Mercurial > repos > proteore > proteore_id_converter

comparison id_converter.xml @ 14:659f1248f535 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 688c456ca57914a63c20eba942ec5fe81e896099-dirty
author proteore
date Wed, 19 Sep 2018 04:45:04 -0400
parents e30234018582
children b50d913ec067
comparison
equal deleted inserted replaced
13:4fcc5e5c0902 14:659f1248f535
1 <tool id="IDconverter" name="ID Converter" version="0.1.2"> 1 <tool id="IDconverter" name="ID Converter" version="2018.09.18">
2 <description>convert public database identifiers 2 <description>convert public database identifiers
3 </description> 3 </description>
4 <requirements> 4 <requirements>
5 <requirement type="package" version="3.4.1">R</requirement> 5 <requirement type="package" version="3.4.1">R</requirement>
6 </requirements> 6 </requirements>
7 <stdio> 7 <stdio>
8 <exit_code range="1:" /> 8 <exit_code range="1:" />
9 </stdio> 9 </stdio>
10 <command interpreter="Rscript"> 10 <command interpreter="Rscript">
11 $__tool_directory__/id_converter_UniProt.R 11 $__tool_directory__/id_converter_UniProt.R
12 --id_type="$idti.idtypein" 12 --id_type="$species.idtypein"
13 #if $input.ids == "text" 13 #if $input.ids == "text"
14 --input="$input.txt" 14 --input="$input.txt"
15 --input_type="list" 15 --input_type="list"
16 #else 16 #else
17 --input="$input.file" 17 --input="$input.file"
18 --column_number="$input.ncol" 18 --column_number="$input.ncol"
19 --header="$input.header" 19 --header="$input.header"
20 --input_type="file" 20 --input_type="file"
21 #end if 21 #end if
22 --target_ids="$idto.idtypeout" 22 --target_ids="$species.idto.idtypeout"
23 --output="$output" 23 --output="$output"
24 --ref_file="$human_id_mapping" 24 --ref_file="$__tool_directory__/${ filter( lambda x: str( x[0] ) == str( $species.mapping_file ), $__app__.tool_data_tables['id_mapping_tab'].get_fields() )[0][-1] }"
25 25
26 </command> 26 </command>
27 <inputs> 27 <inputs>
28 <conditional name="input" > 28 <conditional name="input" >
29 <param name="ids" type="select" label="Provide your identifiers" help="Copy/paste or ID list from a file (e.g. table)" > 29 <param name="ids" type="select" label="Provide your identifiers" help="Copy/paste or ID list from a file (e.g. table)" >
30 <option value="text">Copy/paste your identifiers</option> 30 <option value="text">Copy/paste your identifiers</option>
31 <option value="file" selected="true">Input file containing your identifiers</option> 31 <option value="file" selected="true">Input file containing your identifiers</option>
32 </param> 32 </param>
33 <when value="text" > 33 <when value="text" >
34 <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by spaces into the form field, for example: P31946 P62258' > 34 <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by "," into the form field, for example: P31946,P62258' >
35 <sanitizer> 35 <sanitizer invalid_char="">
36 <valid initial="string.printable"> 36 <valid initial="string.printable">
37 <remove value="&apos;"/> 37 <remove value="&apos;"/>
38 </valid> 38 </valid>
39 <mapping initial="none"> 39 <mapping initial="none">
40 <add source="&apos;" target="__sq__"/> 40 <add source="&apos;" target="__sq__"/>
41 <add source="&#x20;" target=""/>
42 <add source="&#xA;" target=""/>
43 <add source="&#xD;" target=""/>
44 <add source="&#x9;" target=""/>
41 </mapping> 45 </mapping>
42 </sanitizer> 46 </sanitizer>
43 </param> 47 </param>
44 </when> 48 </when>
45 <when value="file" > 49 <when value="file" >
46 <param name="file" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" /> 50 <param name="file" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" />
47 <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" /> 51 <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" />
48 <param name="ncol" type="text" value="c1" label="The 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' /> 52 <param name="ncol" type="text" value="c1" label="The 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' />
49 </when> 53 </when>
50 </conditional> 54 </conditional>
51 <param name="human_id_mapping" type="select" label="Select species for ID conversion" > 55 <conditional name="species">
52 <options from_data_table="human_id_mapping" > 56 <param name="mapping_file" type="select" label="Select species for ID conversion" >
53 </options> 57 <options from_data_table="id_mapping_tab"/>
54 </param> 58 <option value="human_id_mapping"></option>
55 <conditional name="idti" > 59 <option value="mouse_id_mapping"></option>
56 <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" > 60 </param>
57 <option value="neXtProt_ID" >neXtProt ID (e.g. NX_P31946)</option> 61 <when value="human_id_mapping">
58 <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option> 62 <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" >
59 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> 63 <option value="neXtProt" >neXtProt ID (e.g. NX_P31946)</option>
60 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> 64 <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option>
61 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> 65 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option>
62 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> 66 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option>
63 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> 67 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option>
64 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> 68 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option>
65 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> 69 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option>
66 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> 70 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option>
67 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> 71 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option>
68 <option value="Ensembl" >Ensembl gene ID (e.g. ENSG00000166913)</option> 72 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option>
69 <option value="Ensembl_TRS" >Ensembl transcript ID (e.g. ENST00000353703)</option> 73 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option>
70 <option value="Ensembl_PRO" >Ensembl protein ID (e.g. ENSP00000300161)</option> 74 <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option>
71 </param> 75 <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option>
72 <when value="neXtProt_ID" > 76 <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option>
73 </when> 77 <option value="BioGrid" >BioGrid (e.g. 113361)</option>
74 <when value="UniProt.AC" > 78 <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option>
75 </when> 79 <option value="KEGG" >KEGG (e.g. hsa:7529)</option>
76 <when value="UniProt.ID" > 80 </param>
77 </when> 81 <section name="idto" title="Target type of IDs" expanded="True" >
78 <when value="GeneID" > 82 <param name="idtypeout" type="select" label="Target type of IDs you would like to map to" display="checkboxes" multiple="True" help="Please see example of IDs in help section" >
79 </when> 83 <option value="neXtProt" >neXtProt ID (e.g. NX_P31946)</option>
80 <when value="RefSeq" > 84 <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option>
81 </when> 85 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option>
82 <when value="GI" > 86 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option>
83 </when> 87 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option>
84 <when value="PDB" > 88 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option>
85 </when> 89 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option>
86 <when value="GO" > 90 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option>
87 </when> 91 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option>
88 <when value="PIR" > 92 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option>
89 </when> 93 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option>
90 <when value="MIM" > 94 <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option>
91 </when> 95 <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option>
92 <when value="UniGene" > 96 <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option>
93 </when> 97 <option value="BioGrid" >BioGrid (e.g. 113361)</option>
94 <when value="Ensembl" > 98 <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option>
95 </when> 99 <option value="KEGG" >KEGG (e.g. hsa:7529)</option>
96 <when value="Ensembl_TRS" > 100 </param>
97 </when> 101 </section>
98 <when value="Ensembl_PRO" > 102 </when>
99 </when> 103 <when value="mouse_id_mapping">
100 </conditional> 104 <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" >
101 <section name="idto" title="Target type of IDs" expanded="True" > 105 <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option>
102 <param name="idtypeout" type="select" label="Target type of IDs you would like to map to" display="checkboxes" multiple="True" help="Please see example of IDs in help section" > 106 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option>
103 <option value="neXtProt_ID" >neXtProt ID (e.g. NX_P31946)</option> 107 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option>
104 <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option> 108 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option>
105 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> 109 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option>
106 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> 110 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option>
107 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> 111 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option>
108 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> 112 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option>
109 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> 113 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option>
110 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> 114 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option>
111 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> 115 <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option>
112 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> 116 <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option>
113 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> 117 <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option>
114 <option value="Ensembl" >Ensembl gene ID (e.g. ENSG00000166913)</option> 118 <option value="BioGrid" >BioGrid (e.g. 113361)</option>
115 <option value="Ensembl_TRS" >Ensembl transcript ID (e.g. ENST00000353703)</option> 119 <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option>
116 <option value="Ensembl_PRO" >Ensembl protein ID (e.g. ENSP00000300161)</option> 120 <option value="KEGG" >KEGG (e.g. hsa:7529)</option>
117 </param> 121 </param>
118 </section> 122 <section name="idto" title="Target type of IDs" expanded="True" >
123 <param name="idtypeout" type="select" label="Target type of IDs you would like to map to" display="checkboxes" multiple="True" help="Please see example of IDs in help section" >
124 <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option>
125 <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option>
126 <option value="GeneID" >Entrez gene ID (e.g. 7529)</option>
127 <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option>
128 <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option>
129 <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option>
130 <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option>
131 <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option>
132 <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option>
133 <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option>
134 <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option>
135 <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option>
136 <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option>
137 <option value="BioGrid" >BioGrid (e.g. 113361)</option>
138 <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option>
139 <option value="KEGG" >KEGG (e.g. hsa:7529)</option>
140 </param>
141 </section>
142 </when>
143 </conditional>
119 </inputs> 144 </inputs>
120 <outputs> 145 <outputs>
121 <data name="output" format="tabular" /> 146 <data name="output" format="tabular" />
122 </outputs> 147 </outputs>
123 <tests> 148 <tests>
124 <test> 149 <test>
125 <conditional name="input"> 150 <conditional name="input" >
126 <param name="ids" value="file" /> 151 <param name="ids" value="file"/>
127 <param name="file" value="FKW_Lacombe_et_al_2017_OK.txt" /> 152 <param name="file" value="FKW_Lacombe_et_al_2017_OK.txt" />
128 <param name="header" value="True" /> 153 <param name="header" value="true" />
129 <param name="ncol" value="c1" /> 154 <param name="ncol" value="c1"/>
130 </conditional> 155 </conditional>
131 <conditional name="idti"> 156 <conditional name="species">
132 <param name="idtypein" value="UniProt.AC" /> 157 <param name="mapping_file" value="human_id_mapping"/>
158 <param name="idtypein" value="UniProt.AC"/>
159 <section name="idto">
160 <param name="idtypeout" value="neXtProt,UniProt.ID,GeneID,MIM,Ensembl" />
161 </section>
133 </conditional> 162 </conditional>
134 <section name="idto"> 163 <output name="output" value="ID_Converted_FKW_Lacombe_et_al_2017_OK.txt" />
135 <param name="idtypeout" value="neXtProt_ID,UniProt.ID,GeneID,MIM,Ensembl" />
136 </section>
137 <output name="output" file="ID_Converter_FKW_Lacombe_et_al_2017_OK.txt" />
138 </test> 164 </test>
139 </tests> 165 </tests>
140 <help><![CDATA[ 166 <help><![CDATA[
141 This tool converts a list of IDs to another identifier type, select the source and target type from the dropdown menus above (see below supported source and target types). 167 This tool converts a list of IDs to another identifier type, select the source and target type from the dropdown menus above (see below supported source and target types).
142 168
180 206
181 .. class:: infomark 207 .. class:: infomark
182 208
183 This tool converts human IDs using the following source files: 209 This tool converts human IDs using the following source files:
184 210
185 * HUMAN_9606_idmapping_selected.tab (Uniprot 15/05/2018) 211 * HUMAN_9606_idmapping_selected.tab (Uniprot 02/07/2018)
212 Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/
213
214 * HUMAN_9606_idmapping.dat (Uniprot 02/07/18)
186 Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/ 215 Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/
187 216
188 * nextprot_ac_list_all.txt (Nextprot released on 17/01/2018) 217 * nextprot_ac_list_all.txt (Nextprot released on 17/01/2018)
189 Downloaded from ftp://ftp.nextprot.org/pub/current_release/ac_lists/ 218 Downloaded from ftp://ftp.nextprot.org/pub/current_release/ac_lists/
190 219
201 230
202 .. class:: infomark 231 .. class:: infomark
203 232
204 **Authors** 233 **Authors**
205 234
206 T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR 235 T.P. Lien Nguyen, David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
207 236
208 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform 237 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform
209 238
210 This work has been partially funded through the French National Agency for Research (ANR) IFB project. 239 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
211 240