Mercurial > repos > proteore > proteore_id_converter
diff id_converter.xml @ 14:659f1248f535 draft
planemo upload commit 688c456ca57914a63c20eba942ec5fe81e896099-dirty
| author | proteore |
|---|---|
| date | Wed, 19 Sep 2018 04:45:04 -0400 |
| parents | e30234018582 |
| children | b50d913ec067 |
line wrap: on
line diff
--- a/id_converter.xml Mon Aug 27 06:12:21 2018 -0400 +++ b/id_converter.xml Wed Sep 19 04:45:04 2018 -0400 @@ -1,4 +1,4 @@ -<tool id="IDconverter" name="ID Converter" version="0.1.2"> +<tool id="IDconverter" name="ID Converter" version="2018.09.18"> <description>convert public database identifiers </description> <requirements> @@ -9,7 +9,7 @@ </stdio> <command interpreter="Rscript"> $__tool_directory__/id_converter_UniProt.R - --id_type="$idti.idtypein" + --id_type="$species.idtypein" #if $input.ids == "text" --input="$input.txt" --input_type="list" @@ -19,9 +19,9 @@ --header="$input.header" --input_type="file" #end if - --target_ids="$idto.idtypeout" + --target_ids="$species.idto.idtypeout" --output="$output" - --ref_file="$human_id_mapping" + --ref_file="$__tool_directory__/${ filter( lambda x: str( x[0] ) == str( $species.mapping_file ), $__app__.tool_data_tables['id_mapping_tab'].get_fields() )[0][-1] }" </command> <inputs> @@ -31,13 +31,17 @@ <option value="file" selected="true">Input file containing your identifiers</option> </param> <when value="text" > - <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' > - <sanitizer> + <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by "," into the form field, for example: P31946,P62258' > + <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value="'"/> </valid> <mapping initial="none"> <add source="'" target="__sq__"/> + <add source=" " target=""/> + <add source="
" target=""/> + <add source="
" target=""/> + <add source="	" target=""/> </mapping> </sanitizer> </param> @@ -48,93 +52,115 @@ <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' /> </when> </conditional> - <param name="human_id_mapping" type="select" label="Select species for ID conversion" > - <options from_data_table="human_id_mapping" > - </options> - </param> - <conditional name="idti" > - <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" > - <option value="neXtProt_ID" >neXtProt ID (e.g. NX_P31946)</option> - <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option> - <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> - <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> - <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> - <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> - <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> - <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> - <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> - <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> - <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> - <option value="Ensembl" >Ensembl gene ID (e.g. ENSG00000166913)</option> - <option value="Ensembl_TRS" >Ensembl transcript ID (e.g. ENST00000353703)</option> - <option value="Ensembl_PRO" >Ensembl protein ID (e.g. ENSP00000300161)</option> - </param> - <when value="neXtProt_ID" > - </when> - <when value="UniProt.AC" > - </when> - <when value="UniProt.ID" > - </when> - <when value="GeneID" > - </when> - <when value="RefSeq" > - </when> - <when value="GI" > - </when> - <when value="PDB" > - </when> - <when value="GO" > - </when> - <when value="PIR" > - </when> - <when value="MIM" > - </when> - <when value="UniGene" > - </when> - <when value="Ensembl" > - </when> - <when value="Ensembl_TRS" > - </when> - <when value="Ensembl_PRO" > - </when> - </conditional> - <section name="idto" title="Target type of IDs" expanded="True" > - <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" > - <option value="neXtProt_ID" >neXtProt ID (e.g. NX_P31946)</option> - <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option> - <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> - <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> - <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> - <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> - <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> - <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> - <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> - <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> - <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> - <option value="Ensembl" >Ensembl gene ID (e.g. ENSG00000166913)</option> - <option value="Ensembl_TRS" >Ensembl transcript ID (e.g. ENST00000353703)</option> - <option value="Ensembl_PRO" >Ensembl protein ID (e.g. ENSP00000300161)</option> - </param> - </section> + <conditional name="species"> + <param name="mapping_file" type="select" label="Select species for ID conversion" > + <options from_data_table="id_mapping_tab"/> + <option value="human_id_mapping"></option> + <option value="mouse_id_mapping"></option> + </param> + <when value="human_id_mapping"> + <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" > + <option value="neXtProt" >neXtProt ID (e.g. NX_P31946)</option> + <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option> + <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> + <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> + <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> + <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> + <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> + <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> + <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> + <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> + <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> + <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option> + <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option> + <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option> + <option value="BioGrid" >BioGrid (e.g. 113361)</option> + <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option> + <option value="KEGG" >KEGG (e.g. hsa:7529)</option> + </param> + <section name="idto" title="Target type of IDs" expanded="True" > + <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" > + <option value="neXtProt" >neXtProt ID (e.g. NX_P31946)</option> + <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option> + <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> + <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> + <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> + <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> + <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> + <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> + <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> + <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> + <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> + <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option> + <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option> + <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option> + <option value="BioGrid" >BioGrid (e.g. 113361)</option> + <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option> + <option value="KEGG" >KEGG (e.g. hsa:7529)</option> + </param> + </section> + </when> + <when value="mouse_id_mapping"> + <param name="idtypein" type="select" label="Select type/source of identifier of your list" help="Please see example of IDs in help section" > + <option value="UniProt.AC" selected="True" >Uniprot accession number (e.g. P31946)</option> + <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> + <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> + <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> + <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> + <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> + <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> + <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> + <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> + <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> + <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option> + <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option> + <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option> + <option value="BioGrid" >BioGrid (e.g. 113361)</option> + <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option> + <option value="KEGG" >KEGG (e.g. hsa:7529)</option> + </param> + <section name="idto" title="Target type of IDs" expanded="True" > + <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" > + <option value="UniProt.AC" >Uniprot accession number (e.g. P31946)</option> + <option value="UniProt.ID" >Uniprot ID (e.g 1433B_HUMAN)</option> + <option value="GeneID" >Entrez gene ID (e.g. 7529)</option> + <option value="RefSeq" >RefSeq (NCBI) protein (e.g. NP_003395.1)</option> + <option value="GI" >GI (NCBI GI number) ID assigned to each sequence record processed by NCBI (e.g. 21328448)</option> + <option value="PDB" >Protein DataBank ID (e.g. 2BR9:A)</option> + <option value="GO" >GOterms (Gene Ontology) ID (e.g. GO:0070062)</option> + <option value="PIR" >Protein Information Resource ID (e.g. S34755)</option> + <option value="MIM" >OMIM (Online Mendelian Inheritance in Man database) ID (e.g: 601289)</option> + <option value="UniGene" >Unigene ID (e.g. Hs.643544)</option> + <option value="Ensembl_Gene" >Ensembl gene ID (e.g. ENSG00000166913)</option> + <option value="Ensembl_Transcript" >Ensembl transcript ID (e.g. ENST00000353703)</option> + <option value="Ensembl_Protein" >Ensembl protein ID (e.g. ENSP00000300161)</option> + <option value="BioGrid" >BioGrid (e.g. 113361)</option> + <option value="STRING" >STRING (e.g. 9606.ENSP00000300161)</option> + <option value="KEGG" >KEGG (e.g. hsa:7529)</option> + </param> + </section> + </when> + </conditional> </inputs> <outputs> <data name="output" format="tabular" /> </outputs> <tests> <test> - <conditional name="input"> - <param name="ids" value="file" /> + <conditional name="input" > + <param name="ids" value="file"/> <param name="file" value="FKW_Lacombe_et_al_2017_OK.txt" /> - <param name="header" value="True" /> - <param name="ncol" value="c1" /> + <param name="header" value="true" /> + <param name="ncol" value="c1"/> </conditional> - <conditional name="idti"> - <param name="idtypein" value="UniProt.AC" /> + <conditional name="species"> + <param name="mapping_file" value="human_id_mapping"/> + <param name="idtypein" value="UniProt.AC"/> + <section name="idto"> + <param name="idtypeout" value="neXtProt,UniProt.ID,GeneID,MIM,Ensembl" /> + </section> </conditional> - <section name="idto"> - <param name="idtypeout" value="neXtProt_ID,UniProt.ID,GeneID,MIM,Ensembl" /> - </section> - <output name="output" file="ID_Converter_FKW_Lacombe_et_al_2017_OK.txt" /> + <output name="output" value="ID_Converted_FKW_Lacombe_et_al_2017_OK.txt" /> </test> </tests> <help><![CDATA[ @@ -182,7 +208,10 @@ This tool converts human IDs using the following source files: -* HUMAN_9606_idmapping_selected.tab (Uniprot 15/05/2018) +* HUMAN_9606_idmapping_selected.tab (Uniprot 02/07/2018) + Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/ + +* HUMAN_9606_idmapping.dat (Uniprot 02/07/18) Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/ * nextprot_ac_list_all.txt (Nextprot released on 17/01/2018) @@ -203,7 +232,7 @@ **Authors** -T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR +T.P. Lien Nguyen, David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform