Mercurial > repos > vijay > pancancer_targene_summary_figures

changeset 0:d533f991e22e draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository http://github.com/nvk747/papaa/galaxy/ commit 954b283ef7f82f59f55476a4b3a230d655187ac1"
author vijay
date Wed, 16 Dec 2020 23:32:26 +0000
parents
children
files macros.xml targene_summary_figures.xml
diffstat 2 files changed, 328 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Wed Dec 16 23:32:26 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_summary_figures.xml	Wed Dec 16 23:32:26 2020 +0000
@@ -0,0 +1,99 @@
+<tool id="pancancer_targene_summary_figures" name="PAPAA: PanCancer targene summary figures" version="@VERSION@">
+  <description>Visualize targene summary</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <expand macro="stdio"/>
+  <version_command><![CDATA['papaa_targene_summary_figures.R' --version 2>&1 | grep PAPAA]]></version_command>
+  <command><![CDATA[
+    mkdir 'classifier' &&
+    mkdir -p 'classifier/figures' && 
+    mkdir -p 'classifier/tables' &&
+        ln -s '${classifier_summary}' 'classifier/classifier_summary.txt' &&
+        ln -s '${pancan_classifier_coefficients}' 'classifier/classifier_coefficients.tsv' &&
+        ln -s '${summary_counts}' 'classifier/summary_counts.csv' &&
+        ln -s '${mutation_classification_scores}' 'classifier/tables/mutation_classification_scores.tsv' &&
+        ln -s '${path_events_per_sample}' 'classifier/tables/path_events_per_sample.tsv' &&
+        ln -s '${all_gene_metric_ranks}' 'classifier/tables/all_gene_metric_ranks.tsv' &&
+    papaa_targene_summary_figures.R
+    --classifier_summary 'classifier'
+    #if $seed and $seed is not None:
+    --seed '$seed'
+    #end if
+    > '${log}'
+    ]]>
+  </command>
+  <inputs>
+    <param argument="--classifier_summary" label="Classifier data" name="classifier_summary" optional="false" type="data" format="txt" help="classifer_summary.txt"/>
+    <param label="pancancer classifier coefficients" name="pancan_classifier_coefficients" optional="false" type="data" format="tabular" help="classifier_coefficients.tsv"/>
+    <param argument="--seed" label="option to set seed" name="seed" optional="true" type="integer" value="123"/>
+    <param label="summary counts" name="summary_counts" optional="false" type="data" format="csv" help="summary_counts.csv"/>
+    <param label="mutation classification scores" name="mutation_classification_scores" optional="false" type="data" format="tabular" help="mutation_classification_scores.tsv"/>
+    <param label="path events per sample" name="path_events_per_sample" optional="false" type="data" format="tabular" help="path_events_per_sample.tsv"/>
+    <param label="all gene metric ranks" name="all_gene_metric_ranks" optional="false" type="data" format="tabular" help="all_gene_metric_ranks.tsv"/>
+  </inputs>
+  <outputs>
+    <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)"/>
+    <data format="pdf" name="targene_heatmap" label="${tool.name} on ${on_string} (targene_heatmap.pdf)" from_work_dir="classifier/figures/targene_heatmap.pdf"/>
+    <data format="pdf" name="all_targene_heatmap" label="${tool.name} on ${on_string} (all_targene_heatmap.pdf)" from_work_dir="classifier/figures/all_targene_heatmap.pdf"/>
+    <data format="pdf" name="targene_coef_plot" label="${tool.name} on ${on_string} (targene_coef_plot.pdf)" from_work_dir="classifier/figures/targene_coef_plot.pdf"/>
+    <data format="pdf" name="variant_OG_fill_map" label="${tool.name} on ${on_string} (variant_OG_fill_map.pdf)" from_work_dir="classifier/figures/variant_OG_fill_map.pdf"/>
+    <data format="pdf" name="variant_TSG_fill_map" label="${tool.name} on ${on_string} (variant_TSG_fill_map.pdf)" from_work_dir="classifier/figures/variant_TSG_fill_map.pdf"/>
+    <data format="pdf" name="aupr_distribution" label="${tool.name} on ${on_string} (aupr_distribution.pdf)" from_work_dir="classifier/figures/aupr_distribution.pdf"/>
+    <data format="pdf" name="auroc_distribution" label="${tool.name} on ${on_string} (auroc_distribution.pdf)" from_work_dir="classifier/figures/auroc_distribution.pdf"/>
+    <data format="pdf" name="targene_pathway_events_counts" label="${tool.name} on ${on_string} (targene_pathway_events_counts.pdf)" from_work_dir="classifier/figures/targene_pathway_events_counts.pdf"/>
+    <data format="txt" name="targene_pathway_variant_AUPR_ttest" label="${tool.name} on ${on_string} (targene_pathway_variant_AUPR_ttest.txt)" from_work_dir="classifier/tables/targene_pathway_variant_AUPR_ttest.txt"/>
+    <data format="tabular" name="amino_acid_mutation_scores" label="${tool.name} on ${on_string} (amino_acid_mutation_scores.tsv)" from_work_dir="classifier/tables/amino_acid_mutation_scores.tsv"/>
+    <data format="tabular" name="nucleotide_mutation_scores" label="${tool.name} on ${on_string} (nucleotide_mutation_scores.tsv)" from_work_dir="classifier/tables/nucleotide_mutation_scores.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="summary_counts" value="summary_counts.csv" ftype="csv"/>
+          <param name="all_gene_metric_ranks" value="all_gene_metric_ranks.tsv" ftype="tabular"/>
+          <param name="mutation_classification_scores" value="mutation_classification_scores.tsv" ftype="tabular"/>
+          <param name="path_events_per_sample" value="path_events_per_sample.tsv" ftype="tabular"/>
+          <param name="all_gene_metric_ranks" value="all_gene_metric_ranks.tsv" ftype="tabular"/>
+          <output name="log" file="targene_summary_figures_Log.txt"/>
+          <output name="targene_heatmap" file="targene_heatmap.pdf" compare="sim_size" delta="50"/>
+          <output name="all_targene_heatmap" file="all_targene_heatmap.pdf" compare="sim_size" delta="50"/>
+          <output name="targene_coef_plot" file="targene_coef_plot.pdf" compare="sim_size" delta="50"/>
+          <output name="variant_OG_fill_map" file="variant_OG_fill_map.pdf" compare="sim_size" delta="50"/>
+          <output name="aupr_distribution" file="aupr_distribution.pdf" compare="sim_size" delta="50"/>
+          <output name="variant_TSG_fill_map" file="variant_TSG_fill_map.pdf" compare="sim_size" delta="50"/>
+          <output name="auroc_distribution" file="auroc_distribution.pdf" compare="sim_size" delta="50"/>
+          <output name="targene_pathway_events_counts" file="targene_pathway_events_counts.pdf" compare="sim_size" delta="50"/>
+          <output name="targene_pathway_variant_AUPR_ttest" file="targene_pathway_variant_AUPR_ttest.txt" compare="sim_size" delta="50"/>
+          <output name="amino_acid_mutation_scores" file="amino_acid_mutation_scores.tsv" compare="sim_size" delta="50"/>
+          <output name="nucleotide_mutation_scores" file="nucleotide_mutation_scores.tsv" compare="sim_size" delta="50"/>
+        </test>
+    </tests>
+  <help><![CDATA[
+    **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/papaa_targene_summary_figures.R:**
+
+      **Inputs:**
+          --classifier_summary   String of the location of classifier data
+          --seed  value specifies the initial value of the random number seed default: 1234
+      
+      **Outputs:**
+          Heatmap for mutation and gain proportions for the genes used in model across all the TCGA cancer types (all_targene_heatmap.pdf)
+
+          Heatmap for total mutation and total gain proportions for the genes used in model across all the TCGA cancer types (targene_heatmap.pdf")
+
+          Gene weights/Coefficients contributing to the model (targene_coef_plot.pdf)  
+
+          Plot distributions of predictions according to variant classification for OG and TSG ("variant_OG_fill_map.pdf" and "variant_TSG_fill_map.pdf")  
+
+          Targene pathway events counts ("targene_pathway_events_counts.pdf")  
+
+          Performance Metrics Distribution across pathway members ("aupr_distribution.pdf" and "auroc_distribution.pdf")
+          T-Test for AUPR between targene pathway genes and Other genes ("targene_pathway_variant_AUPR_ttest.txt") 
+
+          Extracting sample classifier scores for nucleotide level alterations in each sample and generate "nucleotide_mutation_scores.tsv" file
+
+          Extracting sample classifier scores for amino-acid level alterations in each sample and generate "amino_acid_mutation_scores.tsv" file ]]>
+    </help>
+    <expand macro="citations" />
+</tool>