X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblGene.java;h=edeeeddb08d5ac7ebc5d6708a30f60df29e94de1;hb=3d0101179759ef157b088ea135423cd909512d9f;hp=df4e45a7e07fdb9f0d11a836755e10964c11ace8;hpb=c406d789d51e6ac1ff45e3568d37e9ed53025f03;p=jalview.git
diff --git a/src/jalview/ext/ensembl/EnsemblGene.java b/src/jalview/ext/ensembl/EnsemblGene.java
index df4e45a..edeeedd 100644
--- a/src/jalview/ext/ensembl/EnsemblGene.java
+++ b/src/jalview/ext/ensembl/EnsemblGene.java
@@ -1,16 +1,40 @@
+/*
+ * 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 .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
-import jalview.api.FeatureSettingsI;
+import jalview.api.FeatureColourI;
+import jalview.api.FeatureSettingsModelI;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
import jalview.io.gff.SequenceOntologyFactory;
import jalview.io.gff.SequenceOntologyI;
-import jalview.schemes.FeatureColourScheme;
+import jalview.schemes.FeatureColour;
+import jalview.schemes.FeatureSettingsAdapter;
import jalview.util.MapList;
-import jalview.util.StringUtils;
+import java.awt.Color;
+import java.io.UnsupportedEncodingException;
+import java.net.URLDecoder;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
@@ -37,10 +61,28 @@ public class EnsemblGene extends EnsemblSeqProxy
EnsemblFeatureType.exon, EnsemblFeatureType.cds,
EnsemblFeatureType.variation };
+ /**
+ * Default constructor (to use rest.ensembl.org)
+ */
+ public EnsemblGene()
+ {
+ super();
+ }
+
+ /**
+ * Constructor given the target domain to fetch data from
+ *
+ * @param d
+ */
+ public EnsemblGene(String d)
+ {
+ super(d);
+ }
+
@Override
public String getDbName()
{
- return "ENSEMBL (GENE)";
+ return "ENSEMBL";
}
@Override
@@ -67,7 +109,8 @@ public class EnsemblGene extends EnsemblSeqProxy
*
resolves an external identifier by looking up xref-ed gene ids
* fetches the gene sequence
* fetches features on the sequence
- * identifies "transcript" features whose Parent is the requested gene
+ * identifies "transcript" features whose Parent is the requested
+ * gene
* fetches the transcript sequence for each transcript
* makes a mapping from the gene to each transcript
* copies features from gene to transcript sequences
@@ -78,56 +121,110 @@ public class EnsemblGene extends EnsemblSeqProxy
*
*
* @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 geneIds = getGeneIds(query);
+
+ AlignmentI al = null;
+ for (String geneId : geneIds)
{
- // we are assuming all transcripts have the same gene parent here
- query = new EnsemblLookup().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 (geneAlignment.getHeight() == 1)
+ {
+ getTranscripts(geneAlignment, geneId);
+ }
+ if (al == null)
+ {
+ al = geneAlignment;
+ }
+ else
+ {
+ al.append(geneAlignment);
}
}
+ return al;
+ }
- /*
- * if given a gene or other external name, lookup and fetch
- * the corresponding gene for all model organisms
- */
- if (!isGeneIdentifier(query))
+ /**
+ * Converts a query, which may contain one or more gene or transcript
+ * identifiers, into a non-redundant list of gene identifiers.
+ *
+ * @param accessions
+ * @return
+ */
+ List getGeneIds(String accessions)
+ {
+ List geneIds = new ArrayList();
+
+ for (String acc : accessions.split(getAccessionSeparator()))
{
- List geneIds = new EnsemblSymbol().getIds(query);
- if (geneIds.isEmpty())
+ if (isGeneIdentifier(acc))
{
- return null;
+ if (!geneIds.contains(acc))
+ {
+ geneIds.add(acc);
+ }
}
- String theIds = StringUtils.listToDelimitedString(geneIds,
- getAccessionSeparator());
- return getSequenceRecords(theIds);
- }
- AlignmentI al = super.getSequenceRecords(query);
+ /*
+ * if given a transcript id, look up its gene parent
+ */
+ else if (isTranscriptIdentifier(acc))
+ {
+ String geneId = new EnsemblLookup(getDomain()).getParent(acc);
+ if (geneId != null && !geneIds.contains(geneId))
+ {
+ geneIds.add(geneId);
+ }
+ }
+ else if (isProteinIdentifier(acc))
+ {
+ String tscriptId = new EnsemblLookup(getDomain()).getParent(acc);
+ if (tscriptId != null)
+ {
+ String geneId = new EnsemblLookup(getDomain())
+ .getParent(tscriptId);
- /*
- * if we retrieved a single gene, get its transcripts as well
- */
- if (al.getHeight() == 1)
- {
- getTranscripts(al, query);
+ if (geneId != null && !geneIds.contains(geneId))
+ {
+ geneIds.add(geneId);
+ }
+ }
+ // NOTE - acc is lost if it resembles an ENS.+ ID but isn't actually
+ // resolving to one... e.g. ENSMICP00000009241
+ }
+ /*
+ * if given a gene or other external name, lookup and fetch
+ * the corresponding gene for all model organisms
+ */
+ else
+ {
+ List ids = new EnsemblSymbol(getDomain(), getDbSource(),
+ getDbVersion()).getIds(acc);
+ for (String geneId : ids)
+ {
+ if (!geneIds.contains(geneId))
+ {
+ geneIds.add(geneId);
+ }
+ }
+ }
}
-
- return al;
+ return geneIds;
}
/**
@@ -139,7 +236,8 @@ public class EnsemblGene extends EnsemblSeqProxy
*/
protected String getGeneIdentifiersForName(String query)
{
- List ids = new EnsemblSymbol().getIds(query);
+ List ids = new EnsemblSymbol(getDomain(), getDbSource(),
+ getDbVersion()).getIds(query);
if (ids != null)
{
for (String id : ids)
@@ -173,6 +271,35 @@ public class EnsemblGene extends EnsemblSeqProxy
{
makeTranscript(transcriptFeature, al, gene);
}
+
+ clearGeneFeatures(gene);
+ }
+
+ /**
+ * Remove unwanted features (transcript, exon, CDS) from the gene sequence
+ * after we have used them to derive transcripts and transfer features
+ *
+ * @param gene
+ */
+ protected void clearGeneFeatures(SequenceI gene)
+ {
+ SequenceFeature[] sfs = gene.getSequenceFeatures();
+ if (sfs != null)
+ {
+ SequenceOntologyI so = SequenceOntologyFactory.getInstance();
+ List filtered = new ArrayList();
+ for (SequenceFeature sf : sfs)
+ {
+ String type = sf.getType();
+ if (!isTranscript(type) && !so.isA(type, SequenceOntologyI.EXON)
+ && !so.isA(type, SequenceOntologyI.CDS))
+ {
+ filtered.add(sf);
+ }
+ }
+ gene.setSequenceFeatures(
+ filtered.toArray(new SequenceFeature[filtered.size()]));
+ }
}
/**
@@ -188,8 +315,8 @@ public class EnsemblGene extends EnsemblSeqProxy
* the parent gene sequence, with features
* @return
*/
- SequenceI makeTranscript(SequenceFeature transcriptFeature,
- AlignmentI al, SequenceI gene)
+ SequenceI makeTranscript(SequenceFeature transcriptFeature, AlignmentI al,
+ SequenceI gene)
{
String accId = getTranscriptId(transcriptFeature);
if (accId == null)
@@ -237,11 +364,27 @@ public class EnsemblGene extends EnsemblSeqProxy
mappedFrom.add(new int[] { sf.getBegin(), sf.getEnd() });
}
- Sequence transcript = new Sequence(accId, seqChars, 1, transcriptLength);
- String geneName = (String) transcriptFeature.getValue(NAME);
- if (geneName != null)
+ Sequence transcript = new Sequence(accId, seqChars, 1,
+ transcriptLength);
+
+ /*
+ * Ensembl has gene name as transcript Name
+ * EnsemblGenomes doesn't, but has a url-encoded description field
+ */
+ String description = (String) transcriptFeature.getValue(NAME);
+ if (description == null)
+ {
+ description = (String) transcriptFeature.getValue(DESCRIPTION);
+ }
+ if (description != null)
{
- transcript.setDescription(geneName);
+ try
+ {
+ transcript.setDescription(URLDecoder.decode(description, "UTF-8"));
+ } catch (UnsupportedEncodingException e)
+ {
+ e.printStackTrace(); // as if
+ }
}
transcript.createDatasetSequence();
@@ -254,18 +397,19 @@ public class EnsemblGene extends EnsemblSeqProxy
List mapTo = new ArrayList();
mapTo.add(new int[] { 1, transcriptLength });
MapList mapping = new MapList(mappedFrom, mapTo, 1, 1);
- new EnsemblCdna().transferFeatures(gene.getSequenceFeatures(),
+ EnsemblCdna cdna = new EnsemblCdna(getDomain());
+ cdna.transferFeatures(gene.getSequenceFeatures(),
transcript.getDatasetSequence(), mapping, parentId);
/*
* fetch and save cross-references
*/
- super.getCrossReferences(transcript);
+ cdna.getCrossReferences(transcript);
/*
* and finally fetch the protein product and save as a cross-reference
*/
- new EnsemblCdna().addProteinProduct(transcript);
+ cdna.addProteinProduct(transcript);
return transcript;
}
@@ -362,13 +506,13 @@ public class EnsemblGene extends EnsemblSeqProxy
@Override
protected boolean retainFeature(SequenceFeature sf, String accessionId)
{
- if (SequenceOntologyFactory.getInstance().isA(sf.getType(),
- SequenceOntologyI.GENE))
+ SequenceOntologyI so = SequenceOntologyFactory.getInstance();
+ String type = sf.getType();
+ if (so.isA(type, SequenceOntologyI.GENE))
{
return false;
}
-
- if (isTranscript(sf.getType()))
+ if (isTranscript(type))
{
String parent = (String) sf.getValue(PARENT);
if (!(GENE_PREFIX + accessionId).equals(parent))
@@ -390,15 +534,6 @@ public class EnsemblGene extends EnsemblSeqProxy
return false;
}
- @Override
- protected List 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 super.getCrossReferenceDatabases();
- }
-
/**
* Override to do nothing as Ensembl doesn't return a protein sequence for a
* gene identifier
@@ -414,10 +549,84 @@ public class EnsemblGene extends EnsemblSeqProxy
return ACCESSION_REGEX;
}
+ /**
+ * Returns a descriptor for suitable feature display settings with
+ *
+ * - only exon or sequence_variant features (or their subtypes in the
+ * Sequence Ontology) visible
+ * - variant features coloured red
+ * - exon features coloured by label (exon name)
+ * - variants displayed above (on top of) exons
+ *
+ */
@Override
- public FeatureSettingsI getFeatureColourScheme()
+ public FeatureSettingsModelI getFeatureColourScheme()
{
- return FeatureColourScheme.EnsemblVariants;
+ return new FeatureSettingsAdapter()
+ {
+ SequenceOntologyI so = SequenceOntologyFactory.getInstance();
+
+ @Override
+ public boolean isFeatureDisplayed(String type)
+ {
+ return (so.isA(type, SequenceOntologyI.EXON)
+ || so.isA(type, SequenceOntologyI.SEQUENCE_VARIANT));
+ }
+
+ @Override
+ public FeatureColourI getFeatureColour(String type)
+ {
+ if (so.isA(type, SequenceOntologyI.EXON))
+ {
+ return new FeatureColour()
+ {
+ @Override
+ public boolean isColourByLabel()
+ {
+ return true;
+ }
+ };
+ }
+ if (so.isA(type, SequenceOntologyI.SEQUENCE_VARIANT))
+ {
+ return new FeatureColour()
+ {
+
+ @Override
+ public Color getColour()
+ {
+ return Color.RED;
+ }
+ };
+ }
+ return null;
+ }
+
+ /**
+ * order to render sequence_variant after exon after the rest
+ */
+ @Override
+ public int compare(String feature1, String feature2)
+ {
+ if (so.isA(feature1, SequenceOntologyI.SEQUENCE_VARIANT))
+ {
+ return +1;
+ }
+ if (so.isA(feature2, SequenceOntologyI.SEQUENCE_VARIANT))
+ {
+ return -1;
+ }
+ if (so.isA(feature1, SequenceOntologyI.EXON))
+ {
+ return +1;
+ }
+ if (so.isA(feature2, SequenceOntologyI.EXON))
+ {
+ return -1;
+ }
+ return 0;
+ }
+ };
}
}