X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblSeqProxy.java;h=233707b5de906247c5c8305bedcaab492c87e5f2;hb=4324ab9c09ac74782aef9493b98280060bccd5e8;hp=5a32736798417f8ef16ea78abe5096506bd48cf5;hpb=76de4fc452184b56e01960d05cb2235b1807e836;p=jalview.git
diff --git a/src/jalview/ext/ensembl/EnsemblSeqProxy.java b/src/jalview/ext/ensembl/EnsemblSeqProxy.java
index 5a32736..233707b 100644
--- a/src/jalview/ext/ensembl/EnsemblSeqProxy.java
+++ b/src/jalview/ext/ensembl/EnsemblSeqProxy.java
@@ -1,10 +1,32 @@
+/*
+ * 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.analysis.AlignmentUtils;
import jalview.analysis.Dna;
+import jalview.bin.Cache;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
import jalview.datamodel.Mapping;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
@@ -16,6 +38,7 @@ import jalview.io.gff.SequenceOntologyI;
import jalview.util.Comparison;
import jalview.util.DBRefUtils;
import jalview.util.MapList;
+import jalview.util.RangeComparator;
import java.io.IOException;
import java.net.MalformedURLException;
@@ -88,26 +111,6 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
}
/**
- * A comparator to sort ranges into ascending start position order
- */
- private class RangeSorter implements Comparator
- {
- boolean forwards;
-
- RangeSorter(boolean forward)
- {
- forwards = forward;
- }
-
- @Override
- public int compare(int[] o1, int[] o2)
- {
- return (forwards ? 1 : -1) * Integer.compare(o1[0], o2[0]);
- }
-
- }
-
- /**
* Default constructor (to use rest.ensembl.org)
*/
public EnsemblSeqProxy()
@@ -158,6 +161,7 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
+ " chunks. Unexpected problem (" + r.getLocalizedMessage()
+ ")";
System.err.println(msg);
+ r.printStackTrace();
break;
}
}
@@ -210,7 +214,7 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
EnsemblFeatureType[] features = getFeaturesToFetch();
AlignmentI geneFeatures = gffFetcher.getSequenceRecords(accId,
features);
- if (geneFeatures.getHeight() > 0)
+ if (geneFeatures != null && geneFeatures.getHeight() > 0)
{
genomicSequence = geneFeatures.getSequenceAt(0);
}
@@ -271,7 +275,8 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
proteinSeq.createDatasetSequence();
querySeq.createDatasetSequence();
- MapList mapList = AlignmentUtils.mapCdsToProtein(querySeq, proteinSeq);
+ MapList mapList = AlignmentUtils
+ .mapCdsToProtein(querySeq, proteinSeq);
if (mapList != null)
{
// clunky: ensure Uniprot xref if we have one is on mapped sequence
@@ -281,12 +286,52 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
DBRefEntry dbr = new DBRefEntry(getDbSource(),
getEnsemblDataVersion(), proteinSeq.getName(), map);
querySeq.getDatasetSequence().addDBRef(dbr);
-
+ DBRefEntry[] uprots = DBRefUtils.selectRefs(ds.getDBRefs(),
+ new String[] { DBRefSource.UNIPROT });
+ DBRefEntry[] upxrefs = DBRefUtils.selectRefs(querySeq.getDBRefs(),
+ new String[] { DBRefSource.UNIPROT });
+ if (uprots != null)
+ {
+ for (DBRefEntry up : uprots)
+ {
+ // locate local uniprot ref and map
+ List upx = DBRefUtils.searchRefs(upxrefs,
+ up.getAccessionId());
+ DBRefEntry upxref;
+ if (upx.size() != 0)
+ {
+ upxref = upx.get(0);
+
+ if (upx.size() > 1)
+ {
+ Cache.log
+ .warn("Implementation issue - multiple uniprot acc on product sequence.");
+ }
+ }
+ else
+ {
+ upxref = new DBRefEntry(DBRefSource.UNIPROT,
+ getEnsemblDataVersion(), up.getAccessionId());
+ }
+
+ Mapping newMap = new Mapping(ds, mapList);
+ upxref.setVersion(getEnsemblDataVersion());
+ upxref.setMap(newMap);
+ if (upx.size() == 0)
+ {
+ // add the new uniprot ref
+ querySeq.getDatasetSequence().addDBRef(upxref);
+ }
+
+ }
+ }
+
/*
* copy exon features to protein, compute peptide variants from dna
* variants and add as features on the protein sequence ta-da
*/
- AlignmentUtils.computeProteinFeatures(querySeq, proteinSeq, mapList);
+ AlignmentUtils
+ .computeProteinFeatures(querySeq, proteinSeq, mapList);
}
} catch (Exception e)
{
@@ -343,6 +388,11 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
throw new JalviewException("ENSEMBL Rest API not available.");
}
FileParse fp = getSequenceReader(ids);
+ if (fp == null)
+ {
+ return alignment;
+ }
+
FastaFile fr = new FastaFile(fp);
if (fr.hasWarningMessage())
{
@@ -367,9 +417,8 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
if (fr.getSeqs().size() > 0)
{
- AlignmentI seqal = new Alignment(
- fr.getSeqsAsArray());
- for (SequenceI sq:seqal.getSequences())
+ AlignmentI seqal = new Alignment(fr.getSeqsAsArray());
+ for (SequenceI sq : seqal.getSequences())
{
if (sq.getDescription() == null)
{
@@ -501,7 +550,7 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
int mappedLength = 0;
int direction = 1; // forward
boolean directionSet = false;
-
+
for (SequenceFeature sf : sfs)
{
/*
@@ -518,20 +567,20 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
// abort - mix of forward and backward
System.err.println("Error: forward and backward strand for "
+ accId);
- return null;
- }
- direction = strand;
- directionSet = true;
-
- /*
- * add to CDS ranges, semi-sorted forwards/backwards
- */
- if (strand < 0)
- {
- regions.add(0, new int[] { sf.getEnd(), sf.getBegin() });
- }
- else
- {
+ return null;
+ }
+ direction = strand;
+ directionSet = true;
+
+ /*
+ * add to CDS ranges, semi-sorted forwards/backwards
+ */
+ if (strand < 0)
+ {
+ regions.add(0, new int[] { sf.getEnd(), sf.getBegin() });
+ }
+ else
+ {
regions.add(new int[] { sf.getBegin(), sf.getEnd() });
}
mappedLength += Math.abs(sf.getEnd() - sf.getBegin() + 1);
@@ -546,7 +595,7 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
}
}
}
-
+
if (regions.isEmpty())
{
System.out.println("Failed to identify target sequence for " + accId
@@ -558,11 +607,11 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
* a final sort is needed since Ensembl returns CDS sorted within source
* (havana / ensembl_havana)
*/
- Collections.sort(regions, new RangeSorter(direction == 1));
-
+ Collections.sort(regions, new RangeComparator(direction == 1));
+
List to = Arrays.asList(new int[] { start,
start + mappedLength - 1 });
-
+
return new MapList(regions, to, 1, 1);
}
@@ -606,12 +655,16 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
int start = sf.getBegin();
int end = sf.getEnd();
int[] mappedRange = mapping.locateInTo(start, end);
-
+
if (mappedRange != null)
{
SequenceFeature copy = new SequenceFeature(sf);
copy.setBegin(Math.min(mappedRange[0], mappedRange[1]));
copy.setEnd(Math.max(mappedRange[0], mappedRange[1]));
+ if (".".equals(copy.getFeatureGroup()))
+ {
+ copy.setFeatureGroup(getDbSource());
+ }
targetSequence.addSequenceFeature(copy);
/*
@@ -712,8 +765,8 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
// long start = System.currentTimeMillis();
SequenceFeature[] sfs = sourceSequence.getSequenceFeatures();
- MapList mapping = getGenomicRangesFromFeatures(sourceSequence, accessionId,
- targetSequence.getStart());
+ MapList mapping = getGenomicRangesFromFeatures(sourceSequence,
+ accessionId, targetSequence.getStart());
if (mapping == null)
{
return false;
@@ -844,11 +897,13 @@ public abstract class EnsemblSeqProxy extends EnsemblRestClient
String type, String parentId)
{
List result = new ArrayList();
-
+
SequenceFeature[] sfs = sequence.getSequenceFeatures();
- if (sfs != null) {
+ if (sfs != null)
+ {
SequenceOntologyI so = SequenceOntologyFactory.getInstance();
- for (SequenceFeature sf :sfs) {
+ for (SequenceFeature sf : sfs)
+ {
if (so.isA(sf.getType(), type))
{
String parent = (String) sf.getValue(PARENT);