diff id_converter.xml @ 9:cf91623c09f5 draft

planemo upload commit 328e16fd172a591be630a80c71288e09bafa8edd-dirty
author proteore
date Thu, 25 Oct 2018 04:35:27 -0400
parents f0029ded78dd
children 8ea75a21fe30
line wrap: on
line diff
--- a/id_converter.xml	Tue Sep 18 04:55:47 2018 -0400
+++ b/id_converter.xml	Thu Oct 25 04:35:27 2018 -0400
@@ -1,5 +1,5 @@
-<tool id="IDconverter" name="ID Converter" version="2018.09.18">
-    <description>convert public database identifiers
+<tool id="IDconverter" name="ID Converter" version="2018.10.12">
+    <description>(Human, Mouse, Rat)
     </description>
     <requirements>
       <requirement type="package" version="3.4.1">R</requirement>
@@ -8,7 +8,7 @@
         <exit_code range="1:" />
     </stdio>
     <command interpreter="Rscript">
-        $__tool_directory__/id_converter_UniProt.R
+        $__tool_directory__/id_converter.R
         --id_type="$species.idtypein"
         #if $input.ids == "text"
             --input="$input.txt"
@@ -21,7 +21,7 @@
         #end if
         --target_ids="$species.idto.idtypeout"
         --output="$output"
-        --ref_file="$__tool_directory__/${ filter( lambda x: str( x[0] ) == str( $species.mapping_file ), $__app__.tool_data_tables['id_mapping_tab'].get_fields() )[0][-1] }"
+        --ref_file="$__tool_directory__/${ filter( lambda x: str( x[1] ) == str( $species.mapping_file ), $__app__.tool_data_tables['id_mapping'].get_fields() )[0][-1] }"
         
     </command>
     <inputs>
@@ -54,9 +54,10 @@
         </conditional>
         <conditional name="species">
             <param name="mapping_file" type="select" label="Select species for ID conversion" >
-                <options from_data_table="id_mapping_tab"/>
+                <options from_data_table="id_mapping"/>
                 <option value="human_id_mapping"></option>
                 <option value="mouse_id_mapping"></option>
+                <option value="rat_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" >
@@ -76,7 +77,7 @@
                     <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>
+                    <option value="KEGG" >KEGG gene id (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" >
@@ -96,7 +97,7 @@
                         <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>
+                        <option value="KEGG" >KEGG gene id (e.g. hsa:7529)</option>
                     </param>
                 </section>
             </when>
@@ -117,7 +118,7 @@
                     <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>
+                    <option value="KEGG" >KEGG gene id (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" >
@@ -129,21 +130,59 @@
                         <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>
+                        <option value="KEGG" >KEGG gene id (e.g. hsa:7529)</option>
+                    </param>
+                </section>
+            </when>
+            <when value="rat_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 gene id (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="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 gene id (e.g. hsa:7529)</option>
                     </param>
                 </section>
             </when>
         </conditional>
     </inputs>
     <outputs>
-        <data name="output" format="tabular" />
+        <data name="output" format="tsv" />
     </outputs>
     <tests>
         <test>
@@ -202,6 +241,16 @@
 
 * Ensembl protein ID (e.g. ENSP00000300161)
 
+* BioGrid (e.g. 113361)
+
+* STRING (e.g. 9606.ENSP00000300161)
+
+* KEGG gene id (e.g. hsa:7529)
+
+.. class:: warningmark 
+
+Nextprot and OMIM are only available for Human.
+
 -----
 
 .. class:: infomark
@@ -217,6 +266,12 @@
 * nextprot_ac_list_all.txt (Nextprot released on 17/01/2018)
     Downloaded from ftp://ftp.nextprot.org/pub/current_release/ac_lists/
 
+* MOUSE_10090_idmapping_selected.tab (Uniprot 02/07/2018)
+    Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/
+
+* MOUSE_10090_idmapping.dat (Uniprot 02/07/18)
+    Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/
+
 -----
 
 .. class:: warningmark
@@ -232,7 +287,7 @@
 
 **Authors**
 
-T.P. Lien Nguyen, David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+David Christiany, T.P. Lien Nguyen, 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