<tool id="cpm_tpm_rpk" name="Generate CPM, TPM, RPK" version="0.9.1">
    <description>from raw counts expression values</description>
    <requirements>
        <requirement type="package" version="1.6.0">r-optparse</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[ 
        Rscript $__tool_directory__/cpm_tpm_rpk.R 
            --data '$input'
            --type '$option.type_transfo' 
            --sep '$input_sep' 
            --colnames '$input_header' 
            #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
            --log '$log'
            #if $log == "FALSE":
                -o ${output}
            #else if $log == "TRUE":
                -o ${output_log}
            #end if
]]></command>
    <inputs>
        <param name="input" type="data" format="txt,tabular" label="Raw counts of expression data"/>
        <param name="input_sep" type="select" label="Input column separator">
            <option value="tab" selected="true">Tabulation</option>
            <option value=",">Comma</option>
        </param>
        <param name="input_header" type="select" label="Consider first line of input file as header?">
            <option value="TRUE" selected="true">Yes</option>
            <option value="FALSE">No</option>
        </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>
                </param>
                <when value="tpm">
                    <param name="gene_file" type="data" format="txt,tabular" label="Gene length file"/> 
                    <param name="gene_sep" type="select" label="Gene length column separator">
                        <option value="tab" selected="true">Tabulation</option>
                        <option value=",">Commas</option>
                    </param>
                    <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,tabular" 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>
                    </param>
                    <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="cpm">
                </when>
            </conditional>
        <param name="log" type="select" label="Data should be log transformed ?">
            <option value="FALSE" selected="true">No</option>
            <option value="TRUE">Yes</option>
        </param>
    </inputs>
    <outputs>
        <data name="output" format="tabular" label="${option.type_transfo} of ${on_string}">
            <filter>log == "FALSE"</filter>
        </data>
        <data name="output_log" format="tabular" label="log2(${option.type_transfo} +1) of ${on_string}">
            <filter>log == "TRUE"</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="cpm"/>
            <param name="log" value="TRUE"/>
            <output name="output" file="logcpm.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="tpm"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="log" value="TRUE"/>
            <output name="output" file="logtpm.tab" ftype="tabular"/>
        </test>
        <!-- test without t-SNE -->
        <test>
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="cpm"/>
            <output name="output" file="cpm.tab" ftype="tabular"/>
        </test>
        <test>
            <param name="input" value="counts.tab" ftype="tabular"/>
            <param name="type_transfo" value="tpm"/>
            <param name="gene_file" value="gene_length.tab" ftype="tabular"/>
            <param name="gene_header" value="TRUE"/>
            <output name="output" file="tpm.tab" ftype="tabular"/>
        </test>
        <test>
            <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>
            <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: First header row must NOT start with a '#' comment character

Computed values may be base-2 log-transformed (log2([CPM or RPK or TPM]+1))

    </help>
    <citations>
        <citation type="bibtex">
        @Manual{,
             title = {R: A Language and Environment for Statistical Computing},
             author = {{R Core Team}},
             organization = {R Foundation for Statistical Computing},
             address = {Vienna, Austria},
             year = {2014},
             url = {http://www.R-project.org/},
        }
        </citation>
    </citations>
</tool>