annotate isoem_wrapper.xml @ 2:7044191a603b draft

Uploaded

1 <tool id="isoem" name="IsoEM2" version="1.0.0">
2     <description> Infers isoform and gene expression levels from high-throughput transcriptome sequencing (RNA-Seq) data</description>
3     <requirements>
4         
5     </requirements>
6     <command interpreter="bash">
7         isoem_wrapper.sh
8 
9             ## Provide outputs.
10             --out_gene_fpkm $out_gene_fpkm
11             --out_gene_tpm $out_gene_tpm
12             --out_iso_fpkm $out_iso_fpkm
13             --out_iso_tpm $out_iso_tpm
14             --out_bootstrap $out_bootstrap
15 
16             ## Handle reference file .
17             #if $referenceSource.CCDSsource == "history":
18                 --fastaFile $referenceSource.fastaFile
19             #else:
20                 --GTF $referenceSource.index.fields.GTF --TMAP_INDEX $referenceSource.index.fields.TMAP_INDEX --HISAT2_INDEX $referenceSource.index.fields.HISAT2_INDEX --Cluster $referenceSource.index.fields.Cluster
21             #end if
22 	   
23             ## First input file always required fastq1.
24             --input1 $Data.input1
25 
26             ## Set params based on whether reads are single-end or paired.
27             #if $Data.RNAseqType == "Illumina-paired-end":
28   		--input2 $Data.input2
29 	    #else:
30                 -m $Data.lengthMean
31 	        -d $Data.lengthSd
32 	    #end if
33 
34             ## RNA-Seq type based on sequencing platform.
35             --RNA_type $Data.RNAseqType &gt; $Run 2&gt;&amp;1
36 
37         
38                           
39     </command>
40     <inputs>
41         <conditional name="referenceSource">
42           <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">
43             <option value="indexed">Use a built-in reference</option>
44             <option value="history">Use reference from the history</option>
45           </param>
46           <when value="indexed">
47             <param name="index" type="select" label="Select a reference dataset" help="If your reference of interest is not listed, contact the Galaxy team">
48               <options from_data_table="IsoEM" />
49             </param>
50           </when>
51           <when value="history">
52             <param name="fastaFile" type="data" format="fasta" metadata_name="dbkey" label="Select CCDS fasta file from your history" />
53           </when>  <!-- history -->
54         </conditional>  <!-- referenceSource -->
55         <conditional name="Data">
56 <!--
57             <param name="sPaired" type="select" label="Is this library Single-end or Paired-end?">
58               <option value="single">Single-end</option>
59               <option value="paired">Paired-end</option>
60             </param>
61 -->
62             <param name="RNAseqType" type="select" label="Select RNA-seq type">
63 	        <option value="Ion-Torrent-Proton">Ion Torrent single-end</option>
64         	<option value="Illumina-paired-end">Illumina paired-end</option>
65 	        <option value="Illumina-single-end">Illumina single-end</option>
66             </param>  <!-- RNAseqType -->
67             <when value="Illumina-paired-end">
68               <param name="input1" type="data" label="RNA-Seq file1, fastq or bam format" />
69               <param name="input2" type="data" label="RNA-Seq file2, fastq or bam format" /> 
70 	    </when>
71             <when value="Ion-Torrent-Proton">
72 	      <param name="input1" type="data" label="RNA-Seq file, fastq or bam format" />
73               <param name="lengthMean" type="text" label="m (RNA-Seq fragment length mean)" />
74 	      <param name="lengthSd" type="text" label="d (RNA-Seq fragment length standard deviation)" /> 
75             </when>
76             <when value="Illumina-single-end">
77 	      <param name="input1" type="data" label="RNA-Seq file, fastq or bam format" />
78               <param name="lengthMean" type="text" label="m (RNA-Seq fragment length mean)" />
79 	      <param name="lengthSd" type="text" label="d (RNA-Seq fragment length standard deviation)" /> 
80             </when>
81         </conditional>  <!-- Data -->
82 <!--
83         <param name="RNAseqType" type="select" label="Select RNA-seq type">
84            <option value="Ion-Torrent-Proton">Ion Torrent Proton</option>
85            <option value="Illumina-paired-end">Illumina paired-end</option>
86            <option value="Illumina-single-end">Illumina single-end</option>
87         </param>  
88 -->
89     </inputs>
90     <outputs>
91         <data name="out_gene_fpkm" format="tabular" label="Gene_fpkm"/>
92     	<data name="out_gene_tpm" format="tabular" label="Gene_tpm"/>
93     	<data name="out_iso_fpkm" format="tabular" label="Iso_fpkm"/>
94     	<data name="out_iso_tpm" format="tabular" label="Iso_tpm"/>
95 	<data name="out_bootstrap" format="toolshed.gz" label="Bootstrap.tar.gz"/>
96         <data name="Run" format="log"  label="isoem_wrapper: The log file" />
97     </outputs>
98 <help>
99 **What it does**
00 
01 * The IsoEM can be used to infer isoform and gene expression levels from high-throughput transcriptome sequencing (RNA-Seq) data. 
02 
03 **Input Format**
04 
05 * The tool accept the fastq, fastq.gz, bam formats. Extension must be specified at the end of the file names.
06 * RNA-seq data must be Ion Torrent Proton or Illumina sequncing data.
07 
08 -----
09 
10 
11 **BUILT-IN REFERENCE documentation**
12 
13 **mm10_C57BL/6:** 
14 
15 * GTF file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna.GTF
16 * TMAP_index:/import1/tmap-index/tmap3.4.1/mm10/CCDS_nucleotide.20140407.fna
17 * HISAT2_index: /import1/hisat2-index/mm10_CCDS/mm10_CCDS_nucleotide.20140407
18 * Cluster file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna_transcriptID_geneName.txt
19 
20 **mm10_BALB/c:**
21 
22 * GTF file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna.GTF
23 * TMAP_index: /import1/tmap-index/tmap3.4.1/mm10/mm10_CCDS_nucleotide.20140407_BALBc.fna
24 * HISAT2_index: /import1/hisat2-index/mm10_CCDS/mm10_CCDS_nucleotide.20140407_BALBc
25 * Cluster file: /import1/CCDS/Mm38.1/CCDS_nucleotide.20140407.fna_transcriptID_geneName.txt
26 
27 **hg19**
28 
29 * GTF file: /import1/CCDS/HsGRCh37.1/HsGRCh37.1_CCDS_nucleotide.20131129.fa.GTF
30 * TMAP_index: /import1/tmap-index/tmap3.4.1/hg19/hg19_CCDS_nucleotide.20131129.fa
31 * HISAT2_index: /import1/hisat2-index/hg19/hg19_CCDS_nucleotide.20131129.fna
32 * Cluster file: /import1/CCDS/HsGRCh37.1/HsGRCh37.1_CCDS.20131129_transcriptID_geneName.txt
33 
34 **hg38**
35 
36 * GTF file: /import1/CCDS/GRCh38.p2/GRCh38.p2_CCDS_nucleotide.20150512.fna.GTF
37 * TMAP_index: /import1/tmap-index/tmap3.4.1/hg38/hg38_CCDS_nucleotide.20150512.fna
38 * HISAT2_index: /import1/hisat2-index/hg38_CCDS_downloadedRef/h19_CCDS_nucleotide.20150512.fna
39 * Cluster file: /import1/CCDS/GRCh38.p2/GRCh38.p2_CCDS.20150512_transcriptID_geneName.txt
40 	
41 -----
42 
43 **Output Format**
44 
45 * 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.
46 
47 
48 * 1 Gene/Isoform ID 
49 * 2 Gene/Isoform FPKM (Fragments Per Kilobase per Million reads) or TPM (Transcripts per Million reads) 
50 * 3 Min FPKM/TPM
51 * 4 Max FPKM/TPM
52 
53 * And one compressed **Bootstrap.tar** file will be used in IsoDE2 to compute gene differential expression.
54 </help>
55 
56 
57 </tool>
58 
59 
60 
61