Mercurial > repos > artbio > pathifier

comparison pathifier.xml @ 0:fec313f5c889 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/pathifier commit b94cfc7bf8df30aa8e9249b75ea31332ee2bada1"
author artbio
date Mon, 12 Apr 2021 09:55:24 +0000
parents
children 0960bd1161fa
comparison
equal deleted inserted replaced
-1:000000000000 0:fec313f5c889
1 <tool id="pathifier" name="Pathifier" version="1.0.1">
2 <description>: Quantify deregulation of pathways in cancer</description>
3 <requirements>
4 <requirement type="package" version="1.6.2=r35h6115d3f_0">r-optparse</requirement>
5 <requirement type="package" version="1.22.0=r351_0">bioconductor-pathifier</requirement>
6 <requirement type="package" version="1.0.12=r351h6115d3f_0">r-pheatmap</requirement>
7 <requirement type="package" version="0.3_41=r351h6115d3f_0">r-scatterplot3d</requirement>
8 <requirement type="package" version="0.4.7=r35h6115d3f_0">r-circlize</requirement>
9 </requirements>
10 <stdio>
11 <exit_code range="1:" level="fatal" description="Tool exception" />
12 </stdio>
13 <command detect_errors="exit_code"><![CDATA[
14 Rscript $__tool_directory__/pathifier.R
15 --exp '$input'
16 --sep '$input_sep'
17 --genes '$genes'
18
19 #if $reference.is_normal == "Yes":
20 --is_normal 'TRUE'
21 --normals '$reference.normals'
22 #end if
23
24 --max_stability '$max_stability'
25 --attempts '$attempts'
26 --min_std '$min_std'
27 --min_exp '$min_exp'
28
29 --heatmap_cluster_cells '$heatmap_cluster_cells'
30 --heatmap_cluster_pathways '$heatmap_cluster_pathways'
31 --heatmap_show_cell_labels '$heatmap_show_cell_labels'
32 --heatmap_show_pathway_labels '$heatmap_show_pathway_labels'
33
34 --pds '$pds'
35 --logfile '$logfile'
36 --plot '$plot'
37 --rdata '$rdatafile'
38
39 ]]></command>
40 <inputs>
41 <param name="input" type="data" format="txt,tabular" label="expression data"/>
42 <param name="input_sep" type="select" label="Input column separator">
43 <option value="tab" selected="true">Tabs</option>
44 <option value=",">Comma</option>
45 </param>
46 <param name="genes" type="data" format="txt" label="Gene sets Pathways"
47 help="Must be in gmt format (one pathway per line : Name, description, genes (one by column), tab separated)" />
48 <conditional name="reference">
49 <param name="is_normal" label="Do you have non cancer transcriptomes in your data set ?" type="boolean" truevalue="Yes" falsevalue="" checked="false"
50 help="If set the starting curve depends on the matrix of points with in a certain row order (first 'normal' then 'cancer' samples), otherwise the first principal component is used. See help for more informations"/>
51 <when value="Yes">
52 <param name="normals" type="data" format="tabular" label="Sample status"
53 help="A two-column data frame, first column contains data labels, second column the levels of sample status : 1 = Healthy, 0 = Tumor (no header)" />
54 </when>
55 <when value="">
56 </when>
57 </conditional>
58 <param name="max_stability" label="Throw away components leading to low stability of sampling noise" type="boolean" truevalue="TRUE"
59 falsevalue="FALSE" checked="true" />
60 <param name="attempts" type="integer" label="Number of runs to determine stability" value="100"/>
61 <param name="min_std" type="text" value="0.4" label="Minimum of standard deviation to filter out low variable genes"
62 help="Use 'data' to use the minimum standard deviation of your data" />
63 <param name="min_exp" type="text" value="4" label="Minimum of gene expression to filter out low variable genes"
64 help="Use 'data' to use the minimum expression of your data" />
65 <param name="heatmap_cluster_cells" label="Cluster samples on heatmap" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" />
66 <param name="heatmap_cluster_pathways" label="Cluster pathways on heatmap" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" />
67 <param name="heatmap_show_cell_labels" label="Show sample labels on heatmap" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" />
68 <param name="heatmap_show_pathway_labels" label="Cluster pathway labels on heatmap" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" />
69 <param label="Return log file of pathifier" name="log" type="select" >
70 <option value="no" selected="True">No</option>
71 <option value="yes">Yes</option>
72 </param>
73 <param label="Return Pathifier S4 object" name="rdata" type="select" >
74 <option value="no" selected="True">No</option>
75 <option value="yes">Yes</option>
76 </param>
77
78 </inputs>
79 <outputs>
80 <data name="pds" format="tabular" label="Pathifier Deregulation Score (PDS) of ${on_string}" />
81 <data name="logfile" format="txt" label="Pathifier log file of ${on_string}" >
82 <filter>log == 'yes'</filter>
83 </data>
84 <data name="plot" format="pdf" label="Pathifier vizualization of ${on_string}" />
85 <data name="rdatafile" format="rdata" label="Pathifier S4 object of ${on_string}" >
86 <filter>rds == 'yes'</filter>
87 </data>
88 </outputs>
89 <tests>
90 <test>
91 <param name="input" value="sheffer.tsv" ftype="tabular"/>
92 <param name="genes" value="kegg_pathways.gmt" ftype="txt" />
93 <param name="is_normal" value="True" />
94 <param name="normals" value="normals.tsv" ftype="tabular" />
95 <param name="log" value="yes" />
96 <param name="attempts" value="100" />
97 <output name="logfile" file="sheffer.kegg.log" ftype="txt" compare="sim_size" />
98 <output name="pds" file="sheffer.kegg.tsv" ftype="tabular"/>
99 <output name="plot" file="plot.pdf" ftype="pdf" compare="sim_size" />
100 </test>
101 <test>
102 <param name="input" value="sheffer_noref.tsv" ftype="tabular"/>
103 <param name="genes" value="kegg_pathways.gmt" ftype="txt" />
104 <param name="is_normal" value="" />
105 <param name="log" value="no" />
106 <param name="rdata" value="yes" />
107 <param name="attempts" value="50" />
108 <param name="min_exp" value="data" />
109 <param name="min_std" value="data" />
110 <output name="pds" file="sheffer.kegg_noref.tsv" ftype="tabular"/>
111 <output name="rdatafile" file="sheffer.kegg_noref.rdata" ftype="rdata" compare="sim_size" />
112 <output name="plot" file="plot_noref.pdf" ftype="pdf" compare="sim_size" />
113 </test>
114 </tests>
115 <help>
116
117 **What it does**
118
119 Pathifier is an algorithm that infers pathway deregulation scores for each (tumor) sample on the basis
120 of expression data. This score is determined, in a context-specific manner, for every particular dataset
121 and type of cancer that is being investigated. The algorithm transforms gene-level information into
122 pathway-level information, generating a compact and biologically relevant representation of each sample.
123
124 For each pathway analysed, the transcriptome datasets are plotted in the gene pathway space using a
125 Principal Component analysis (PCA) and a principal curve is regressed from these points. All transcriptomes
126 are projected on the nearest point of this curve. Pathifier finally computes a score which corresponds to
127 the distance (normalized to 1) of each point (transcriptome) to the curve origin.
128
129 **Inputs**
130
131 * a matrix of n columns of observations (generally RNAseq experiments) and k rows of variables (generally k genes).
132 * a Gene Matrix Transposed file (GMT format) where each row represents a gene set :
133 * first column : gene set name (pathway name)
134 * second : description of gene set
135 * third and + : list of genes that composed the gene set tab-separated
136 * (Optional) a two column table with no header, to described transcriptome status (Tumor or not) :
137 * first column : sample labels
138 * second : levels of sample status : 1 = Healthy, 0 = Tumor
139
140 **Outputs**
141
142 * Table of Pathway Deregulation Scores : one by pathway (column) and by transcriptome (row)
143 * Visualization of PDS (pdf) :
144 * Principal curve of different PDS
145 * Heatmap of PDS that allows (through clustering) to see pattern in pathway deregulation
146 * (Optional) Log file of Pathifier algorithm
147 * (Optional) Pathifier S4 object which contains all informations and results generated by Pathifier, for each pathway :
148 * `scores` : PDS scores
149 * `genesinpathway` : Gene identifiers in each pathway
150 * `newmeanstd`
151 * `origmeanstd`
152 * `pathwaysize` : Number of genes retained in pathway
153 * `curves` : Coordinates of transcriptomes projected on the principal curve
154 * `curves_order` : Order of transcriptomes along the principal curve
155 * `z` : z-scores matrix
156 * `compin`
157 * `xm`
158 * `xs`
159 * `center`
160 * `rot`
161 * `pctaken` : Number of principal component retained for pathifier analysis
162 * `samplings`
163 * `sucess` : List of pathway index that passed Pathfiier filters (more info in log file)
164 * `logfile` : Name of logfile
165
166 </help>
167 <citations>
168 <citation type="bibtex">@Manual{,
169 title = {{pathifier}: Quantify deregulation of pathways in cancer},
170 author = {Yotam Drier},
171 year = {2013-06-27},
172 note = {R package version 1.22.0},
173 url = {https://git.bioconductor.org/packages/pathifier},
174 }
175 </citation>
176 <citation type="bibtex">@article {Drier6388,
177 author = {Drier, Yotam and Sheffer, Michal and Domany, Eytan},
178 title = {Pathway-based personalized analysis of cancer},
179 volume = {110},
180 number = {16},
181 pages = {6388--6393},
182 year = {2013},
183 doi = {10.1073/pnas.1219651110},
184 publisher = {National Academy of Sciences},
185 issn = {0027-8424},
186 URL = {https://www.pnas.org/content/110/16/6388},
187 eprint = {https://www.pnas.org/content/110/16/6388.full.pdf},
188 journal = {Proceedings of the National Academy of Sciences}
189 }
190 </citation>
191 </citations>
192 </tool>