Mercurial > repos > vijay > pancancer_within_disease_analysis
changeset 0:99d944bfe9b3 draft default tip
"planemo upload for repository http://github.com/nvk747/papaa/galaxy/ commit 954b283ef7f82f59f55476a4b3a230d655187ac1"
| author | vijay |
|---|---|
| date | Wed, 16 Dec 2020 23:31:13 +0000 |
| parents | |
| children | |
| files | macros.xml within_disease_analysis.xml |
| diffstat | 2 files changed, 369 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Wed Dec 16 23:31:13 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/within_disease_analysis.xml Wed Dec 16 23:31:13 2020 +0000 @@ -0,0 +1,140 @@ +<tool id="pancancer_within_disease_analysis" name="PAPAA: PanCancer within disease analysis" version="@VERSION@"> + <description>within disease analysis</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <version_command><![CDATA['papaa_within_disease_analysis.py' --version]]></version_command> + <command><![CDATA[ + papaa_within_disease_analysis.py + @INPUTS_ALPHAS@ + @INPUTS_L1_RATIOS@ + @INPUT_REMOVE_HYPER@ + @INPUTS_BASIC@ + @INPUTS_GENES_DISEASES@ + @INPUTS_COPY_NUMBER_CLASS_FILE_PREFIX@ + @INPUTS_COPY_NUMBER_CLASS_FILE@ + --classifier_results 'classifier' + #if $seed and $seed is not None: + --seed '$seed' + #end if + #if $num_features and $num_features is not None: + --num_features '$num_features' + #end if + > '${log}' + && papaa_flatten_classifier_directory.py -i 'classifier/within_disease' -o 'classifier_within' + ]]> + </command> + <inputs> + <expand macro="inputs_basic" /> + <expand macro="inputs_genes_diseases" /> + <expand macro="inputs_copy_number_class_file" /> + <expand macro="input_alphas" /> + <expand macro="input_l1_ratios" /> + <expand macro="input_remove_hyper" /> + <param argument="--seed" label="option to set seed" name="seed" optional="true" type="integer" value="1234"/> + <param argument="--num_features" label="Number of MAD genes to include in classifier" name="num_features" optional="true" type="integer" value="8000"/> + </inputs> + <outputs> + <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)" /> + <collection name="classifier_summary" type="list" label="classifier_summary.txt"> + <discover_datasets pattern="(?P<identifier_0>.+)_classifier_summary\.txt" format="txt" directory="classifier_within/within_disease" visible="false" /> + </collection> + <collection name="classifier_coefficients" type="list" label="classifier_coefficients.tsv"> + <discover_datasets pattern="(?P<identifier_0>.+)_classifier_coefficients\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" /> + </collection> + <collection name="pancan_roc_results" type="list" label="pancan_roc_results.tsv"> + <discover_datasets pattern="(?P<identifier_0>.+)_pancan_roc_results\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" /> + </collection> + <collection name="summary_counts" type="list" label="summary_counts.csv"> + <discover_datasets pattern="(?P<identifier_0>.+)_summary_counts\.csv" format="csv" directory="classifier_within/within_disease" visible="false" /> + </collection> + <collection name="within_disease" type="list:list" label="Within disease figures"> + <discover_datasets pattern="(?P<identifier_0>[^_]+)_(?P<identifier_1>.+)\.pdf" format="pdf" directory="classifier_within/within_disease" visible="false" /> + </collection> + <collection name="disease_figures" type="list:list" label="Disease classifier figures"> + <discover_datasets pattern="classifier_(?P<identifier_1>.+)__pred_(?P<identifier_0>.+)\.pdf" format="pdf" directory="classifier_within/disease" visible="false" /> + </collection> + </outputs> + <tests> + <test> + <param name="genes" value="ERBB2,PIK3CA,KRAS,AKT1"/> + <param name="diseases" value="GBM"/> + <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="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="alphas" value="0.1,0.13,0.15,0.18,0.2,0.3,0.4,0.6,0.7"/> + <param name="l1_ratios" value="0.1,0.125,0.15,0.2,0.25,0.3,0.35"/> + <param name="seed" value="1234"/> + <param name="num_features" value="8000"/> + <param name="remove_hyper" value="true"/> + <output name="log"> + <assert_contents> + <has_line line="['ERBB2', 'PIK3CA', 'KRAS', 'AKT1']" /> + <has_line line="GBM" /> + <has_n_lines n="2" /> + </assert_contents> + </output> + <output_collection name="classifier_coefficients" type="list"> + <element name="GBM" file="GBM_108_coef.tabular" ftype="tabular" /> + </output_collection> + <output_collection name="classifier_summary" type="list"> + <element name="GBM" file="GBM_111_summary.txt" ftype="txt" /> + </output_collection> + <output_collection name="pancan_roc_results" type="list"> + <element name="GBM" ftype="tabular"> + <assert_contents> + <has_line line="	fpr	tpr	threshold	train_type	disease" /> + <has_n_columns n="6" /> + <has_n_lines n="253" /> + </assert_contents> + </element> + </output_collection> + <output_collection name="summary_counts" type="list"> + <element name="GBM" file="GBM_106_summary_counts.csv" ftype="csv" /> + </output_collection> + <output_collection name="within_disease" type="list:list"> + <element name="GBM" > + <element name="cv_heatmap" file="GBM_cv_heatmap_103.pdf" compare="sim_size" delta="50"/> + <element name="all_disease_pr" file="GBM_all_disease_pr_101.pdf" compare="sim_size" delta="50" /> + <element name="all_disease_roc" file="GBM_all_disease_roc_102.pdf" compare="sim_size" delta="50"/> + <element name="disease_aupr" file="GBM_disease_aupr_104.pdf" compare="sim_size" delta="50"/> + <element name="disease_auroc" file="GBM_disease_auroc_105.pdf" compare="sim_size" delta="50"/> + </element> + </output_collection> + <output_collection name="disease_figures" type="list:list"> + <element name="GBM" > + <element name="pr" file="GBM_pr_99.pdf" compare="sim_size" delta="50"/> + <element name="roc" file="GBM_roc_100.pdf" compare="sim_size" delta="50"/> + </element> + </output_collection> + </test> + </tests> + <help><![CDATA[ + **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/papaa_within_disease_analysis.py:** + + **Inputs:** + --genes comma separated string of HUGO symbols for target genes or targenes_list.csv file + --diseases Comma separated diseases list in a file + --alphas The alphas for parameter sweep + --l1_ratios The l1 ratios for parameter sweep + --remove_hyper Remove hypermutated samples + --classifier_results String of location to classification folder extending to individual diseases + --x_matrix Filename of features to use in model + --filename_mut 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:** + ROC curves, AUROC across diseases, and classifier coefficients for individual diseases ]]> + </help> + <expand macro="citations" /> +</tool>