annotate isoem_wrapper.xml @ 9:ce0a125b3cd1 draft

Uploaded

<tool id="isoem" name="IsoEM2" version="1.0.0">
    <description> Infers isoform and gene expression levels from high-throughput transcriptome sequencing (RNA-Seq) data</description>
    <requirements>
        
    </requirements>
    <command interpreter="bash">
        isoem_wrapper.sh

            ## Provide outputs.
            --out_gene_fpkm $out_gene_fpkm
            --out_gene_tpm $out_gene_tpm
            --out_iso_fpkm $out_iso_fpkm
            --out_iso_tpm $out_iso_tpm
            --out_bootstrap $out_bootstrap

            ## Handle reference file .
            #if $referenceSource.CCDSsource == "history":
                --fastaFile $referenceSource.fastaFile
            #else:
                --GTF $referenceSource.index.fields.GTF --TMAP_INDEX $referenceSource.index.fields.TMAP_INDEX --HISAT2_INDEX $referenceSource.index.fields.HISAT2_INDEX --Cluster $referenceSource.index.fields.Cluster
            #end if
	   
            ## First input file always required fastq1.
            --input1 $Data.input1

            ## Set params based on whether reads are single-end or paired.
            #if $Data.RNAseqType == "Illumina-paired-end":
  		--input2 $Data.input2
	    #else:
                -m $Data.lengthMean
	        -d $Data.lengthSd
	    #end if

            ## RNA-Seq type based on sequencing platform.
            --RNA_type $Data.RNAseqType &gt; $Run 2&gt;&amp;1

        
                          
    </command>
    <inputs>
        <conditional name="referenceSource">
          <param name="CCDSsource" type="select" label="Will you upload a reference transcriptome fasta file from your history or use a built-in reference?" help="Built-ins were indexed using default options">
            <option value="indexed">Use a built-in reference</option>
            <option value="history">Use reference from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a reference dataset" help="If your reference of interest is not listed, contact the Galaxy team">
              <options from_data_table="IsoEM" />
            </param>
          </when>
          <when value="history">
            <param name="fastaFile" type="data" format="fasta" metadata_name="dbkey" label="Select CCDS fasta file from your history" />
          </when>  <!-- history -->
        </conditional>  <!-- referenceSource -->
        <conditional name="Data">
<!--
            <param name="sPaired" type="select" label="Is this library Single-end or Paired-end?">
              <option value="single">Single-end</option>
              <option value="paired">Paired-end</option>
            </param>
-->
            <param name="RNAseqType" type="select" label="Select RNA-seq type">
	        <option value="Ion-Torrent-Proton">Ion Torrent single-end</option>
        	<option value="Illumina-paired-end">Illumina paired-end</option>
	        <option value="Illumina-single-end">Illumina single-end</option>
            </param>  <!-- RNAseqType -->
            <when value="Illumina-paired-end">
              <param name="input1" type="data" label="RNA-Seq file1, fastq or bam format" />
              <param name="input2" type="data" label="RNA-Seq file2, fastq or bam format" /> 
	    </when>
            <when value="Ion-Torrent-Proton">
	      <param name="input1" type="data" label="RNA-Seq file, fastq or bam format" />
              <param name="lengthMean" type="text" label="m (RNA-Seq fragment length mean)" />
	      <param name="lengthSd" type="text" label="d (RNA-Seq fragment length standard deviation)" /> 
            </when>
            <when value="Illumina-single-end">
	      <param name="input1" type="data" label="RNA-Seq file, fastq or bam format" />
              <param name="lengthMean" type="text" label="m (RNA-Seq fragment length mean)" />
	      <param name="lengthSd" type="text" label="d (RNA-Seq fragment length standard deviation)" /> 
            </when>
        </conditional>  <!-- Data -->
<!--
        <param name="RNAseqType" type="select" label="Select RNA-seq type">
           <option value="Ion-Torrent-Proton">Ion Torrent Proton</option>
           <option value="Illumina-paired-end">Illumina paired-end</option>
           <option value="Illumina-single-end">Illumina single-end</option>
        </param>  
-->
    </inputs>
    <outputs>
        <data name="out_gene_fpkm" format="tabular" label="Gene_fpkm"/>
    	<data name="out_gene_tpm" format="tabular" label="Gene_tpm"/>
    	<data name="out_iso_fpkm" format="tabular" label="Iso_fpkm"/>
    	<data name="out_iso_tpm" format="tabular" label="Iso_tpm"/>
	<data name="out_bootstrap" format="toolshed.gz" label="Bootstrap.tar.gz"/>
        <data name="Run" format="log"  label="isoem_wrapper: The log file" />
    </outputs>
<help>
**What it does**

* The IsoEM can be used to infer isoform and gene expression levels from high-throughput transcriptome sequencing (RNA-Seq) data. 

**Input Format**

* The tool accept the fastq, fastq.gz, bam formats. Extension must be specified at the end of the file names.
* RNA-seq data must be Ion Torrent Proton or Illumina sequncing data.

-----


**BUILT-IN REFERENCE documentation**

**mm10_C57BL/6:** 

* GTF file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna.GTF
* TMAP_index:/import1/tmap-index/tmap3.4.1/mm10/CCDS_nucleotide.20140407.fna
* HISAT2_index: /import1/hisat2-index/mm10_CCDS/mm10_CCDS_nucleotide.20140407
* Cluster file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna_transcriptID_geneName.txt

**mm10_BALB/c:**

* GTF file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna.GTF
* TMAP_index: /import1/tmap-index/tmap3.4.1/mm10/mm10_CCDS_nucleotide.20140407_BALBc.fna
* HISAT2_index: /import1/hisat2-index/mm10_CCDS/mm10_CCDS_nucleotide.20140407_BALBc
* Cluster file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna_transcriptID_geneName.txt

**hg19**

* GTF file: /import1/CCDS/HsGRCh37.1/HsGRCh37.1_CCDS_nucleotide.20131129.fa.GTF
* TMAP_index: /import1/tmap-index/tmap3.4.1/hg19/hg19_CCDS_nucleotide.20131129.fa
* HISAT2_index: /import1/hisat2-index/hg19/hg19_CCDS_nucleotide.20131129.fna
* Cluster file: /import1/CCDS/HsGRCh37.1/HsGRCh37.1_CCDS.20131129_transcriptID_geneName.txt

**hg38**

* GTF file: /import1/CCDS/GRCh38.p2/GRCh38.p2_CCDS_nucleotide.20150512.fna.GTF
* TMAP_index: /import1/tmap-index/tmap3.4.1/hg38/hg38_CCDS_nucleotide.20150512.fna
* HISAT2_index: /import1/hisat2-index/hg38_CCDS_downloadedRef/h19_CCDS_nucleotide.20150512.fna
* Cluster file: /import1/CCDS/GRCh38.p2/GRCh38.p2_CCDS.20150512_transcriptID_geneName.txt
	
-----

**Output Format**

* Four output files containinag results for **Gene FPKM**, **Gene TPM**, **Isoform FPKM**, and **Isoform TPM**. The four files have identical format with the following fields.


* 1 Gene/Isoform ID 
* 2 Gene/Isoform FPKM (Fragments Per Kilobase per Million reads) or TPM (Transcripts per Million reads) 
* 3 Min FPKM/TPM
* 4 Max FPKM/TPM

* And one compressed **Bootstrap.tar** file will be used in IsoDE2 to compute gene differential expression.
</help>


</tool>