+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
import jalview.api.FeatureColourI;
import jalview.datamodel.SequenceI;
import jalview.io.gff.SequenceOntologyFactory;
import jalview.io.gff.SequenceOntologyI;
-import jalview.schemes.FeatureColourAdapter;
+import jalview.schemes.FeatureColour;
import jalview.schemes.FeatureSettingsAdapter;
import jalview.util.MapList;
-import jalview.util.StringUtils;
import java.awt.Color;
import java.io.UnsupportedEncodingException;
*/
public class EnsemblGene extends EnsemblSeqProxy
{
- private static final List<String> CROSS_REFERENCES = Arrays
- .asList(new String[] { "CCDS" });
-
private static final String GENE_PREFIX = "gene:";
/*
* </ul>
*
* @param query
- * one or more identifiers separated by a space
- * @return an alignment containing one or more genes, and possibly
- * transcripts, or null
+ * a single gene or transcript identifier or gene name
+ * @return an alignment containing a gene, and possibly transcripts, or null
*/
@Override
public AlignmentI getSequenceRecords(String query) throws Exception
{
- // todo: tidy up handling of one or multiple accession ids
- String[] queries = query.split(getAccessionSeparator());
-
/*
- * if given a transcript id, look up its gene parent
+ * convert to a non-duplicated list of gene identifiers
*/
- if (isTranscriptIdentifier(query))
+ List<String> geneIds = getGeneIds(query);
+
+ AlignmentI al = null;
+ for (String geneId : geneIds)
{
- // we are assuming all transcripts have the same gene parent here
- query = new EnsemblLookup(getDomain()).getParent(queries[0]);
- if (query == null)
+ /*
+ * fetch the gene sequence(s) with features and xrefs
+ */
+ AlignmentI geneAlignment = super.getSequenceRecords(geneId);
+ if (geneAlignment == null)
{
- return null;
+ continue;
}
- }
-
- /*
- * if given a gene or other external name, lookup and fetch
- * the corresponding gene for all model organisms
- */
- if (!isGeneIdentifier(query))
- {
- List<String> geneIds = new EnsemblSymbol(getDomain()).getIds(query);
- if (geneIds.isEmpty())
+ if (geneAlignment.getHeight() == 1)
{
- return null;
+ getTranscripts(geneAlignment, geneId);
+ }
+ if (al == null)
+ {
+ al = geneAlignment;
+ }
+ else
+ {
+ al.append(geneAlignment);
}
- String theIds = StringUtils.listToDelimitedString(geneIds,
- getAccessionSeparator());
- return getSequenceRecords(theIds);
- }
-
- /*
- * fetch the gene sequence(s) with features and xrefs
- */
- AlignmentI al = super.getSequenceRecords(query);
-
- /*
- * if we retrieved a single gene, get its transcripts as well
- */
- if (al.getHeight() == 1)
- {
- getTranscripts(al, query);
}
-
return al;
}
/**
- * Attempts to get Ensembl stable identifiers for model organisms for a gene
- * name by calling the xrefs symbol REST service to resolve the gene name.
+ * Converts a query, which may contain one or more gene, transcript, or
+ * external (to Ensembl) identifiers, into a non-redundant list of gene
+ * identifiers.
*
- * @param query
+ * @param accessions
* @return
*/
- protected String getGeneIdentifiersForName(String query)
+ List<String> getGeneIds(String accessions)
{
- List<String> ids = new EnsemblSymbol(getDomain()).getIds(query);
- if (ids != null)
+ List<String> geneIds = new ArrayList<String>();
+
+ for (String acc : accessions.split(getAccessionSeparator()))
{
- for (String id : ids)
+ /*
+ * First try lookup as an Ensembl (gene or transcript) identifier
+ */
+ String geneId = new EnsemblLookup(getDomain()).getGeneId(acc);
+ if (geneId != null)
{
- if (isGeneIdentifier(id))
+ if (!geneIds.contains(geneId))
{
- return id;
+ geneIds.add(geneId);
+ }
+ }
+ else
+ {
+ /*
+ * if given a gene or other external name, lookup and fetch
+ * the corresponding gene for all model organisms
+ */
+ List<String> ids = new EnsemblSymbol(getDomain(), getDbSource(),
+ getDbVersion()).getGeneIds(acc);
+ for (String id : ids)
+ {
+ if (!geneIds.contains(id))
+ {
+ geneIds.add(id);
+ }
}
}
}
- return null;
+ return geneIds;
}
/**
}
}
gene.setSequenceFeatures(filtered
- .toArray(new SequenceFeature[filtered
- .size()]));
+ .toArray(new SequenceFeature[filtered.size()]));
}
}
return false;
}
- @Override
- protected List<String> getCrossReferenceDatabases()
- {
- // found these for ENSG00000157764 on 30/01/2016:
- // return new String[] {"Vega_gene", "OTTG", "ENS_LRG_gene", "ArrayExpress",
- // "EntrezGene", "HGNC", "MIM_GENE", "MIM_MORBID", "WikiGene"};
- return CROSS_REFERENCES;
- }
-
/**
* Override to do nothing as Ensembl doesn't return a protein sequence for a
* gene identifier
return new FeatureSettingsAdapter()
{
SequenceOntologyI so = SequenceOntologyFactory.getInstance();
+
@Override
public boolean isFeatureDisplayed(String type)
{
{
if (so.isA(type, SequenceOntologyI.EXON))
{
- return new FeatureColourAdapter()
+ return new FeatureColour()
{
@Override
public boolean isColourByLabel()
}
if (so.isA(type, SequenceOntologyI.SEQUENCE_VARIANT))
{
- return new FeatureColourAdapter()
+ return new FeatureColour()
{
@Override