changeset 0:872aab514d37 draft default tip

"planemo upload for repository http://github.com/nvk747/papaa/galaxy/ commit 954b283ef7f82f59f55476a4b3a230d655187ac1"
author vijay
date Wed, 16 Dec 2020 23:30:22 +0000
parents
children
files macros.xml targene_cell_line_predictions.xml
diffstat 2 files changed, 394 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Wed Dec 16 23:30:22 2020 +0000
@@ -0,0 +1,229 @@
+<macros>
+    <token name="@VERSION@">0.1.9</token>
+
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@VERSION@">papaa</requirement>
+        </requirements>
+    </xml>
+
+    <xml name="stdio">
+        <stdio>
+             <exit_code level="fatal" range="1:"/>
+        </stdio>
+    </xml>
+
+    <xml name="inputs_basic">
+        <param argument="--x_matrix" label="Filename of features to use in model" name="x_matrix" optional="true" type="data" format="tabular" help="data/pancan_rnaseq_freeze.tsv.gz"/>
+        <yield/>
+        <param argument="--filename_mut" label="Filename mutations" name="filename_mut" optional="true" type="data" format="tabular" help="data/pancan_mutation_freeze.tsv.gz"/>
+        <param argument="--filename_mut_burden" label="Filename of mutation burden" name="filename_mut_burden" optional="true" type="data" format="tabular" help="data/mutation_burden_freeze.tsv"/>
+        <param argument="--filename_sample" label="Filename of sample" name="filename_sample" optional="true" type="data" format="tabular" help="data/sample_freeze.tsv"/>
+    </xml>
+
+    <token name="@INPUTS_BASIC@"><![CDATA[
+        #if $x_matrix and $x_matrix is not None:
+        --x_matrix '$x_matrix'
+        #end if
+        #if $filename_mut and $filename_mut is not None:
+        --filename_mut '$filename_mut'
+        #end if
+        #if $filename_mut_burden and $filename_mut_burden is not None:
+        --filename_mut_burden '$filename_mut_burden'
+        #end if
+        #if $filename_sample and $filename_sample is not None:
+        --filename_sample '$filename_sample'
+        #end if
+        ]]>
+    </token>
+
+    <xml name="inputs_genes_diseases">
+        <param argument="--genes" label="Comma separated string of HUGO gene symbols" name="genes" optional="False" type="text" value="ERBB2,PIK3CA,KRAS,AKT1"/>
+        <param argument="--diseases" label="Comma sep string of TCGA disease acronyms. If no arguments are passed, filtering will default to options given in --filter_count and --filter_prop." name="diseases" optional="true" type="text" value="BLCA,BRCA,CESC,COAD,ESCA,LUAD,LUSC,OV,PRAD,READ,STAD,UCEC,UCS"/>
+    </xml>
+
+    <token name="@INPUTS_GENES_DISEASES@"><![CDATA[
+        #if $genes and $genes is not None:
+        --genes '$genes'
+        #end if
+        #if $diseases and str($diseases) != '':
+        --diseases '$diseases'
+        #end if
+        ]]>
+    </token>
+
+
+    <xml name="input_filename_raw_mut">
+        <param argument="--filename_raw_mut" label="Filename of raw mut MAF" name="filename_raw_mut" optional="true" type="data" format="tabular" help="data/raw/mc3.v0.2.8.PUBLIC.maf"/>
+    </xml>
+
+    <token name="@INPUT_FILENAME_RAW_MUT@"><![CDATA[
+        #if $filename_raw_mut and $filename_raw_mut is not None:
+        --filename_raw_mut '$filename_raw_mut'
+        #end if
+        ]]>
+    </token>
+
+
+    <xml name="input_filename_burden">
+        <param argument="--filename_burden" label="Burden file" name="filename_burden" optional="true" type="data" format="tabular" help="data/seg_based_scores.tsv"/>
+    </xml>
+
+    <token name="@INPUT_FILENAME_BURDEN@"><![CDATA[
+        #if $filename_burden and $filename_burden is not None:
+        --filename_burden '$filename_burden'
+        #end if
+        ]]>        
+    </token>
+
+    <xml name="input_filename_snaptron_samples">
+        <param argument="--sample_file" label="SNAPTRON samples" name="sample_file" optional="true" type="data" format="tabular" help="scripts/snaptron/samples.tsv.gz"/>
+    </xml>
+
+    <token name="@INPUT_FILENAME_SNAPTRON_SAMPLES@"><![CDATA[
+        #if $sample_file and $sample_file is not None:
+        --sample_file '$sample_file'
+        #end if
+        ]]>       
+    </token>
+
+
+    <xml name="input_filename_snaptron_junctions">
+        <param argument="--junction_file" label="SNAPTRON junctions" name="junction_file" optional="true" type="data" format="tabular" help="scripts/snaptron/tp53_junctions.txt.gz"/>
+    </xml>
+
+    <token name="@INPUT_FILENAME_SNAPTRON_JUNCTIONS@"><![CDATA[
+        #if $junction_file and $junction_file is not None:
+        --junction_file '$junction_file'
+        #end if
+        ]]>    
+    </token>
+
+    <xml name="inputs_copy_number_file">
+        <param argument="--filename_copy_loss" label="File with Copy number loss" name="filename_copy_loss" optional="true" type="data" format="tabular" help="data/copy_number_loss_status.tsv.gz"/>
+        <param argument="--filename_copy_gain" label="File with Copy number gain" name="filename_copy_gain" optional="true" type="data" format="tabular" help="data/copy_number_gain_status.tsv.gz"/>
+    </xml>
+
+    <xml name="inputs_copy_number_class_file">
+        <expand macro="inputs_copy_number_file" />
+        <param argument="--filename_cancer_gene_classification" label="File with cancer gene classification table" name="filename_cancer_gene_classification" optional="true" type="data" format="tabular" help="data/cosmic_cancer_classification.tsv"/>
+    </xml>
+
+    <xml name="inputs_copy_number_file_conditional">
+        <conditional name="copy_number_conditional">
+          <param argument="--copy_number" checked="false" label="Supplement Y matrix with copy number events" name="copy_number" type="boolean" truevalue="--copy_number" falsevalue=""/>
+          <when value="--copy_number">
+            <expand macro="inputs_copy_number_file" />
+          </when>
+          <when value=""/>
+        </conditional>
+    </xml>
+
+    <xml name="inputs_copy_number_class_file_conditional">
+        <conditional name="copy_number_conditional">
+          <param argument="--copy_number" checked="false" label="Supplement Y matrix with copy number events" name="copy_number" type="boolean" truevalue="--copy_number" falsevalue=""/>
+          <when value="--copy_number">
+            <expand macro="inputs_copy_number_class_file" />
+          </when>
+          <when value=""/>
+        </conditional>
+    </xml>
+
+    <token name="@INPUTS_COPY_NUMBER_FILE_PREFIX@"><![CDATA[
+        #set $copy_number_conditional = type('',(object,),{'filename_copy_loss':$filename_copy_loss,'filename_copy_gain':$filename_copy_gain})()
+                ]]>
+    </token>
+
+    <token name="@INPUTS_COPY_NUMBER_FILE@"><![CDATA[
+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:
+        --filename_copy_loss '$copy_number_conditional.filename_copy_loss'
+        #end if
+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:
+        --filename_copy_gain '$copy_number_conditional.filename_copy_gain'
+        #end if
+        ]]>
+    </token>
+    
+    <token name="@INPUTS_COPY_NUMBER_FILE_CONDITIONAL@"><![CDATA[
+        #if $copy_number_conditional.copy_number
+        $copy_number_conditional.copy_number
+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:
+        --filename_copy_loss '$copy_number_conditional.filename_copy_loss'
+        #end if
+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:
+        --filename_copy_gain '$copy_number_conditional.filename_copy_gain'
+        #end if
+        ##@INPUTS_COPY_NUMBER_FILE@
+        #end if
+        ]]>
+    </token>
+
+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE_PREFIX@"><![CDATA[
+        #set $copy_number_conditional = type('',(object,),{'filename_copy_loss':$filename_copy_loss,'filename_copy_gain':$filename_copy_gain,'filename_cancer_gene_classification':$filename_cancer_gene_classification})()
+        ]]>
+    </token>
+
+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE@"><![CDATA[
+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:
+        --filename_copy_loss '$copy_number_conditional.filename_copy_loss'
+        #end if
+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:
+        --filename_copy_gain '$copy_number_conditional.filename_copy_gain'
+        #end if
+        #if $copy_number_conditional.filename_cancer_gene_classification and $copy_number_conditional.filename_cancer_gene_classification is not None:
+        --filename_cancer_gene_classification '$copy_number_conditional.filename_cancer_gene_classification'
+        #end if
+        ]]>
+    </token>
+    
+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE_CONDITIONAL@"><![CDATA[
+        #if $copy_number_conditional.copy_number
+        $copy_number_conditional.copy_number
+        ##
+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:
+        --filename_copy_loss '$copy_number_conditional.filename_copy_loss'
+        #end if
+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:
+        --filename_copy_gain '$copy_number_conditional.filename_copy_gain'
+        #end if
+        #if $copy_number_conditional.filename_cancer_gene_classification and $copy_number_conditional.filename_cancer_gene_classification is not None:
+        --filename_cancer_gene_classification '$copy_number_conditional.filename_cancer_gene_classification'
+        #end if
+        ##@INPUTS_COPY_NUMBER_CLASS_FILE@
+        #end if
+        ]]> 
+    </token>
+
+    <xml name="input_remove_hyper">
+        <param argument="--remove_hyper" checked="false" label="Remove hypermutated samples" name="remove_hyper" type="boolean" truevalue="--remove_hyper" falsevalue=""/>
+    </xml>
+    <token name="@INPUT_REMOVE_HYPER@"><![CDATA[$remove_hyper]]></token>
+       
+    <xml name="input_alphas">
+        <param argument="--alphas" label="the alphas for parameter sweep" name="alphas" optional="true" type="text" value="0.1,0.13,0.15,0.18,0.2,0.3,0.4,0.6,0.7"/>
+    </xml>
+
+    <token name="@INPUTS_ALPHAS@"><![CDATA[
+        #if $alphas and $alphas is not None:
+        --alphas '$alphas'
+        #end if
+        ]]>
+    </token>
+
+    <xml name="input_l1_ratios">
+        <param argument="--l1_ratios" label="the l1 ratios for parameter sweep" name="l1_ratios" optional="true" type="text" value="0.1,0.125,0.15,0.2,0.25,0.3,0.35"/>
+    </xml>
+
+    <token name="@INPUTS_L1_RATIOS@"><![CDATA[
+        #if $l1_ratios and $l1_ratios is not None:
+        --l1_ratios '$l1_ratios'
+        #end if
+        ]]>
+    </token>
+    <xml name="citations">
+        <citations>
+            <yield />
+        </citations>
+    </xml>
+</macros>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/targene_cell_line_predictions.xml	Wed Dec 16 23:30:22 2020 +0000
@@ -0,0 +1,165 @@
+<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>