<tool id="cnvkit_theta" name="CNVkit Theta" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>Convert segments to THetA2 input file format</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="xrefs"/>
    <expand macro="creators"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[  
        ln -s '$input_segmented_file' ./sample.cns &&
        ln -s '$advanced_settings.reference' ./reference.cnn &&
        ln -s '$advanced_settings.vcf' ./sample.vcf &&
        cnvkit.py export theta
            ./sample.cns
            #if $advanced_settings.reference
              --reference ./reference.cnn
            #end if
            #if $advanced_settings.vcf
              --vcf ./sample.vcf
            #end if
            #if $advanced_settings.sample_id
              --sample-id '$advanced_settings.sample_id'
            #end if
            #if $advanced_settings.normal_id
              --normal-id '$advanced_settings.normal_id'
            #end if
            #if $advanced_settings.min_variant_depth
              --min-variant-depth $advanced_settings.min_variant_depth
            #end if
            #if $advanced_settings.zygosity_freq
              --zygosity-freq $advanced_settings.zygosity_freq
            #end if
            --output sample.cnv.input
    ]]></command>
     <inputs>
        <param name="input_segmented_file" type="data" format="cns,cnr" label="Segmented copy ratio data file (cns file)" help="" />
        <section name="advanced_settings" title="Advanced settings" expanded="false">
            <param argument="--reference" optional="true" type="data" format="cnn" label="Reference" help="Reference copy number profile (.cnn), or normal-sample bin-level log2 copy ratios (.cnr). Use if the tumor_segment input file does not contain a 'weight' column" />
            <param argument="--vcf" optional="true" type="data" format="vcf" label="VCF" help="VCF file containing SNVs observed in both the tumor and normal samples. Tumor sample ID should match the `tumor_segment` filename or be specified with sample ID" />
            <param argument="--sample-id" type="text" label="Sample ID" help="Sample name to write in the genotype field of the output VCF file" />
            <param argument="--normal-id" type="text" label="Normal Id" help="Corresponding normal sample ID in the input VCF" />
            <param argument="--min-variant-depth" optional="true" type="integer" label="Minimum Variant Depth" min="1" value="20" help="Minimum read depth for a SNP in the VCF to be counted. [Default: 20]" />
            <param argument="--zygosity-freq" optional="true" type="float" label="Zygosity Frequency" min="0" value="0.25" help="Ignore VCF's genotypes (GT field) and instead infer zygosity from allele frequencies. [Default if used without a number: 0.25]" />

        </section>  
        </inputs>
    <outputs>
        <data name="CNVs_Theta" format="tabular" label="${tool.name} on ${on_string}: CNVs theta file" from_work_dir="sample.cnv.input" />
    </outputs>
       <tests>
        <test expect_num_outputs="1">
            <param name="input_segmented_file" ftype="cns" value="tumor.cns" />
            <output name="CNVs_Theta" file="sample.cnv.input" />
        </test>
    </tests>
    <help><![CDATA[
        
Export the segmented copy number data (from a *.cns file) to THetA2 input file format (*.input).
   
-----

**Copy Number Reference Profile (.cnn)**

Tabular file defining the reference baseline built from control samples (e.g., normal samples). Used to normalize test samples.

.. csv-table::
   :header-rows: 0

    "chromosome","Genomic chromosome (e.g., chr1, chrX)."
    "start","Start position of the bin."
    "end","End position of the bin."
    "gene","Gene name(s) (if applicable)."
    "log2","Reference log2 ratio (typically 0 for diploid regions)."
    "depth","Average read depth across control samples."
    "spread","Variability (standard deviation) of coverage in controls."

-----

**Segmented log2 ratios (.cns)**

Tabular file with smoothed, merged segments of stable copy number, derived from the .cnr file. Represents final CNV calls.

.. csv-table::
   :header-rows: 0

    "chromosome","start, end: Genomic coordinates of the segment"
    "gene","Gene(s) overlapping the segment."
    "log2","Mean log2 ratio of the segment."
    "probes","Mean log2 ratio of the segment."
    "depth","Average read depth."
    "weight","Reliability weight."
    "p_value","Statistical confidence (lower = more significant)."
    
    ]]></help>
    <expand macro="citations" />
</tool>