diff htseqsams2mx.xml @ 56:9b59cd40f20d draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/htseqsams2mx.xml	Tue Apr 28 22:56:39 2015 -0400
@@ -0,0 +1,133 @@
+<tool id="htseqsams2mxlocal" name="SAM/BAM to count matrix" version="0.5">
+  <description>using HTSeq code</description>
+  <stdio>
+   <regex match=".*" source="both" level="warning" description="chatter from HTSeq:"/>
+  </stdio>
+  <requirements>
+      <requirement type="package" version="0.7.6">pysam</requirement>
+      <requirement type="package" version="1.2.1">matplotlib</requirement> 
+      <requirement type="package" version="0.5.4p3">htseq</requirement>
+  </requirements>
+  <command interpreter="python">
+    htseqsams2mx.py -g "$gfffile" -o "$outfile" -m "$model" --id_attribute "$id_attr" --feature_type "$feature_type"
+    --mapqMin $mapqMin  
+    #for $s in $samfiles:
+      #if $s.ext != 'data':
+        --samf "'${s}','${s.name}','${s.ext}','${s.metadata.bam_index}'" 
+      #end if
+    #end for
+    #if $filter_extras:
+       --filter_extras "$filter_extras"
+    #end if
+  </command>
+  <inputs>
+    <param format="gtf" name="gfffile" type="data" label="Gene model (GFF) file to count reads over from your current history" size="100" />
+    <param name="mapqMin" label="Filter reads with mapq below than this value" 
+    help="0 to count any mapping quality read. Otherwise only reads at or above specified mapq will be counted" 
+    type="integer" value="5"/>
+    <param name="title" label="Name for this job's output file" type="text" size="80" value="bams to DGE count matrix"/>
+    <param name="stranded" value="false" type="boolean" label="Reads are stranded - use strand in counting" display="checkbox"
+      truevalue="yes" falsevalue="no" checked="no" help="Check this ONLY if you know your sequences are strand specific" />
+    <param name="model"  type="select" label="Model for counting reads over the supplied gene model- see HTSeq docs"
+        help="If in doubt, union is a reasonable default but intersection-strict avoids double counting over overlapping exons">
+        <option value="union" selected="true">union</option>
+        <option value="intersection-strict">intersection-strict</option>
+        <option value="intersection-nonempty">intersection-nonempty</option>
+    </param>   
+    <param name="id_attr" type="select" label="GTF attribute to output as the name for each contig - see HTSeq docs"
+        help="If in doubt, use gene name or if you need the id in your GTF, gene id">
+        <option value="gene_name" selected="true">gene name</option>
+        <option value="gene_id">gene id</option>
+        <option value="transcript_id">transcript id</option>
+        <option value="transcript_name">transcript name</option>
+    </param>   
+    <param name="feature_type" type="select" label="GTF feature type for counting reads over the supplied gene model- see HTSeq docs"
+        help="GTF feature type to count over - exon is a good choice with gene name as the contig to count over">
+        <option value="exon" selected="true">exon</option>
+        <option value="CDS">CDS</option>
+        <option value="UTR">UTR</option>
+        <option value="transcript">transcript</option>
+    </param>   
+    <param name="filter_extras" type="select" label="Filter any read with one or more flags"
+        help="eg the XS tag created by bowtie for multiple reads" optional="true" mutliple="true">
+        <option value="">None</option>
+        <option value="XS">XS:i > 0 - More than one mapping position Bowtie</option>
+        <option value="XS:A">Might be useful for tophat</option>
+    </param>   
+
+    <param name="samfiles" type="data" label="bam/sam file from your history" format="sam,bam" size="100" multiple="true"/>
+  </inputs>
+  <outputs>
+    <data format="tabular" name="outfile" label="${title}_htseqsams2mx.xls" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="feature_type" value="exon" />
+      <param name="gfffile" value="rn4_chr20_100k.gtf" />
+      <param name="samfiles" value="rn4chr20test1.bam,rn4chr20test2.bam" ftype="bam"/>
+      <param name="id_attr" value="gene_name" />
+      <param name="model" value="union" />
+      <param name="stranded" value="no" />
+      <param name="title" value="htseqtest" />
+      <param name="mapqMin" value="0" />
+
+      <output name="outfile" file="htseqsams2mx_test1_out.xls" lines_diff="1"/>
+    </test>
+  </tests>
+  <help>
+
+**What this tool does**
+
+Counts reads in multiple sam/bam format mapped files and generates a matrix ideal for edgeR and other count based tools
+It uses HTSeq to count your sam reads over a gene model supplied as a GTF file
+The output is a tabular text (columnar - spreadsheet) file containing the 
+count matrix for downstream processing. Each row contains the counts from each sample for each
+of the non-emtpy GTF input file contigs matching the GTF attribute choice above. 
+You probably want to use gene level GTF output attribute and count reads that overlap 
+GTF exons for RNA-seq. Or you can count over exons by using transcript level output names or ids. Etc.
+
+----
+
+**Author's plea on replicates**
+
+If you want to interpret the downstream p values in terms of rejecting or accepting the null hypothesis 
+under random sampling with replacement from the universe of possible biological/experimental replicates from which your data was derived,
+which is what published p values are often assumed to do, then you need biological 
+(or for cell culture material experimental) replicates. 
+
+Using technical or no replicates means the downstream p values are not interpretable the way most people would assume 
+they are - ie as the probability of obtaining a result as or more extreme as your experimental data
+in millions of experiments conducted using the same methods under the null hypothesis.
+
+There is no way around this and it is scientific fraud to ignore this issue and publish bogus p values derived from 
+technical or no replicates without making the lack of biological or experimental error in the p value calculations 
+clear to your readers so they can adjust their expectations. However, the buck stops here at higher level inference.
+If you have no replicates, you must not use this tool as the p values are uninterpretable. So there.
+
+See your stats 101 notes on the central limit theorem and test statistics for a refresher or talk to a 
+statistician if this makes no sense please.
+
+**Attribution**
+
+This Galaxy tool relies on HTSeq_ from http://www-huber.embl.de/users/anders/HTSeq/doc/index.html 
+for the tricky work of counting. That code includes the following attribution:
+
+## Written by Simon Anders ([e-mail]), European Molecular Biology
+## Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
+## Public License v3. Part of the 'HTSeq' framework, version HTSeq-0.5.4p3
+
+It will be automatically installed if you use the toolshed as in general, you probably should.
+HTSeq_ must be installed with this tool if you install manually.
+
+Otherwise, all code and documentation comprising this tool including the requirement
+for more than one sample bam
+was written by Ross Lazarus and is 
+licensed to you under the LGPL_ like other rgenetics artefacts
+
+Sorry, I don't use readgroups so had no reason to code read groups. Contributions welcome. Send code
+
+.. _LGPL: http://www.gnu.org/copyleft/lesser.html
+.. _HTSeq: http://www-huber.embl.de/users/anders/HTSeq/doc/index.html
+  </help>
+
+</tool>