comparison within_disease_analysis.xml @ 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
comparison
equal deleted inserted replaced
-1:000000000000 0:99d944bfe9b3
1 <tool id="pancancer_within_disease_analysis" name="PAPAA: PanCancer within disease analysis" version="@VERSION@">
2 <description>within disease analysis</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
8 <version_command><![CDATA['papaa_within_disease_analysis.py' --version]]></version_command>
9 <command><![CDATA[
10 papaa_within_disease_analysis.py
11 @INPUTS_ALPHAS@
12 @INPUTS_L1_RATIOS@
13 @INPUT_REMOVE_HYPER@
14 @INPUTS_BASIC@
15 @INPUTS_GENES_DISEASES@
16 @INPUTS_COPY_NUMBER_CLASS_FILE_PREFIX@
17 @INPUTS_COPY_NUMBER_CLASS_FILE@
18 --classifier_results 'classifier'
19 #if $seed and $seed is not None:
20 --seed '$seed'
21 #end if
22 #if $num_features and $num_features is not None:
23 --num_features '$num_features'
24 #end if
25 > '${log}'
26 && papaa_flatten_classifier_directory.py -i 'classifier/within_disease' -o 'classifier_within'
27 ]]>
28 </command>
29 <inputs>
30 <expand macro="inputs_basic" />
31 <expand macro="inputs_genes_diseases" />
32 <expand macro="inputs_copy_number_class_file" />
33 <expand macro="input_alphas" />
34 <expand macro="input_l1_ratios" />
35 <expand macro="input_remove_hyper" />
36 <param argument="--seed" label="option to set seed" name="seed" optional="true" type="integer" value="1234"/>
37 <param argument="--num_features" label="Number of MAD genes to include in classifier" name="num_features" optional="true" type="integer" value="8000"/>
38 </inputs>
39 <outputs>
40 <data format="txt" name="log" label="${tool.name} on ${on_string} (Log)" />
41 <collection name="classifier_summary" type="list" label="classifier_summary.txt">
42 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_classifier_summary\.txt" format="txt" directory="classifier_within/within_disease" visible="false" />
43 </collection>
44 <collection name="classifier_coefficients" type="list" label="classifier_coefficients.tsv">
45 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_classifier_coefficients\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" />
46 </collection>
47 <collection name="pancan_roc_results" type="list" label="pancan_roc_results.tsv">
48 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_pancan_roc_results\.tsv" format="tabular" directory="classifier_within/within_disease" visible="false" />
49 </collection>
50 <collection name="summary_counts" type="list" label="summary_counts.csv">
51 <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_summary_counts\.csv" format="csv" directory="classifier_within/within_disease" visible="false" />
52 </collection>
53 <collection name="within_disease" type="list:list" label="Within disease figures">
54 <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;.+)\.pdf" format="pdf" directory="classifier_within/within_disease" visible="false" />
55 </collection>
56 <collection name="disease_figures" type="list:list" label="Disease classifier figures">
57 <discover_datasets pattern="classifier_(?P&lt;identifier_1&gt;.+)__pred_(?P&lt;identifier_0&gt;.+)\.pdf" format="pdf" directory="classifier_within/disease" visible="false" />
58 </collection>
59 </outputs>
60 <tests>
61 <test>
62 <param name="genes" value="ERBB2,PIK3CA,KRAS,AKT1"/>
63 <param name="diseases" value="GBM"/>
64 <param name="x_matrix" value="pancan_rnaseq_freeze_t1p.tsv.gz" ftype="tabular"/>
65 <param name="filename_mut" value="pancan_mutation_freeze_t1p.tsv.gz" ftype="tabular"/>
66 <param name="filename_mut_burden" value="mutation_burden_freeze.tsv" ftype="tabular"/>
67 <param name="filename_sample" value="sample_freeze.tsv" ftype="tabular"/>
68 <param name="filename_copy_loss" value="copy_number_loss_status_t10p.tsv.gz" ftype="tabular"/>
69 <param name="filename_copy_gain" value="copy_number_gain_status_t10p.tsv.gz" ftype="tabular"/>
70 <param name="filename_cancer_gene_classification" value="cosmic_cancer_classification.tsv" ftype="tabular"/>
71 <param name="alphas" value="0.1,0.13,0.15,0.18,0.2,0.3,0.4,0.6,0.7"/>
72 <param name="l1_ratios" value="0.1,0.125,0.15,0.2,0.25,0.3,0.35"/>
73 <param name="seed" value="1234"/>
74 <param name="num_features" value="8000"/>
75 <param name="remove_hyper" value="true"/>
76 <output name="log">
77 <assert_contents>
78 <has_line line="[&apos;ERBB2&apos;, &apos;PIK3CA&apos;, &apos;KRAS&apos;, &apos;AKT1&apos;]" />
79 <has_line line="GBM" />
80 <has_n_lines n="2" />
81 </assert_contents>
82 </output>
83 <output_collection name="classifier_coefficients" type="list">
84 <element name="GBM" file="GBM_108_coef.tabular" ftype="tabular" />
85 </output_collection>
86 <output_collection name="classifier_summary" type="list">
87 <element name="GBM" file="GBM_111_summary.txt" ftype="txt" />
88 </output_collection>
89 <output_collection name="pancan_roc_results" type="list">
90 <element name="GBM" ftype="tabular">
91 <assert_contents>
92 <has_line line="&#009;fpr&#009;tpr&#009;threshold&#009;train_type&#009;disease" />
93 <has_n_columns n="6" />
94 <has_n_lines n="253" />
95 </assert_contents>
96 </element>
97 </output_collection>
98 <output_collection name="summary_counts" type="list">
99 <element name="GBM" file="GBM_106_summary_counts.csv" ftype="csv" />
100 </output_collection>
101 <output_collection name="within_disease" type="list:list">
102 <element name="GBM" >
103 <element name="cv_heatmap" file="GBM_cv_heatmap_103.pdf" compare="sim_size" delta="50"/>
104 <element name="all_disease_pr" file="GBM_all_disease_pr_101.pdf" compare="sim_size" delta="50" />
105 <element name="all_disease_roc" file="GBM_all_disease_roc_102.pdf" compare="sim_size" delta="50"/>
106 <element name="disease_aupr" file="GBM_disease_aupr_104.pdf" compare="sim_size" delta="50"/>
107 <element name="disease_auroc" file="GBM_disease_auroc_105.pdf" compare="sim_size" delta="50"/>
108 </element>
109 </output_collection>
110 <output_collection name="disease_figures" type="list:list">
111 <element name="GBM" >
112 <element name="pr" file="GBM_pr_99.pdf" compare="sim_size" delta="50"/>
113 <element name="roc" file="GBM_roc_100.pdf" compare="sim_size" delta="50"/>
114 </element>
115 </output_collection>
116 </test>
117 </tests>
118 <help><![CDATA[
119 **Pancancer_Aberrant_Pathway_Activity_Analysis scripts/papaa_within_disease_analysis.py:**
120
121 **Inputs:**
122 --genes comma separated string of HUGO symbols for target genes or targenes_list.csv file
123 --diseases Comma separated diseases list in a file
124 --alphas The alphas for parameter sweep
125 --l1_ratios The l1 ratios for parameter sweep
126 --remove_hyper Remove hypermutated samples
127 --classifier_results String of location to classification folder extending to individual diseases
128 --x_matrix Filename of features to use in model
129 --filename_mut Filename of sample/gene mutations to use in model
130 --filename_mut_burden Filename of sample mutation burden to use in model
131 --filename_sample Filename of patient/samples to use in model
132 --filename_copy_loss Filename of copy number loss
133 --filename_copy_gain Filename of copy number gain
134 --filename_cancer_gene_classification Filename of cancer gene classification table
135
136 **Outputs:**
137 ROC curves, AUROC across diseases, and classifier coefficients for individual diseases ]]>
138 </help>
139 <expand macro="citations" />
140 </tool>