# HG changeset patch # User saharlcc # Date 1474336803 14400 # Node ID 7044191a603bc1e4ec98b78ff29f6af901b134f9 # Parent babf45f7c9a35427292f5f01ec24aa77468ddc91 Uploaded diff -r babf45f7c9a3 -r 7044191a603b isoem_wrapper.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/isoem_wrapper.xml Mon Sep 19 22:00:03 2016 -0400 @@ -0,0 +1,161 @@ + + Infers isoform and gene expression levels from high-throughput transcriptome sequencing (RNA-Seq) data + + + + + 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 > $Run 2>&1 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**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. + + + + + + + +