"> 
+./../src/deseq2-hts.sh $anno_input_selected $deseq_out $deseq_out.extra_files_path/gene_map.mat 
+$distype
+#for $i in $replicate_groups
+#for $j in $i.replicates
+$j.bam_alignment:#slurp
+#end for
+
+#end for
+    >> $Log_File </command>
+  <inputs>
+	<param format="gff,gtf,gff3" name="anno_input_selected" type="data" label="Genome annotation in GFF file" help="A tab delimited format for storing sequence features and annotations"/>
+   <repeat name="replicate_groups" title="Replicate group" min="2">
+     <repeat name="replicates" title="Replicate">
+      <param format="bam" name="bam_alignment" type="data" label="BAM alignment file" help="BAM alignment file. Can be generated from SAM files using the SAMTools."/>
+     </repeat>
+   </repeat>
+
+    <param name="distype" type="select" label="Select fitting of dispersions to the mean intensity">
+            <option value="parametric">Parametric</option>
+            <option value="local">Local</option>
+            <option value="mean" selected="true">Mean</option>
+    </param>
+
+  </inputs>
+
+  <outputs>
+    <data format="txt" name="deseq_out" label="${tool.name} on ${on_string}: Differential Expression"/>
+    <data format="txt" name="Log_File" label="${tool.name} on ${on_string}: log"/>
+  </outputs>
+
+  <tests>
+    <test> 
+	./deseq2-hts.sh ../test_data/deseq_c_elegans_WS200-I-regions.gff3 ../test_data/deseq_c_elegans_WS200-I-regions_deseq.txt ../test_data/genes.mat ../test_data/deseq_c_elegans_WS200-I-regions-SRX001872.bam ../test_data/deseq_c_elegans_WS200-I-regions-SRX001875.bam
+	
+      <param name="anno_input_selected" value="deseq_c_elegans_WS200-I-regions.gff3" ftype="gff3" />
+      <param name="bam_alignments1" value="deseq_c_elegans_WS200-I-regions-SRX001872.bam" ftype="bam" />
+      <param name="bam_alignments2" value="deseq_c_elegans_WS200-I-regions-SRX001875.bam" ftype="bam" />
+      <output name="deseq_out" file="deseq_c_elegans_WS200-I-regions_deseq.txt" />
+    </test>
+  </tests> 
+
+  <help>
+
+.. class:: infomark
+
+**What it does** 
+
+DESeq2_ Estimate variance-mean dependence in count data from high-throughput sequencing assays and test for differential expression based on a model using the negative binomial distribution.
+
+.. _DESeq2: http://bioconductor.org/packages/2.12/bioc/html/DESeq2.html
+
+`DESeq2` requires:
+
+Genome annotation in GFF file type, containing the necessary information about the transcripts that are to be quantified.
+
+The BAM alignment files grouped into replicate groups, each containing several replicates. BAM files store the read alignments, The program will also work with only two groups containing only a single replicate each. However, this analysis has less statistical power and is therefore not recommended!
+
+------
+
+**Licenses**
+
+If **DESeq2** is used to obtain results for scientific publications it
+should be cited as [1]_.
+
+**References** 
+
+.. [1] Anders, S and Huber, W (2010): `Differential expression analysis for sequence count data`_. 
+
+.. _Differential expression analysis for sequence count data: http://dx.doi.org/10.1186/gb-2010-11-10-r106
+
+------
+
+.. class:: infomark
+
+**About formats**
+
+**GFF/GTF format** General Feature Format/Gene Transfer Format is a format for describing genes and other features associated with DNA, RNA and protein sequences. GFF3 lines have nine tab-separated fields:
+
+1. seqid - The name of a chromosome or scaffold.
+2. source - The program that generated this feature.
+3. type - The name of this type of feature. Some examples of standard feature types are "gene", "CDS", "protein", "mRNA", and "exon". 
+4. start - The starting position of the feature in the sequence. The first base is numbered 1.
+5. stop - The ending position of the feature (inclusive).
+6. score - A score between 0 and 1000. If there is no score value, enter ".".
+7. strand - Valid entries include '+', '-', or '.' (for don't know/care).
+8. phase - If the feature is a coding exon, frame should be a number between 0-2 that represents the reading frame of the first base. If the feature is not a coding exon, the value should be '.'.
+9. attributes - All lines with the same group are linked together into a single item.
+
+For more information see http://www.sequenceontology.org/gff3.shtml
+
+**BAM format** The Sequence Alignment/Map (SAM) format is a
+tab-limited text format that stores large nucleotide sequence
+alignments. BAM is the binary version of a SAM file that allows for
+fast and intensive data processing. The format specification and the
+description of SAMtools can be found on
+http://samtools.sourceforge.net/.
+
+------
+
+DESeq2-hts Wrapper Version 0.2 (Aug 2013)
+
+</help>
+</tool>