<tool id="pancancer_apply_weights" name="PAPAA: PanCancer apply weights" version="@VERSION@">
  <description>apply weights</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <version_command><![CDATA['papaa_apply_weights.py' --version]]></version_command>
  <command><![CDATA[
  mkdir 'classifier' &&
  ln -s '${pancan_classifier_summary}' 'classifier/classifier_summary.txt' &&
  ln -s '${pancan_classifier_coefficients}' 'classifier/classifier_coefficients.tsv' &&
  papaa_apply_weights.py 
  --classifier_summary 'classifier'
  @INPUTS_BASIC@
  @INPUTS_COPY_NUMBER_CLASS_FILE_CONDITIONAL@
  > '${log}'
 ]]></command>
  <inputs>
    <expand macro="inputs_basic"/>
    <expand macro="inputs_copy_number_class_file_conditional"/>
    <param argument="--classifier_summary" label="pancancer classifier summary" name="pancan_classifier_summary" optional="false" type="data" format="txt" help="classifer_summary.txt"/>
    <param label="pancancer classifier coefficients" name="pancan_classifier_coefficients" optional="false" type="data" format="tabular" help="classifier_coefficients.tsv"/>
  </inputs>
  <outputs>
    <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)"/>
    <data format="tabular" name="classifier_decisions" label="${tool.name} on ${on_string} (classifier_decisions.tsv)" from_work_dir="classifier/classifier_decisions.tsv"/>
  </outputs>
  <tests>
        <test>
            <param name="x_matrix" value="pancan_rnaseq_freeze_t1p.tsv.gz" ftype="tabular"/>
            <param name="filename_mut" value="pancan_mutation_freeze_t1p.tsv.gz" ftype="tabular"/>
            <param name="filename_mut_burden" value="mutation_burden_freeze.tsv" ftype="tabular"/>
            <param name="filename_sample" value="sample_freeze.tsv" ftype="tabular"/>
            <param name="copy_number" value="yes"/>
            <param name="filename_copy_loss" value="copy_number_loss_status_t10p.tsv.gz" ftype="tabular"/>
            <param name="filename_copy_gain" value="copy_number_gain_status_t10p.tsv.gz" ftype="tabular"/>
            <param name="filename_cancer_gene_classification" value="cosmic_cancer_classification.tsv" ftype="tabular"/>
            <param name="pancan_classifier_summary" value="classifier_summary.txt" ftype="txt"/>
            <param name="pancan_classifier_coefficients" value="classifier_coefficients.tsv" ftype="tabular"/>
            <output name="log" file="apply_weights_Log.txt"/>
            <output name="classifier_decisions">
              <assert_contents>
                  <has_line line="SAMPLE_BARCODE&#009;log10_mut&#009;total_status&#009;weight&#009;AKT1&#009;AKT1_gain&#009;ERBB2&#009;ERBB2_gain&#009;KRAS&#009;KRAS_gain&#009;PIK3CA&#009;PIK3CA_gain&#009;PATIENT_BARCODE&#009;DISEASE&#009;SUBTYPE&#009;hypermutated&#009;include" />
                  <has_n_columns n="17" />
                  <has_n_lines n="90" />
              </assert_contents>
          </output>
        </test>
    </tests>
  <help><![CDATA[
    
    **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/papaa_apply_weights.py:**

      **Inputs:**
        --classifier_summary  String of the location of classifier_summary.txt file
        --copy_number   Supplement Y matrix with copy number events
        --x_matrix  Filename of features to use in model
        --filename_mut_burden   Filename of sample/gene mutations to use in model
        --filename_mut_burden   Filename of sample mutation burden to use in model
        --filename_sample   Filename of patient/samples to use in model
        --filename_copy_loss  Filename of copy number loss
        --filename_copy_gain  Filename of copy number gain
        --filename_cancer_gene_classification   Filename of cancer gene classification table

      **Outputs:**
      Apply a logit transform on expression values (y = 1/(1+e^(-wX))) to output mutational probabilities. Generates "classifier_decisions.tsv" file which has scores/probabilities and other covariate information.  The scores/probabilities will be used for gene ranking and variant specific classification. ]]>  
  </help>
  <expand macro="citations" />
</tool>