Repository 'pancancer_within_disease_analysis'
hg clone https://toolshed.g2.bx.psu.edu/repos/vijay/pancancer_within_disease_analysis

Changeset 0:99d944bfe9b3 (2020-12-16)
Commit message:
"planemo upload for repository http://github.com/nvk747/papaa/galaxy/ commit 954b283ef7f82f59f55476a4b3a230d655187ac1"
added:
macros.xml
within_disease_analysis.xml
b
diff -r 000000000000 -r 99d944bfe9b3 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Wed Dec 16 23:31:13 2020 +0000
[
b'@@ -0,0 +1,229 @@\n+<macros>\n+    <token name="@VERSION@">0.1.9</token>\n+\n+    <xml name="requirements">\n+        <requirements>\n+            <requirement type="package" version="@VERSION@">papaa</requirement>\n+        </requirements>\n+    </xml>\n+\n+    <xml name="stdio">\n+        <stdio>\n+             <exit_code level="fatal" range="1:"/>\n+        </stdio>\n+    </xml>\n+\n+    <xml name="inputs_basic">\n+        <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"/>\n+        <yield/>\n+        <param argument="--filename_mut" label="Filename mutations" name="filename_mut" optional="true" type="data" format="tabular" help="data/pancan_mutation_freeze.tsv.gz"/>\n+        <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"/>\n+        <param argument="--filename_sample" label="Filename of sample" name="filename_sample" optional="true" type="data" format="tabular" help="data/sample_freeze.tsv"/>\n+    </xml>\n+\n+    <token name="@INPUTS_BASIC@"><![CDATA[\n+        #if $x_matrix and $x_matrix is not None:\n+        --x_matrix \'$x_matrix\'\n+        #end if\n+        #if $filename_mut and $filename_mut is not None:\n+        --filename_mut \'$filename_mut\'\n+        #end if\n+        #if $filename_mut_burden and $filename_mut_burden is not None:\n+        --filename_mut_burden \'$filename_mut_burden\'\n+        #end if\n+        #if $filename_sample and $filename_sample is not None:\n+        --filename_sample \'$filename_sample\'\n+        #end if\n+        ]]>\n+    </token>\n+\n+    <xml name="inputs_genes_diseases">\n+        <param argument="--genes" label="Comma separated string of HUGO gene symbols" name="genes" optional="False" type="text" value="ERBB2,PIK3CA,KRAS,AKT1"/>\n+        <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"/>\n+    </xml>\n+\n+    <token name="@INPUTS_GENES_DISEASES@"><![CDATA[\n+        #if $genes and $genes is not None:\n+        --genes \'$genes\'\n+        #end if\n+        #if $diseases and str($diseases) != \'\':\n+        --diseases \'$diseases\'\n+        #end if\n+        ]]>\n+    </token>\n+\n+\n+    <xml name="input_filename_raw_mut">\n+        <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"/>\n+    </xml>\n+\n+    <token name="@INPUT_FILENAME_RAW_MUT@"><![CDATA[\n+        #if $filename_raw_mut and $filename_raw_mut is not None:\n+        --filename_raw_mut \'$filename_raw_mut\'\n+        #end if\n+        ]]>\n+    </token>\n+\n+\n+    <xml name="input_filename_burden">\n+        <param argument="--filename_burden" label="Burden file" name="filename_burden" optional="true" type="data" format="tabular" help="data/seg_based_scores.tsv"/>\n+    </xml>\n+\n+    <token name="@INPUT_FILENAME_BURDEN@"><![CDATA[\n+        #if $filename_burden and $filename_burden is not None:\n+        --filename_burden \'$filename_burden\'\n+        #end if\n+        ]]>        \n+    </token>\n+\n+    <xml name="input_filename_snaptron_samples">\n+        <param argument="--sample_file" label="SNAPTRON samples" name="sample_file" optional="true" type="data" format="tabular" help="scripts/snaptron/samples.tsv.gz"/>\n+    </xml>\n+\n+    <token name="@INPUT_FILENAME_SNAPTRON_SAMPLES@"><![CDATA[\n+        #if $sample_file and $sample_file is not None:\n+        --sample_file \'$sample_file\'\n+        #end if\n+        ]]>       \n+    </token>\n+\n+\n+    <xml name="input_filename_snaptron_junctions">\n+        <param argument="--junction_file" label="SNAPTRON junctions" name="junct'..b'\'\n+        #end if\n+        ]]>\n+    </token>\n+    \n+    <token name="@INPUTS_COPY_NUMBER_FILE_CONDITIONAL@"><![CDATA[\n+        #if $copy_number_conditional.copy_number\n+        $copy_number_conditional.copy_number\n+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:\n+        --filename_copy_loss \'$copy_number_conditional.filename_copy_loss\'\n+        #end if\n+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:\n+        --filename_copy_gain \'$copy_number_conditional.filename_copy_gain\'\n+        #end if\n+        ##@INPUTS_COPY_NUMBER_FILE@\n+        #end if\n+        ]]>\n+    </token>\n+\n+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE_PREFIX@"><![CDATA[\n+        #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})()\n+        ]]>\n+    </token>\n+\n+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE@"><![CDATA[\n+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:\n+        --filename_copy_loss \'$copy_number_conditional.filename_copy_loss\'\n+        #end if\n+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:\n+        --filename_copy_gain \'$copy_number_conditional.filename_copy_gain\'\n+        #end if\n+        #if $copy_number_conditional.filename_cancer_gene_classification and $copy_number_conditional.filename_cancer_gene_classification is not None:\n+        --filename_cancer_gene_classification \'$copy_number_conditional.filename_cancer_gene_classification\'\n+        #end if\n+        ]]>\n+    </token>\n+    \n+    <token name="@INPUTS_COPY_NUMBER_CLASS_FILE_CONDITIONAL@"><![CDATA[\n+        #if $copy_number_conditional.copy_number\n+        $copy_number_conditional.copy_number\n+        ##\n+        #if $copy_number_conditional.filename_copy_loss and $copy_number_conditional.filename_copy_loss is not None:\n+        --filename_copy_loss \'$copy_number_conditional.filename_copy_loss\'\n+        #end if\n+        #if $copy_number_conditional.filename_copy_gain and $copy_number_conditional.filename_copy_gain is not None:\n+        --filename_copy_gain \'$copy_number_conditional.filename_copy_gain\'\n+        #end if\n+        #if $copy_number_conditional.filename_cancer_gene_classification and $copy_number_conditional.filename_cancer_gene_classification is not None:\n+        --filename_cancer_gene_classification \'$copy_number_conditional.filename_cancer_gene_classification\'\n+        #end if\n+        ##@INPUTS_COPY_NUMBER_CLASS_FILE@\n+        #end if\n+        ]]> \n+    </token>\n+\n+    <xml name="input_remove_hyper">\n+        <param argument="--remove_hyper" checked="false" label="Remove hypermutated samples" name="remove_hyper" type="boolean" truevalue="--remove_hyper" falsevalue=""/>\n+    </xml>\n+    <token name="@INPUT_REMOVE_HYPER@"><![CDATA[$remove_hyper]]></token>\n+       \n+    <xml name="input_alphas">\n+        <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"/>\n+    </xml>\n+\n+    <token name="@INPUTS_ALPHAS@"><![CDATA[\n+        #if $alphas and $alphas is not None:\n+        --alphas \'$alphas\'\n+        #end if\n+        ]]>\n+    </token>\n+\n+    <xml name="input_l1_ratios">\n+        <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"/>\n+    </xml>\n+\n+    <token name="@INPUTS_L1_RATIOS@"><![CDATA[\n+        #if $l1_ratios and $l1_ratios is not None:\n+        --l1_ratios \'$l1_ratios\'\n+        #end if\n+        ]]>\n+    </token>\n+    <xml name="citations">\n+        <citations>\n+            <yield />\n+        </citations>\n+    </xml>\n+</macros>\n+\n'
b
diff -r 000000000000 -r 99d944bfe9b3 within_disease_analysis.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/within_disease_analysis.xml Wed Dec 16 23:31:13 2020 +0000
[
b'@@ -0,0 +1,140 @@\n+<tool id="pancancer_within_disease_analysis" name="PAPAA: PanCancer within disease analysis" version="@VERSION@">\n+  <description>within disease analysis</description>\n+  <macros>\n+    <import>macros.xml</import>\n+  </macros>\n+  <expand macro="requirements"/>\n+  <expand macro="stdio"/>\n+  <version_command><![CDATA[\'papaa_within_disease_analysis.py\' --version]]></version_command>\n+  <command><![CDATA[\n+    papaa_within_disease_analysis.py\n+    @INPUTS_ALPHAS@\n+    @INPUTS_L1_RATIOS@\n+    @INPUT_REMOVE_HYPER@\n+    @INPUTS_BASIC@\n+    @INPUTS_GENES_DISEASES@\n+    @INPUTS_COPY_NUMBER_CLASS_FILE_PREFIX@\n+    @INPUTS_COPY_NUMBER_CLASS_FILE@\n+    --classifier_results \'classifier\'\n+    #if $seed and $seed is not None:\n+    --seed \'$seed\'\n+    #end if\n+    #if $num_features and $num_features is not None:\n+    --num_features \'$num_features\'\n+    #end if\n+    > \'${log}\'\n+    && papaa_flatten_classifier_directory.py -i \'classifier/within_disease\' -o \'classifier_within\'\n+   ]]>\n+  </command>\n+  <inputs>\n+    <expand macro="inputs_basic" />\n+    <expand macro="inputs_genes_diseases" />\n+    <expand macro="inputs_copy_number_class_file" />\n+    <expand macro="input_alphas" />\n+    <expand macro="input_l1_ratios" />\n+    <expand macro="input_remove_hyper" />\n+    <param argument="--seed" label="option to set seed" name="seed" optional="true" type="integer" value="1234"/>\n+    <param argument="--num_features" label="Number of MAD genes to include in classifier" name="num_features" optional="true" type="integer" value="8000"/>\n+  </inputs>\n+  <outputs>\n+    <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)" />\n+    <collection name="classifier_summary" type="list" label="classifier_summary.txt">\n+      <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_classifier_summary\\.txt" format="txt" directory="classifier_within/within_disease" visible="false" />\n+    </collection>\n+    <collection name="classifier_coefficients" type="list" label="classifier_coefficients.tsv">\n+      <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_classifier_coefficients\\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" />\n+    </collection>\n+    <collection name="pancan_roc_results" type="list" label="pancan_roc_results.tsv">\n+      <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_pancan_roc_results\\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" />\n+    </collection>\n+    <collection name="summary_counts" type="list" label="summary_counts.csv">\n+      <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_summary_counts\\.csv" format="csv" directory="classifier_within/within_disease" visible="false" />\n+    </collection>\n+    <collection name="within_disease" type="list:list" label="Within disease figures">\n+      <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;.+)\\.pdf" format="pdf" directory="classifier_within/within_disease" visible="false" />\n+    </collection>\n+    <collection name="disease_figures" type="list:list" label="Disease classifier figures">\n+      <discover_datasets pattern="classifier_(?P&lt;identifier_1&gt;.+)__pred_(?P&lt;identifier_0&gt;.+)\\.pdf" format="pdf" directory="classifier_within/disease" visible="false" />\n+    </collection>\n+  </outputs>\n+  <tests>\n+        <test>\n+              <param name="genes" value="ERBB2,PIK3CA,KRAS,AKT1"/>\n+              <param name="diseases" value="GBM"/>\n+              <param name="x_matrix" value="pancan_rnaseq_freeze_t1p.tsv.gz" ftype="tabular"/>\n+              <param name="filename_mut" value="pancan_mutation_freeze_t1p.tsv.gz" ftype="tabular"/>\n+              <param name="filename_mut_burden" value="mutation_burden_freeze.tsv" ftype="tabular"/>\n+              <param name="filename_sample" value="sample_freeze.tsv" ftype="tabular"/>\n+              <param name="filename_copy_loss" value="copy_number_loss_status_t10p.tsv.gz" ftype="tabular"/>\n+          '..b'am name="l1_ratios" value="0.1,0.125,0.15,0.2,0.25,0.3,0.35"/>\n+              <param name="seed" value="1234"/>\n+              <param name="num_features" value="8000"/>\n+              <param name="remove_hyper" value="true"/>\n+              <output name="log">\n+                <assert_contents>\n+                  <has_line line="[&apos;ERBB2&apos;, &apos;PIK3CA&apos;, &apos;KRAS&apos;, &apos;AKT1&apos;]" />\n+                  <has_line line="GBM" />\n+                  <has_n_lines n="2" />\n+                </assert_contents>\n+              </output>\n+              <output_collection name="classifier_coefficients" type="list">\n+                 <element name="GBM" file="GBM_108_coef.tabular" ftype="tabular" />\n+              </output_collection>\n+              <output_collection name="classifier_summary" type="list">\n+                 <element name="GBM" file="GBM_111_summary.txt" ftype="txt" />\n+              </output_collection>\n+              <output_collection name="pancan_roc_results" type="list">\n+                 <element name="GBM" ftype="tabular">\n+                    <assert_contents>\n+                        <has_line line="&#009;fpr&#009;tpr&#009;threshold&#009;train_type&#009;disease" />\n+                        <has_n_columns n="6" />\n+                        <has_n_lines n="253" />\n+                    </assert_contents>\n+                  </element>\n+              </output_collection>\n+              <output_collection name="summary_counts" type="list">\n+                 <element name="GBM" file="GBM_106_summary_counts.csv" ftype="csv" />\n+              </output_collection>\n+              <output_collection name="within_disease" type="list:list">\n+                <element name="GBM" >\n+                  <element name="cv_heatmap" file="GBM_cv_heatmap_103.pdf" compare="sim_size" delta="50"/>\n+                  <element name="all_disease_pr" file="GBM_all_disease_pr_101.pdf" compare="sim_size" delta="50" />\n+                  <element name="all_disease_roc" file="GBM_all_disease_roc_102.pdf" compare="sim_size" delta="50"/>\n+                  <element name="disease_aupr" file="GBM_disease_aupr_104.pdf" compare="sim_size" delta="50"/>\n+                  <element name="disease_auroc" file="GBM_disease_auroc_105.pdf" compare="sim_size" delta="50"/>\n+                </element>\n+              </output_collection>\n+              <output_collection name="disease_figures" type="list:list">\n+                <element name="GBM" >\n+                  <element name="pr" file="GBM_pr_99.pdf" compare="sim_size" delta="50"/>\n+                  <element name="roc" file="GBM_roc_100.pdf" compare="sim_size" delta="50"/>\n+                </element>\n+              </output_collection>\n+        </test>\n+    </tests>\n+  <help><![CDATA[\n+    **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/papaa_within_disease_analysis.py:**\n+\n+      **Inputs:**\n+        --genes   comma separated string of HUGO symbols for target genes or targenes_list.csv file\n+        --diseases  Comma separated diseases list in a file\n+        --alphas  The alphas for parameter sweep\n+        --l1_ratios   The l1 ratios for parameter sweep\n+        --remove_hyper  Remove hypermutated samples\n+        --classifier_results  String of location to classification folder extending to individual diseases\n+        --x_matrix  Filename of features to use in model\n+        --filename_mut  Filename of sample/gene mutations to use in model\n+        --filename_mut_burden   Filename of sample mutation burden to use in model\n+        --filename_sample   Filename of patient/samples to use in model\n+        --filename_copy_loss  Filename of copy number loss\n+        --filename_copy_gain  Filename of copy number gain\n+        --filename_cancer_gene_classification   Filename of cancer gene classification table\n+\n+      **Outputs:**\n+        ROC curves, AUROC across diseases, and classifier coefficients for individual diseases ]]>\n+  </help>\n+  <expand macro="citations" />\n+</tool>\n'