+/*
+ * 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.analysis.AlignmentUtils;
import jalview.analysis.Dna;
+import jalview.bin.Cache;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.util.Comparison;
import jalview.util.DBRefUtils;
import jalview.util.MapList;
+import jalview.util.RangeComparator;
import java.io.IOException;
import java.net.MalformedURLException;
}
/**
- * A comparator to sort ranges into ascending start position order
- */
- private class RangeSorter implements Comparator<int[]>
- {
- 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()
// danger: accession separator used as a regex here, a string elsewhere
// in this case it is ok (it is just a space), but (e.g.) '\' would not be
- List<String> allIds = Arrays.asList(query
- .split(getAccessionSeparator()));
+ List<String> allIds = Arrays
+ .asList(query.split(getAccessionSeparator()));
AlignmentI alignment = null;
inProgress = true;
+ " chunks. Unexpected problem (" + r.getLocalizedMessage()
+ ")";
System.err.println(msg);
+ r.printStackTrace();
break;
}
}
EnsemblFeatureType[] features = getFeaturesToFetch();
AlignmentI geneFeatures = gffFetcher.getSequenceRecords(accId,
features);
- if (geneFeatures.getHeight() > 0)
+ if (geneFeatures != null && geneFeatures.getHeight() > 0)
{
genomicSequence = geneFeatures.getSequenceAt(0);
}
}
} catch (IOException e)
{
- System.err.println("Error transferring Ensembl features: "
- + e.getMessage());
+ System.err.println(
+ "Error transferring Ensembl features: " + e.getMessage());
}
}
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
SequenceI ds = proteinSeq.getDatasetSequence();
- ds.setSourceDBRef(proteinSeq.getSourceDBRef());
-
+ // TODO: Verify ensp primary ref is on proteinSeq.getDatasetSequence()
Mapping map = new Mapping(ds, mapList);
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<DBRefEntry> 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)
{
seq = seq.getDatasetSequence();
}
- EnsemblXref xrefFetcher = new EnsemblXref(getDomain());
+ EnsemblXref xrefFetcher = new EnsemblXref(getDomain(), getDbSource(),
+ getEnsemblDataVersion());
List<DBRefEntry> xrefs = xrefFetcher.getCrossReferences(seq.getName());
for (DBRefEntry xref : xrefs)
{
seq.addDBRef(xref);
- /*
- * Save any Uniprot xref to be the reference for SIFTS mapping
- */
- if (DBRefSource.UNIPROT.equals(xref.getSource()))
- {
- seq.setSourceDBRef(xref);
- }
}
/*
* and add a reference to itself
*/
- DBRefEntry self = new DBRefEntry(getDbSource(),
- getEnsemblDataVersion(), seq.getName());
+ DBRefEntry self = new DBRefEntry(getDbSource(), getEnsemblDataVersion(),
+ seq.getName());
seq.addDBRef(self);
}
* @throws JalviewException
* @throws IOException
*/
- protected AlignmentI fetchSequences(List<String> ids, AlignmentI alignment)
- throws JalviewException, IOException
+ protected AlignmentI fetchSequences(List<String> ids,
+ AlignmentI alignment) throws JalviewException, IOException
{
if (!isEnsemblAvailable())
{
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())
{
- System.out.println(String.format(
- "Warning when retrieving %d ids %s\n%s", ids.size(),
- ids.toString(), fr.getWarningMessage()));
+ System.out.println(
+ String.format("Warning when retrieving %d ids %s\n%s",
+ ids.size(), ids.toString(), fr.getWarningMessage()));
}
else if (fr.getSeqs().size() != ids.size())
{
System.out.println(String.format(
- "Only retrieved %d sequences for %d query strings", fr
- .getSeqs().size(), ids.size()));
+ "Only retrieved %d sequences for %d query strings",
+ fr.getSeqs().size(), ids.size()));
}
if (fr.getSeqs().size() == 1 && fr.getSeqs().get(0).getLength() == 0)
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)
{
if (ids.contains(name)
|| ids.contains(name.replace("ENSP", "ENST")))
{
- DBRefUtils.parseToDbRef(sq, getDbSource(),
+ DBRefEntry dbref = DBRefUtils.parseToDbRef(sq, getDbSource(),
getEnsemblDataVersion(), name);
+ sq.addDBRef(dbref);
}
}
if (alignment == null)
int mappedLength = 0;
int direction = 1; // forward
boolean directionSet = false;
-
+
for (SequenceFeature sf : sfs)
{
/*
if (directionSet && strand != direction)
{
// 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
- {
+ 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
+ {
regions.add(new int[] { sf.getBegin(), sf.getEnd() });
}
mappedLength += Math.abs(sf.getEnd() - sf.getBegin() + 1);
}
}
}
-
+
if (regions.isEmpty())
{
System.out.println("Failed to identify target sequence for " + accId
* a final sort is needed since Ensembl returns CDS sorted within source
* (havana / ensembl_havana)
*/
- Collections.sort(regions, new RangeSorter(direction == 1));
-
- List<int[]> to = Arrays.asList(new int[] { start,
- start + mappedLength - 1 });
-
+ Collections.sort(regions, new RangeComparator(direction == 1));
+
+ List<int[]> to = Arrays
+ .asList(new int[]
+ { start, start + mappedLength - 1 });
+
return new MapList(regions, to, 1, 1);
}
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);
/*
* for sequence_variant on reverse strand, have to convert the allele
* values to their complements
*/
- if (!forwardStrand
- && SequenceOntologyFactory.getInstance().isA(sf.getType(),
- SequenceOntologyI.SEQUENCE_VARIANT))
+ if (!forwardStrand && SequenceOntologyFactory.getInstance()
+ .isA(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT))
{
reverseComplementAlleles(copy);
}
// 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;
String type, String parentId)
{
List<SequenceFeature> result = new ArrayList<SequenceFeature>();
-
+
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);
git://source.jalview.org / jalview.git / blobdiff