comparison get_expression_profiles.xml @ 8:2c0bab71a436 draft

planemo upload commit 5e13878e9679f3f5ba8e482b9108249a43f3355e-dirty
author proteore
date Tue, 18 Dec 2018 09:48:29 -0500
parents
children 0a0f6c37f05e
comparison
equal deleted inserted replaced
7:f7e93829327e 8:2c0bab71a436
1 <tool id="sel_ann_hpa" name="Get expression profiles" version="2018.12.17">
2 <description>by (normal or tumor) tissue/cell type [Human Protein Atlas]
3 </description>
4 <requirements>
5 </requirements>
6 <stdio>
7 <exit_code range="1:" />
8 </stdio>
9 <command interpreter="Rscript">
10 $__tool_directory__/get_expression_profiles.R
11 --ref_file="$__tool_directory__/$options.proteinatlas"
12 --input_type="$input.ids"
13 #if $input.ids == "list"
14 --input="$input.list"
15 #else
16 --input="$input.file"
17 --column_number="$input.ncol"
18 --header="$input.header"
19 #end if
20
21 #if $options.database == "normal"
22 --atlas="normal"
23 --tissue="$options.normal_tissue"
24 --level="$options.level"
25 --reliability="$options.reliability"
26 #else if $options.database == "tumor"
27 --atlas="cancer"
28 --cancer="$options.cancer_tissue"
29 #end if
30 --not_mapped="$not_mapped"
31 --output="$hpa_output"
32 </command>
33 <inputs>
34 <conditional name="input" >
35 <param name="ids" type="select" label="Enter your IDs (ENSG IDs only)" help="Copy/paste or from a file (e.g. table)" >
36 <option value="list">Copy/paste your IDs</option>
37 <option value="file" selected="true">Input file containing your IDs</option>
38 </param>
39 <when value="list" >
40 <param name="list" type="text" label="Copy/paste your IDs" help='IDs must be separated by spaces into the form field, for example: ENSG00000174876 ENSG00000178372 ENSG00000159763' >
41 <sanitizer>
42 <valid initial="string.printable">
43 <remove value="&apos;"/>
44 </valid>
45 <mapping initial="none">
46 <add source="&apos;" target="__sq__"/>
47 </mapping>
48 </sanitizer>
49 </param>
50 </when>
51 <when value="file" >
52 <param name="file" type="data" format="txt,tabular" label="" help="" />
53 <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
54 <param name="ncol" type="text" value="c1" label="Column number of IDs to map" help='For example, fill in "c1" if it is the first column, "c2" if it is the second column and so on' />
55 </when>
56 </conditional>
57 <conditional name="options">
58 <param name="database" type="select" label="Human Protein Atlas (normal or tumor tissue)">
59 <option value="normal">Human Normal Tissue</option>
60 <option value="tumor">Human Tumor Tissue</option>
61 </param>
62 <when value="normal">
63 <param name="proteinatlas" type="select" label="Normal tissue HPA version" >
64 <!--options from_file="proteinatlas.loc" >
65 <column name="name" index="1"/>
66 <column name="value" index="2"/>
67 <filter type="remove_value" key="name" value="Full Human Protein Atlas (23/10/18)"/>
68 <filter type="remove_value" key="name" value="HPA Tumor Tissue (23/10/18)"/>
69 </options-->
70 <option value="tool-data/HPA_normal_tissue_23-10-2018.tsv">HPA Normal Tissue (23/10/18)</option>
71 </param>
72 <param name="normal_tissue" type="select" label="Select tissue(s)" multiple="True" display="checkboxes" optional="False">
73 <option value="adrenal gland" >Adrenal gland</option>
74 <option value="appendix" >Appendix</option>
75 <option value="bone marrow" >Bone marrow</option>
76 <option value="breast" >Breast</option>
77 <option value="bronchus" >Bronchus</option>
78 <option value="caudate" >Caudate</option>
79 <option value="cerebellum" >Cerebellum</option>
80 <option value="cerebral cortex" >Cerebral cortex</option>
81 <option value="cervix" >Cervix</option>
82 <option value="colon" >Colon</option>
83 <option value="duodenum" >Duodenum</option>
84 <option value="endometrium 1" >Endometrium 1</option>
85 <option value="endometrium 2" >Endometrium 2</option>
86 <option value="epididymis" >Epididymis</option>
87 <option value="esophagus" >Esophagus</option>
88 <option value="fallopian tube" >Fallopian tube</option>
89 <option value="gallbladder" >Gallbladder</option>
90 <option value="heart muscle" >Heart muscle</option>
91 <option value="hippocampus" >Hippocampus</option>
92 <option value="kidney" >Kidney</option>
93 <option value="liver" >Liver</option>
94 <option value="lung" >Lung</option>
95 <option value="lymph node" >Lymph node</option>
96 <option value="nasopharynx" >Nasopharynx</option>
97 <option value="oral mucosa" >Oral mucosa</option>
98 <option value="ovary" >Ovary</option>
99 <option value="pancreas" >Pancreas</option>
100 <option value="parathyroid gland" >Parathyroid gland</option>
101 <option value="placenta" >Placenta</option>
102 <option value="prostate" >Prostate</option>
103 <option value="rectum" >Rectum</option>
104 <option value="salivary gland" >Salivary gland</option>
105 <option value="seminal vesicle" >Seminal vesicle</option>
106 <option value="skeletal muscle" >Skeletal muscle</option>
107 <option value="skin 1" >Skin 1</option>
108 <option value="skin 2" >Skin 2</option>
109 <option value="small intestine" >Small intestine</option>
110 <option value="smooth muscle" >Smooth muscle</option>
111 <option value="soft tissue 1" >Soft tissue 1</option>
112 <option value="soft tissue 2" >Soft tissue 2</option>
113 <option value="spleen" >Spleen</option>
114 <option value="stomach 1" >Stomach 1</option>
115 <option value="stomach 2" >Stomach 2</option>
116 <option value="testis" >Testis</option>
117 <option value="thyroid gland" >Thyroid gland</option>
118 <option value="tonsil" >Tonsil</option>
119 <option value="urinary bladder" >Urinary bladder</option>
120 <option value="vagina" >Vagina</option>
121 </param>
122 <param name="level" type="select" label="Expression level" display="checkboxes" multiple="True" optional="False">
123 <option value="High" selected="true">High</option>
124 <option value="Medium">Medium</option>
125 <option value="Low">Low</option>
126 <option value="Not detected">Not detected</option>
127 </param>
128 <param name="reliability" type="select" label="Reliability score" display="checkboxes" multiple="True" optional="False">
129 <option value="Enhanced" selected="true">Enhanced</option>
130 <option value="Supported" selected="true">Supported</option>
131 <option value="Approved">Approved</option>
132 <option value="Uncertain">Uncertain</option>
133 </param>
134 </when>
135 <when value="tumor">
136 <param name="proteinatlas" type="select" label="Tumor tissue HPA version" >
137 <!--options from_file="proteinatlas.loc" >
138 <column name="name" index="1" />
139 <column name="value" index="2" />
140 <filter type="remove_value" meta_ref="proteinatlas" key="name" value="Full Human Protein Atlas (23/10/18)" />
141 <filter type="remove_value" meta_ref="proteinatlas" key="name" value="HPA Normal Tissue (23/10/18)" />
142 </options-->
143 <option value="tool-data/HPA_pathology_23-10-2018.tsv">HPA Tumor Tissue (23/10/18)</option>
144 </param>
145 <param name="cancer_tissue" type="select" label="Select cancer tissue(s)" multiple="True" display="checkboxes" optional="False">
146 <option value="breast cancer" >Breast cancer</option>
147 <option value="carcinoid" >Carcinoid</option>
148 <option value="cervical cancer" >Cervical cancer</option>
149 <option value="colorectal cancer" >Colorectal cancer</option>
150 <option value="endometrial cancer" >Endometrial cancer</option>
151 <option value="glioma" >Glioma</option>
152 <option value="head and neck cancer" >Head and neck cancer</option>
153 <option value="liver cancer" >Liver cancer</option>
154 <option value="lung cancer" >Lung cancer</option>
155 <option value="lymphoma" >Lymphoma</option>
156 <option value="melanoma" >Melanoma</option>
157 <option value="ovarian cancer" >Ovarian cancer</option>
158 <option value="pancreatic cancer" >Pancreatic cancer</option>
159 <option value="prostate cancer" >Prostate cancer</option>
160 <option value="renal cancer" >Renal cancer</option>
161 <option value="skin cancer" >Skin cancer</option>
162 <option value="stomach cancer" >Stomach cancer</option>
163 <option value="testis cancer" >Testis cancer</option>
164 <option value="thyroid cancer" >Thyroid cancer</option>
165 <option value="urothelial cancer" >Urothelial cancer</option>
166 </param>
167 </when>
168 </conditional>
169 <param name="not_mapped" type="boolean" truevalue="true" falsevalue="false" label="Keep IDs not found in HPA?" checked="true"/>
170 </inputs>
171 <outputs>
172 <data name="hpa_output" format="tsv" label="" />
173 </outputs>
174 <tests>
175 <test>
176 <conditional name="input">
177 <param name="ids" value="file"/>
178 <param name="file" value="ID_Converter_FKW_Lacombe_et_al_2017_OK.txt"/>
179 <param name="header" value="true"/>
180 <param name="ncol" value="c8"/>
181 </conditional>
182 <conditional name="options">
183 <param name="database" value="normal"/>
184 <param name="proteinatlas" value="normal_tissue.tsv"/>
185 <param name="normal_tissue" value="bronchus,lung,nasopharynx,salivary gland"/>
186 <param name="level" value="Not detected,Medium,High,Low"/>
187 <param name="reliability" value="Approved,Supported,Uncertain"/>
188 </conditional>
189 <param name="not_mapped" value="true" />
190 <output name="hpa_output" file="Expres_levels_Lacombe_et_al_2017_OK.txt"/>
191 </test>
192 </tests>
193 <help><![CDATA[
194
195 **Description**
196
197 This tool allows to retrieve expression profiles (normal or tumor tissue) from Human Protein Atlas (https://www.proteinatlas.org/)
198
199 **Input**
200
201 A list of ENSG (Ensembl gene) IDs must be entered (either via a copy/paste or by choosing a file); if it's not the case, please use the ID_Converter tool of ProteoRE.
202
203 -----
204
205 **Parameters**
206
207 "Human Protein Atlas (normal or tumor tissue)": two resources are currently available
208
209 * **Human normal tissue data**: expression profiles for proteins in human tissues based on immunohistochemisty using tissue micro arrays.
210
211 **Output** will be in the form: a tab-separated file includes Ensembl gene identifier ("Gene"), tissue name ("Tissue"), annotated cell type ("Cell type"), expression value ("Level"), and the gene reliability of the expression value ("Reliability").
212
213 * **Human tumor tissue data**: staining profiles for proteins in human tumor tissue based on immunohistochemisty using tissue micro arrays and log-rank P value for Kaplan-Meier analysis of correlation between mRNA expression level and patient survival.
214
215 **Ouptut** will be in the form: The tab-separated file includes Ensembl gene identifier ("Gene"), gene name ("Gene name"), tumor name ("Cancer"), the number of patients annotated for different staining levels ("High", "Medium", "Low" & "Not detected") and log-rank p values for patient survival and mRNA correlation ("prognostic - favourable", "unprognostic - favourable", "prognostic - unfavourable", "unprognostic - unfavourable").
216
217 "Select tissue(s)": information from more than one tissue can be retrieved
218
219 "Keep IDs not found in HPA?": ENSG ID not found in Human Protein Atlas will be returned in the output file in the form of "NA" (default is "No")
220
221 -----
222
223 **Reliability score (only for normal tissue)**
224
225 Reliability score is divided into Enhanced, Supported, Approved, or Uncertain with respect to the definitions from HPA:
226
227 Enhanced - One or several antibodies with non-overlapping epitopes targeting the same gene have obtained enhanced validation based on orthogonal or independent antibody validation method.
228
229 Supported - Consistency with RNA-seq and/or protein/gene characterization data, in combination with similar staining pattern if independent antibodies are available.
230
231 Approved - Consistency with RNA-seq data in combination with inconsistency with, or lack of, protein/gene characterization data. Alternatively, consistency with protein/gene characterization data in combination with inconsistency with RNA-seq data. If independent antibodies are available, the staining pattern is partly similar or dissimilar.
232
233 Uncertain - Inconsistency with, or lack of, RNA-seq and/or protein/gene characterization data, in combination with dissimilar staining pattern if independent antibodies are available.
234
235 -----
236
237 **Data sources (release date)**
238
239 Both normal and tumor tissues data are based on the Human Protein Atlas version 18 and Ensembl version 88.38.
240
241 -----
242
243 .. class:: infomark
244
245 **Authors**
246
247 T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
248
249 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
250
251 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
252
253 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
254
255 ]]></help>
256 <citations>
257 </citations>
258 </tool>