comparison cpm_tpm_rpk.xml @ 7:f00c1c34565e draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/cpm_tpm_rpk commit 8cca5f05212cd25113955fb9c11801f4047c12b4

6:d2575928b824

<tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.5.2">
    <description>from raw counts expression values</description>
    <requirements>
        <requirement type="package" version="1.7.1">r-optparse</requirement>
        <requirement type="package" version="0.16">r-rtsne</requirement>
        <requirement type="package" version="3.3.6">r-ggplot2</requirement>
        <requirement type="package" version="0.4.14">r-ggfortify</requirement>
        <requirement type="package" version="1.4.4">r-reshape2</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>

            #if $option.type_transfo == "tpm":
                -f $option.gene_file 
                --gene_sep $option.gene_sep 
                --gene_header $option.gene_header
            #end if 
            #if $option.type_transfo == "rpk":
                -f $option.gene_file 
                --gene_sep $option.gene_sep 
                --gene_header $option.gene_header
            #end if
            -l $log

        </param>
            <conditional name="option">
                <param name="type_transfo" type="select" label="Type of transformation">
                    <option value="cpm" selected="true">CPM</option>
                    <option value="tpm">TPM</option>
                    <option value="rpk">RPK</option>
                    <option value="none">NONE</option>
                </param>
                <when value="tpm">
                    <param name="gene_file" type="data" format="txt" label="Gene length file"/> 
                    <param name="gene_sep" type="select" label="Gene length column separator">

                    <param name="gene_header" type="select" label="Consider first line of gene length file as header ?">
                        <option value="TRUE" selected="true">Yes</option>
                        <option value="FALSE">No</option>
                    </param>
                </when>
                <when value="rpk">
                    <param name="gene_file" type="data" format="txt" label="Gene length file"/>
                    <param name="gene_sep" type="select" label="Gene length column separator">
                        <option value="tab" selected="true">Tabs</option>
                        <option value=",">Commas</option>
                        <option value="\ ">Whitespaces</option>

            <param name="log" value="TRUE"/>
            <output name="output" file="logtpm.tab" ftype="tabular" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="rpk"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="gene_header" value="TRUE"/>
            <output name="output" file="rpk.tab" ftype="tabular" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="rpk"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="gene_header" value="TRUE"/>
            <param name="log" value="TRUE"/>
            <output name="output" file="logrpk.tab" ftype="tabular" />
        </test>
    </tests>
    <help>

**What it does**

Takes a raw count expression matrix and returns a table of normalized expression values.

Normalization can be:

- CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million.
- RPK (Reads Per Kilobases) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides).
- TPM (Transcripts Per Million) are obtained by dividing RPK values by the sum of all RPK values in a sample and multiplying the results by 1 million.

RPK and TPM require a two-column correspondance table gene_name - gene length where the length is specified in nucleotide. Both these metrics are relevant only for sequencing of full length RNAs.

Note: do not comment you header line if you have header line in you tabular input (ie do not start the header line with a '#' character)

7:f00c1c34565e

<tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPKM" version="0.6.0">
    <description>from raw counts expression values</description>
    <requirements>
        <requirement type="package" version="1.7.5">r-optparse</requirement>
        <requirement type="package" version="0.17">r-rtsne</requirement>
        <requirement type="package" version="3.5.1">r-ggplot2</requirement>
        <requirement type="package" version="0.4.17">r-ggfortify</requirement>
        <requirement type="package" version="1.4.4">r-reshape2</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>

            #if $option.type_transfo == "tpm":
                -f $option.gene_file 
                --gene_sep $option.gene_sep 
                --gene_header $option.gene_header
            #end if 
            #if $option.type_transfo == "rpkm":
                -f $option.gene_file 
                --gene_sep $option.gene_sep 
                --gene_header $option.gene_header
            #end if
            -l $log

        </param>
            <conditional name="option">
                <param name="type_transfo" type="select" label="Type of transformation">
                    <option value="cpm" selected="true">CPM</option>
                    <option value="tpm">TPM</option>
                    <option value="rpkm">RPKM</option>
                    <option value="none">NONE</option>
                </param>
                <when value="tpm">
                    <param name="gene_file" type="data" format="txt" label="Gene length file"/> 
                    <param name="gene_sep" type="select" label="Gene length column separator">

                    <param name="gene_header" type="select" label="Consider first line of gene length file as header ?">
                        <option value="TRUE" selected="true">Yes</option>
                        <option value="FALSE">No</option>
                    </param>
                </when>
                <when value="rpkm">
                    <param name="gene_file" type="data" format="txt" label="Gene length file"/>
                    <param name="gene_sep" type="select" label="Gene length column separator">
                        <option value="tab" selected="true">Tabs</option>
                        <option value=",">Commas</option>
                        <option value="\ ">Whitespaces</option>

            <param name="log" value="TRUE"/>
            <output name="output" file="logtpm.tab" ftype="tabular" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="rpkm"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="gene_header" value="TRUE"/>
            <output name="output" file="rpkm.tab" ftype="tabular" />
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="rpkm"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="gene_header" value="TRUE"/>
            <param name="log" value="TRUE"/>
            <output name="output" file="logrpkm.tab" ftype="tabular" />
        </test>
    </tests>
    <help>

**What it does**

Takes a raw count expression matrix and returns a table of normalized expression values.

Normalization can be:

- CPM (Counts Per Million) are obtained by dividing counts by the library counts sum and multiplying the results by a million.
- RPK (Reads Per Kilobase) are obtained by dividing read counts by gene lengths (expressed as kilo-nucleotides).
- RPKM (Reads Per Kilobase per Million of Counts) are obtained by dividing read counts by gene lengths (expressed in kilo-nucleotides) then by the sum of library counts (expressed as millions of reads)
- TPM (Transcripts Per Million) are obtained by dividing RPK values by the sum of all RPK values in a sample and multiplying the results by 1 million.

RPK and TPM require a two-column correspondance table gene_name - gene length where the length is specified in nucleotide. Both these metrics are relevant only for sequencing of full length RNAs.

Note: do not comment you header line if you have header line in you tabular input (ie do not start the header line with a '#' character)