view targene_cell_line_predictions.xml @ 0:872aab514d37 draft default tip

"planemo upload for repository http://github.com/nvk747/papaa/galaxy/ commit 954b283ef7f82f59f55476a4b3a230d655187ac1"

<tool id="pancancer_targene_cell_line_predictions" name="PAPAA: PanCancer targene cell line predictions" version="@VERSION@">
    <description>targene status in ccle cell lines </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <version_command><![CDATA['papaa_targene_cell_line_predictions.py' --version]]></version_command>
    <command><![CDATA[
        mkdir 'classifier' &&
        mkdir -p 'classifier/figures' &&
        mkdir -p 'classifier/figures/cell_line' &&  
        mkdir -p 'classifier/tables' &&
        mkdir -p 'classifier/results' &&
        ln -s '${classifier_summary}' 'classifier/classifier_summary.txt' &&
        ln -s '${pancan_classifier_coefficients}' 'classifier/classifier_coefficients.tsv' &&
        ln -s '${nucleotide_mutation_scores}' 'classifier/tables/nucleotide_mutation_scores.tsv' &&
        ln -s '${amino_acid_mutation_scores}' 'classifier/tables/amino_acid_mutation_scores.tsv' &&
        papaa_targene_cell_line_predictions.py
        --classifier_summary 'classifier'
        #if $targenes and str($targenes):
        --targenes '$targenes'
        #end if
        #if $path_genes and str($path_genes):
        --path_genes '$path_genes'
        #end if
        #if $ccle_rnaseq and $ccle_rnaseq is not None:
        --ccle_rnaseq '$ccle_rnaseq'
        #end if
        #if $ccle_mut and $ccle_mut is not None:
        --ccle_mut '$ccle_mut'
        #end if
        #if $ccle_maf and $ccle_maf is not None:
        --ccle_maf '$ccle_maf'
        #end if
        #if $gdsc_rnaseq and $gdsc_rnaseq is not None:
        --gdsc_rnaseq '$gdsc_rnaseq'
        #end if
        #if $gdsc_mut and $gdsc_mut is not None:
        --gdsc_mut '$gdsc_mut'
        #end if
        #if $gdsc1_phar and $gdsc1_phar is not None:
        --gdsc1_phar '$gdsc1_phar'
        #end if
        #if $gdsc2_phar and $gdsc2_phar is not None:
        --gdsc2_phar '$gdsc2_phar'
        #end if
        > '${log}'
        ]]>
    </command>
    <inputs>
        <param argument="--classifier_summary" label="Classifier data" name="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"/>
        <param label="nucleotide mutation scores" name="nucleotide_mutation_scores" optional="false" type="data" format="tabular" help="nucleotide_mutation_scores.tsv"/>
        <param label="amino acid mutation scores" name="amino_acid_mutation_scores" optional="false" type="data" format="tabular" help="amino_acid_mutation_scores.tsv"/>
        <param argument="--targenes" label="Comma separated string of HUGO targene symbols" name="targenes" optional="False" type="text" value="ERBB2_MUT,PIK3CA_MUT,KRAS_MUT,AKT1_MUT"/>
        <param argument="--path_genes" label="string of the genes to extract or genelist file" name="path_genes" optional="true" type= "data" format="txt"/>
        <param argument="--ccle_rnaseq" label="Filename ccle rnaseq data" name="ccle_rnaseq" optional="false" type="data" format="tabular" help="data/ccle_rnaseq_genes_rpkm_20180929_mod.tsv"/>
        <param argument="--ccle_mut" label="Filename ccle mutational data" name="ccle_mut" optional="true" type="data" format="txt" help="data/CCLE_MUT_CNA_AMP_DEL_binary_Revealer.gct"/>
        <param argument="--ccle_maf" label="Filename ccle variant data" name="ccle_maf"  optional="true" type="data" format="txt" help="data/CCLE_DepMap_18Q1_maf_20180207.txt" />
        <param argument="--gdsc_rnaseq" label="Filename gdsc rnaseq data" name="gdsc_rnaseq" optional="false" type="data" format="tabular" help="data/GDSC_EXP_CCLE_converted_name.tsv"/>
        <param argument="--gdsc_mut" label="Filename gdsc mutational data" name="gdsc_mut" optional="true" type="data" format="tabular" help="data/GDSC_CCLE_common_mut_cnv_binary.tsv"/>
        <param argument="--gdsc1_phar" label="Filename for gdsc1 pharmacological data file" name="gdsc1_phar" optional="false" type="data" format="txt" help="data/gdsc1_ccle_pharm_fitted_dose_data.txt"/>
        <param argument="--gdsc2_phar" label="Filename for gdsc2 pharmacological data file" name="gdsc2_phar" optional="false" type="data" format="txt" help="data/gdsc2_ccle_pharm_fitted_dose_data.txt"/>
    </inputs>
    <outputs>
        <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)"/>
        <data format="png" name="ccle_histogram" label="${tool.name} on ${on_string} (ccle_histogram.png)" from_work_dir="classifier/figures/ccle_histogram.png"/>
        <data format="tabular" name="ccle_targene_classifier_scores" label="${tool.name} on ${on_string} (ccle_targene_classifier_scores.tsv)" from_work_dir="classifier/tables/ccle_targene_classifier_scores.tsv"/>
        <data format="pdf" name="ccle_targene_WT_MUT_predictions" label="${tool.name} on ${on_string} (ccle_targene_WT_MUT_predictions.pdf)" from_work_dir="classifier/figures/cell_line/ccle_targene_WT_MUT_predictions.pdf"/>
        <data format="csv" name="updated_data_nucleotide_scores" label="${tool.name} on ${on_string} (updated_data_nucleotide_scores.csv)" from_work_dir="classifier/tables/updated_data_nucleotide_scores.csv"/>
        <data format="csv" name="updated_data_aminoacid_scores" label="${tool.name} on ${on_string} (updated_data_aminoacid_scores.csv)" from_work_dir="classifier/tables/updated_data_aminoacid_scores.csv"/>
        <data format="png" name="gdsc_scores_histogram" label="${tool.name} on ${on_string} (gdsc_scores_histogram.png)" from_work_dir="classifier/figures/gdsc_scores_histogram.png"/>
        <data format="tabular" name="gdsc_targene_classifier_scores" label="${tool.name} on ${on_string} (gdsc_targene_classifier_scores.tsv)" from_work_dir="classifier/tables/gdsc_targene_classifier_scores.tsv"/>
        <data format="pdf" name="gdsc_targene_WT_MUT_predictions" label="${tool.name} on ${on_string} (gdsc_targene_WT_MUT_predictions.pdf)" from_work_dir="classifier/figures/cell_line/gdsc_targene_WT_MUT_predictions.pdf"/>
        <data format="tabular" name="gdsc1_targene_pharmacology_predictions" label="${tool.name} on ${on_string} (gdsc1_targene_pharmacology_predictions.tsv)" from_work_dir="classifier/tables/gdsc1_targene_pharmacology_predictions.tsv"/>
        <data format="tabular" name="gdsc2_targene_pharmacology_predictions" label="${tool.name} on ${on_string} (gdsc2_targene_pharmacology_predictions.tsv)" from_work_dir="classifier/tables/gdsc2_targene_pharmacology_predictions.tsv"/>
        <data format="tabular" name="gdsc1_ccle_targene_pharmacology_predictions" label="${tool.name} on ${on_string} (gdsc1_ccle_targene_pharmacology_predictions.tsv)" from_work_dir="classifier/tables/gdsc1_ccle_targene_pharmacology_predictions.tsv"/>
        <data format="tabular" name="gdsc2_ccle_targene_pharmacology_predictions" label="${tool.name} on ${on_string} (gdsc2_ccle_targene_pharmacology_predictions.tsv)" from_work_dir="classifier/tables/gdsc2_ccle_targene_pharmacology_predictions.tsv"/>
    </outputs>
    <tests>
        <test>
          <param name="classifier_summary" value="classifier_summary.txt" ftype="txt"/>
          <param name="pancan_classifier_coefficients" value="classifier_coefficients.tsv" ftype="tabular"/>
          <param name="nucleotide_mutation_scores" value="nucleotide_mutation_scores.tsv" ftype="tabular"/>
          <param name="amino_acid_mutation_scores" value="amino_acid_mutation_scores.tsv" ftype="tabular"/>
          <param name="targenes" value="ERBB2_MUT,PIK3CA_MUT,KRAS_MUT,AKT1_MUT"/>
          <param name="path_genes" value="path_genes.txt" ftype="txt"/>
          <param name="ccle_rnaseq" value="ccle_rnaseq_genes_rpkm_20180929_mod_t5p.tsv.gz" ftype="tabular"/>
          <param name="ccle_mut" value="CCLE_MUT_CNA_AMP_DEL_binary_Revealer.gct.gz" ftype="tabular"/>
          <param name="ccle_maf" value="CCLE_DepMap_18Q1_maf_20180207_t1p.txt.gz" ftype="txt"/>
          <param name="gdsc_rnaseq" value="GDSC_EXP_CCLE_converted_name_t10p.tsv.gz" ftype="tabular"/>
          <param name="gdsc_mut" value="GDSC_CCLE_common_mut_cnv_binary.tsv.gz" ftype="tabular"/>
          <param name="gdsc1_phar" value="gdsc1_ccle_pharm_fitted_dose_data_t10p.txt.gz" ftype="txt"/>
          <param name="gdsc2_phar" value="gdsc2_ccle_pharm_fitted_dose_data_t10p.txt.gz" ftype="txt"/>
          <output name="log" file="targene_cell_line_predictions_Log.txt" lines_diff="2"/>
          <output name="ccle_histogram" file="ccle_histogram.png" compare="sim_size" delta="50"/>
          <output name="ccle_targene_classifier_scores" file="ccle_targene_classifier_scores.tsv" />
          <output name="ccle_targene_WT_MUT_predictions" file="ccle_targene_WT_MUT_predictions.pdf" compare="sim_size" delta="100"/>
          <output name="updated_data_nucleotide_scores" file="updated_data_nucleotide_scores.csv" />
          <output name="updated_data_aminoacid_scores" file="updated_data_aminoacid_scores.csv" />
          <output name="gdsc_scores_histogram" file="gdsc_scores_histogram.png" />
          <output name="gdsc_targene_classifier_scores" file="gdsc_targene_classifier_scores.tsv" />
          <output name="gdsc_targene_WT_MUT_predictions" file="gdsc_targene_WT_MUT_predictions.pdf" compare="sim_size" delta="50"/>
          <output name="gdsc1_targene_pharmacology_predictions">
            <assert_contents>
                <has_line line="&#009;GDSC1_cell_line&#009;NLME_CURVE_ID&#009;COSMIC_ID&#009;SANGER_MODEL_ID&#009;TCGA_DESC&#009;DRUG_ID&#009;Compound&#009;PUTATIVE_TARGET&#009;PATHWAY_NAME&#009;MIN_CONC&#009;MAX_CONC&#009;LN_IC50&#009;AUC&#009;RMSE&#009;Z_SCORE&#009;tissue&#009;ERBB2_MUT&#009;PIK3CA_MUT&#009;KRAS_MUT&#009;AKT1_MUT&#009;targene_status&#009;weight&#009;sample_name&#009;predictions" />
                <has_n_columns n="25" />
                <has_n_lines n="10281" />
            </assert_contents>
          </output>
          <output name="gdsc2_targene_pharmacology_predictions">
            <assert_contents>
                <has_line line="&#009;GDSC1_cell_line&#009;NLME_CURVE_ID&#009;COSMIC_ID&#009;SANGER_MODEL_ID&#009;TCGA_DESC&#009;DRUG_ID&#009;Compound&#009;PUTATIVE_TARGET&#009;PATHWAY_NAME&#009;MIN_CONC&#009;MAX_CONC&#009;LN_IC50&#009;AUC&#009;RMSE&#009;Z_SCORE&#009;tissue&#009;ERBB2_MUT&#009;PIK3CA_MUT&#009;KRAS_MUT&#009;AKT1_MUT&#009;targene_status&#009;weight&#009;sample_name&#009;predictions" />
                <has_n_columns n="25" />
                <has_n_lines n="10281" />
            </assert_contents>
          </output>
          <output name="gdsc1_ccle_targene_pharmacology_predictions" file="gdsc1_ccle_targene_pharmacology_predictions.tsv" />
          <output name="gdsc2_ccle_targene_pharmacology_predictions" file="gdsc2_ccle_targene_pharmacology_predictions.tsv" />
        </test>
    </tests>
    <help><![CDATA[
      
      **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/viz/papaa_targene_cell_line_predictions_mod.py:**
        
        **Inputs:**
          --targenes  comma separated string of HUGO symbols for target genes or targenes_list.csv file
          --path_genes  comma separated string of HUGO symbols for all genes in the target pathway or path_genes.txt file
          --classifier_summary  String of the location of classifier_summary file
          --ccle_rnaseq   Filename of CCLE gene expression data file
          --ccle_mut  Filename of CCLE cell lines/gene mutations data file
          --ccle_maf  Filename of CCLE mutational variant level data file
          --gdsc_rnaseq   Filename of GDSC gene expression data file
          --gdsc_mut  Filename of GDSC cell lines/gene mutations data file
          --gdsc1_phar  Filename of GDSC1 pharmacological response data
          --gdsc2_phar  Filename of GDSC2 pharmacological response data

        **Outputs:**
          Generate predictions for CCLE data using targene classifier(ccle_histogram.png)  

          Generate classifier scores for CCLE cell lines and combines CCLE mutational data and variant data with classifier scores (ccle_targene_classifier_scores.tsv)  

          Performs t-test on classifier weights across targene mutant vs targene wildtype cell-line groups(ccle_targene_WT_MUT_predictions.pdf)  

          Add CCLE nucleotide scores at variant level and update nucleotide_mutation_scores.tsv (updated_data_nucleotide_scores.csv)  

          Add CCLE protein scores at variant level and update aminoacid_mutation_scores.tsv (updated_data_aminoacid_scores.csv)  

          Generate predictions for GDSC data using targene classifier(gdsc_scores_histogram.png)  

          Generate classifier scores for GDSC cell lines and combines CCLE mutational data and variant data with classifier scores (gdsc_targene_classifier_scores.tsv)  

          Performs t-test on classifier weights across targene mutant vs targene wildtype cell-line groups(gdsc_targene_WT_MUT_predictions.pdf)  

          Apply GDSC classifier scores to evaluate GDSC1 pharmacological data response(gdsc1_targene_pharmacology_predictions.tsv)  

          Apply GDSC classifier scores to evaluate GDSC2 pharmacological data response(gdsc2_targene_pharmacology_predictions.tsv)  

          Apply CCLE classifier scores to evaluate GDSC1 pharmacological data response(gdsc1_ccle_targene_pharmacology_predictions.tsv)  

          Apply CCLE classifier scores to evaluate GDSC2 pharmacological data response(gdsc2_ccle_targene_pharmacology_predictions.tsv) ]]>
    </help>
    <expand macro="citations" />
</tool>