<tool id="rseqc_infer_experiment" name="Infer Experiment" version="2.4galaxy1">
    <description>speculates how RNA-seq were configured</description>

    <macros>
        <import>rseqc_macros.xml</import>
    </macros>

    <requirements>
        <expand macro="requirement_package_numpy" />
        <expand macro="requirement_package_rseqc" />
    </requirements>

    <expand macro="stdio" />

    <version_command><![CDATA[infer_experiment.py --version]]></version_command>

    <command><![CDATA[
        infer_experiment.py -i $input -r $refgene
            --sample-size $sample_size
            --mapq $mapq
            > $output
            ]]>
    </command>

    <inputs>
        <param name="input" type="data" format="bam,sam" label="Input BAM/SAM file" help="(--input-file)"/>
        <param name="refgene" type="data" format="bed" label="Reference gene model in bed format" help="(--refgene)" />
        <param name="sample_size" type="integer" label="Number of reads sampled from SAM/BAM file (default = 200000)" value="200000" help="(--sample-size)"/>
        <param name="mapq" type="integer" label="Minimum mapping quality (default=30)" help="Minimum phred scale mapping quality to consider a read 'uniquely mapped' (--mapq)" value="30" />
    </inputs>

    <outputs>
        <data format="txt" name="output" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed"/>
            <output name="output" file="output.infer_experiment.txt"/>
        </test>
    </tests>

    <help><![CDATA[
infer_experiment.py
+++++++++++++++++++

This program is used to speculate how RNA-seq sequencing were configured, especially how
reads were stranded for strand-specific RNA-seq data, through comparing reads' mapping
information to the underneath gene model.


Inputs
++++++++++++++

Input BAM/SAM file
    Alignment file in BAM/SAM format.

Reference gene model
    Gene model in BED format.

Number of usable sampled reads (default=200000)
    Number of usable reads sampled from SAM/BAM file. More reads will give more accurate estimation, but make program little slower.

Outputs
+++++++

For pair-end RNA-seq, there are two different
ways to strand reads (such as Illumina ScriptSeq protocol):

1. 1++,1--,2+-,2-+

* read1 mapped to '+' strand indicates parental gene on '+' strand
* read1 mapped to '-' strand indicates parental gene on '-' strand
* read2 mapped to '+' strand indicates parental gene on '-' strand
* read2 mapped to '-' strand indicates parental gene on '+' strand

2. 1+-,1-+,2++,2--

* read1 mapped to '+' strand indicates parental gene on '-' strand
* read1 mapped to '-' strand indicates parental gene on '+' strand
* read2 mapped to '+' strand indicates parental gene on '+' strand
* read2 mapped to '-' strand indicates parental gene on '-' strand

For single-end RNA-seq, there are also two different ways to strand reads:

1. ++,--

* read mapped to '+' strand indicates parental gene on '+' strand
* read mapped to '-' strand indicates parental gene on '-' strand

2. +-,-+

* read mapped to '+' strand indicates parental gene on '-' strand
* read mapped to '-' strand indicates parental gene on '+' strand


Example Output
++++++++++++++

**Example1** ::

    =========================================================
    This is PairEnd Data ::

    Fraction of reads explained by "1++,1--,2+-,2-+": 0.4992
    Fraction of reads explained by "1+-,1-+,2++,2--": 0.5008
    Fraction of reads explained by other combinations: 0.0000
    =========================================================

*Conclusion*: We can infer that this is NOT a strand specific because 50% of reads can be explained by "1++,1--,2+-,2-+", while the other 50% can be explained by "1+-,1-+,2++,2--".

**Example2** ::

    ============================================================
    This is PairEnd Data

    Fraction of reads explained by "1++,1--,2+-,2-+": 0.9644 ::
    Fraction of reads explained by "1+-,1-+,2++,2--": 0.0356
    Fraction of reads explained by other combinations: 0.0000
    ============================================================

*Conclusion*: We can infer that this is a strand-specific RNA-seq data. strandness of read1 is consistent with that of gene model, while strandness of read2 is opposite to the strand of reference gene model.

**Example3** ::

    =========================================================
    This is SingleEnd Data ::

    Fraction of reads explained by "++,--": 0.9840 ::
    Fraction of reads explained by "+-,-+": 0.0160
    Fraction of reads explained by other combinations: 0.0000
    =========================================================

*Conclusion*: This is single-end, strand specific RNA-seq data. Strandness of reads are concordant with strandness of reference gene.


-----

About RSeQC
+++++++++++

The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation.

The RSeQC package is licensed under the GNU GPL v3 license.

.. image:: http://rseqc.sourceforge.net/_static/logo.png

.. _RSeQC: http://rseqc.sourceforge.net/

]]>
    </help>

    <expand macro="citations" />

</tool>