Mercurial > repos > proteore > proteore_prot_features

comparison prot_features.xml @ 1:bfc679370c64 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 5774fd6a5a746f36f6bf4671a51a39ea2b978300-dirty
author proteore
date Fri, 16 Feb 2018 04:06:16 -0500
parents e3b52db3d583
children 6659a32876ea
comparison
equal deleted inserted replaced
0:e3b52db3d583 1:bfc679370c64
1 <tool id="prot_features" name="Protein Features (neXtProt)" version="0.1.0"> 1 <tool id="prot_features" name="Protein Features (neXtProt)" version="0.1.0">
2 <description> 2 <description>
3 obtains different features of your protein list from neXtProt. 3 Annotate your protein list using features retrieved from neXtProt database.
4 </description> 4 </description>
5 <requirements> 5 <requirements>
6 </requirements> 6 </requirements>
7 <stdio> 7 <stdio>
8 <exit_code range="1:" /> 8 <exit_code range="1:" />
9 </stdio> 9 </stdio>
10 <command><![CDATA[ 10 <command><![CDATA[
11 11
12 #if $inputtype.filetype == "copy_paste": 12 #if $inputtype.filetype == "copy_paste":
13 Rscript --vanilla $__tool_directory__/get_data_nextprot.R --inputtype copypaste --input '$inputtype.genelist' --nextprot $__tool_directory__/result_nextprot.txt --column c1 --argsP1 '$Nextprot_params.P1' --argsP2 '$Nextprot_params.P2'--argsP3 '$Nextprot_params.P3' --type '$idtype' --output '$output' --header None 13
14 Rscript $__tool_directory__/protein_features.R --inputtype=copypaste --input='$inputtype.genelist' --nextprot=$__tool_directory__/result_nextprot.txt --column=c1 --argsP1='$Nextprot_params.P1' --argsP2='$Nextprot_params.P2' --argsP3='$Nextprot_params.P3' --type='$idtype' --output='$output' --header=None
15
14 #end if 16 #end if
15 17
16 #if $inputtype.filetype == "file_all": 18 #if $inputtype.filetype == "file_all":
17 19
18 Rscript --vanilla $__tool_directory__/get_data_nextprot.R --inputtype tabfile --input '$inputtype.genelist' --nextprot $__tool_directory__/result_nextprot.txt --column '$inputtype.column' --argsP1 '$Nextprot_params.P1' --argsP2 '$Nextprot_params.P2'--argsP3 '$Nextprot_params.P3' --type '$idtype' --output '$output' --header '$inputtype.header' 20 Rscript $__tool_directory__/protein_features.R --inputtype=tabfile --input='$inputtype.genelist' --nextprot=$__tool_directory__/result_nextprot.txt --column='$inputtype.column' --argsP1='$Nextprot_params.P1' --argsP2='$Nextprot_params.P2' --argsP3='$Nextprot_params.P3' --type='$idtype' --output='$output' --header='$inputtype.header'
19 21
20 #end if 22 #end if
21 23
22
23 ]]></command> 24 ]]></command>
24 25
25 <inputs> 26 <inputs>
26 <conditional name="inputtype"> 27 <conditional name="inputtype">
27 <param name="filetype" type="select" label="Select your type of input file"> 28 <param name="filetype" type="select" label="Select your type of input file">
28 <option value="file_all">Input file containing your identifiers</option> 29 <option value="file_all">Input file containing your identifiers (neXtProt or Uniprot ID)</option>
29 <option value="copy_paste">Copy/paste your list of IDs</option> 30 <option value="copy_paste">Copy/paste your list of IDs</option>
30 </param> 31 </param>
31 <when value="copy_paste"> 32 <when value="copy_paste">
32 <param name="genelist" type="text" label="Enter a list of identifiers"/> 33 <param name="genelist" type="text" label="Enter a list of identifiers"/>
33 </when> 34 </when>
34 <when value="file_all"> 35 <when value="file_all">
35 <param name="genelist" type="data" format="txt,tabular" label="Choose a multiple-columns file" help="This file must imperatively have 1 column filled with IDs consistent with the database that will be used. Please use the MappingIDs component if this is not the case."/> 36 <param name="genelist" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="This file must imperatively have 1 column filled with IDs consistent with the neXtprot database (Uniprot accession number or neXtProt ID). If this is not the case, please use the ID_Converter tool."/>
36 <param name="column" type="text" label="Please specify the column where you would like to apply the comparison (e.g : Enter c1)" value="c1"/> 37 <param name="column" type="text" label="Please specify the column where are your IDs (e.g : Enter c1 for column n°1)" value="c1"/>
37 <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false"> 38 <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false">
38 <option value="TRUE" selected="true">Yes</option> 39 <option value="true" selected="true">Yes</option>
39 <option value="FALSE" selected="false">No</option> 40 <option value="false" selected="false">No</option>
40 </param> 41 </param>
41 </when> 42 </when>
42 </conditional> 43 </conditional>
44
43 <param name="idtype" type="select" label="Type of your input ids" multiple="false" optional="false"> 45 <param name="idtype" type="select" label="Type of your input ids" multiple="false" optional="false">
44 <option value="nextprot" selected="false">Nextprot IDs</option> 46 <option value="uniprot" selected="true">Uniprot accession number</option>
45 <option value="uniprot" selected="true">Uniprot IDs</option> 47 <option value="nextprot" selected="false">neXtProt IDs</option>
46 </param> 48 </param>
47 49 <section name="Nextprot_params" title="Select features of interest (compulsory step)" expanded="True">
48 <section name="Nextprot_params" title="Choose the type of information (compulsory step)" expanded="True">
49 <param name="P1" type="select" label="Physico-Chemical Features" multiple="true" help="Choose the information you want to add to your data from Nextprot" display="checkboxes" optional="true"> 50 <param name="P1" type="select" label="Physico-Chemical Features" multiple="true" help="Choose the information you want to add to your data from Nextprot" display="checkboxes" optional="true">
51 <option value="SeqLength" selected="false">Sequence Length</option>
50 <option value="MW" selected="false">Molecular Weight</option> 52 <option value="MW" selected="false">Molecular Weight</option>
51 <option value="SeqLength" selected="false">Sequence Length</option>
52 <option value="IsoPoint" selected="false">Isoelectric point</option> 53 <option value="IsoPoint" selected="false">Isoelectric point</option>
53 <option value="TMDomains" selected="false">Number of transmembrane domains</option> 54 <option value="TMDomains" selected="false">Number of transmembrane domains</option>
54 <option value="ProteinExistence" selected="false">Protein Existence (PE level)</option> 55 <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option>
55 </param> 56 </param>
56 57
57 <param name="P2" type="select" label="Localization" multiple="true" help="Choose the information you want to add to your data from Nextprot" display="checkboxes" optional="true"> 58 <param name="P2" type="select" label="Localization" multiple="true" help="Choose the information you want to add to your data from Nextprot" display="checkboxes" optional="true">
58 <option value="Chr" selected="false">Chromosome</option> 59 <option value="Chr" selected="false">Chromosome</option>
59 <option value="SubcellLocations" selected="false">Subcellular Location</option> 60 <option value="SubcellLocations" selected="false">Subcellular Location</option>
60 </param> 61 </param>
61 62
62 <param name="P3" type="select" label="Diseases information"> 63 <param name="P3" type="select" label="Diseases information">
63 <option value="Diseases">Yes</option> 64 <option value="Diseases">Yes</option>
64 <option value="None">No</option> 65 <option value="None">No</option>
67 68
68 </inputs> 69 </inputs>
69 70
70 71
71 <outputs> 72 <outputs>
72 <data name="output" format="tsv" label="Add information from ${database_type.database}"/> 73 <data name="output" format="tsv" label="Add information from neXtProt"/>
73
74
75 </outputs> 74 </outputs>
76
77 75
78 <tests> 76 <tests>
79 <test> 77 <test>
80 <conditional name="inputtype"> 78 <conditional name="inputtype">
81 <param name="filetype " value="tabfile"/> 79 <param name="filetype " value="tabfile"/>
82 <param name="genelist" value="mitochondrion_enzymes_Nextprot.txt"/> 80 <param name="genelist" value="FKW_ID_Converter_Lacombe_et_al_2017_OK.txt"/>
83 <param name="column" value="c1"/> 81 <param name="column" value="c1"/>
84 <param name="header" value="TRUE"/> 82 <param name="header" value="true"/>
85 </conditional> 83 </conditional>
86 84
87 <param name="idtype" value="nextprot"/> 85 <param name="idtype" value="uniprot"/>
88 86
89 <section name="Nextprot_params"> 87 <section name="Nextprot_params">
90 <param name="P1" value="MW,SeqLength,IsoPoint,TMDomains,ProteinExistence"/> 88 <param name="P1" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/>
91 <param name="P2" value="Chr,SubcellLocations"/> 89 <param name="P2" value="Chr,SubcellLocations"/>
92 <param name="P3" value="Diseases"/> 90 <param name="P3" value="Diseases"/>
93 </section> 91 </section>
94 92
95 <output name="output" file="output_get_data.tsv"/> 93 <output name="output" file="Add_information_from_neXtProt.tsv"/>
96 </test> 94 </test>
97 </tests> 95 </tests>
98 96
99 <help><![CDATA[ 97 <help><![CDATA[
100 98
101 This tool filters an input **tabular** file according to different databases. 99 This tool add annotation (protein features) from neXtProt database (knowledge base on human proteins) to your protein IDs list.
102 100
103 **Input** 101 **Input**
104 102
105 Input can be a file containing multiple fields but with **at least one column of Ensembl gene IDs** or a list of Ensembl gene ids. If your input file contains other kind of IDs, please refer to the MappingIDs component to create a column of Ensembl gene IDs. 103 Input can be a file containing multiple fields but with **at least one column of Uniprot accession number or neXtProt IDs**. If your input file contains other type of IDs, please use the ID_Converter tool.
106 104
107 **Databases** 105 **Databases**
108 106
109 The input file will be filtered using information from different sources : 107 Annotations have been retrieved from the neXtProt database (Gaudet et al., 2017) via a REST API (https://academic.oup.com/nar/article/43/D1/D764/2439066#40348985)
110
111 - HPA normal tissue : will filter the input according to the data contained in the Human Protein Atlas webservice. Pertinent information, such as tissular location, will be added for each gene to your input file.
112
113 - HPA cancer tissue : will filter the input according to the data contained in the Human Protein Atlas webservice for cancer. Pertinent information, such as tumor type, will be added for each gene to your input file.
114
115 **Parameters**
116
117 For HPA normal tissue :
118
119 - tissue category : categories based on RNA-Seq data to estimate the transcript abundance of each protein-coding gene in tissues. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#rna .
120
121 - level of detection IF : level of detection of the protein associated to the coding gene tissues based on immunofluorescency. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#if .
122
123 - level of detection IH : level of detection of the protein associated to the coding gene tissues based on immunohistochemistry. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#if .
124
125 For HPA cancer tissue :
126
127 - tumors : which tumors are associated with your protein-coding genes according to the Human Protein Atlas.
128
129 108
130 **Outputs** 109 **Outputs**
131 110
132 The output will be a tabular file. The initial columns will be kept, but lines can be deleted due to the filtering process. Additional columns will be added according to which data you chose to filter your input with. 111 The output is a tabular file. The initial columns are kept and columns are be added according to which annotation you have selected.
133 112
113 **Authors**
134 114
135 **Data sources** 115 T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
136 116
137 The data for HPA normal tissue was retrieved from the Human Protein Atlas downloadable data repository (http://www.proteinatlas.org/download/proteinatlas.tab.gz). 117 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform
138 118
139 The data for HPA cancer was retrieved from the Human Protein Atlas downloadable data repository (http://www.proteinatlas.org/download/cancer.csv.zip). 119 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
140 ]]></help>
141 120
142 <citations> 121 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
143 </citations> 122
123 ]]></help>
124 <citations>
125 </citations>
144 126
145 </tool> 127 </tool>