*/
package jalview.ws.dbsources;
+import java.io.InputStream;
+import java.net.HttpURLConnection;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Locale;
+import java.util.Vector;
+
+import javax.xml.bind.JAXBContext;
+import javax.xml.bind.JAXBElement;
+import javax.xml.bind.JAXBException;
+import javax.xml.stream.FactoryConfigurationError;
+import javax.xml.stream.XMLInputFactory;
+import javax.xml.stream.XMLStreamException;
+import javax.xml.stream.XMLStreamReader;
+
+import com.stevesoft.pat.Regex;
+
import jalview.bin.Cache;
+import jalview.bin.Console;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.xml.binding.uniprot.PositionType;
import jalview.xml.binding.uniprot.PropertyType;
-import java.io.InputStream;
-import java.net.URL;
-import java.net.URLConnection;
-import java.util.ArrayList;
-import java.util.List;
-import java.util.Vector;
-
-import javax.xml.bind.JAXBContext;
-import javax.xml.bind.JAXBException;
-import javax.xml.stream.FactoryConfigurationError;
-import javax.xml.stream.XMLInputFactory;
-import javax.xml.stream.XMLStreamException;
-import javax.xml.stream.XMLStreamReader;
-
-import com.stevesoft.pat.Regex;
-
/**
* This class queries the Uniprot database for sequence data, unmarshals the
* returned XML, and converts it to Jalview Sequence records (including attached
startQuery();
try
{
- queries = queries.toUpperCase().replaceAll(
+ queries = queries.toUpperCase(Locale.ROOT).replaceAll(
"(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
AlignmentI al = null;
- String downloadstring = getDomain() + "/uniprot/" + queries
- + ".xml";
+ String downloadstring = getDomain() + "/uniprot/" + queries + ".xml";
URL url = new URL(downloadstring);
- URLConnection urlconn = url.openConnection();
- InputStream istr = urlconn.getInputStream();
- List<Entry> entries = getUniprotEntries(istr);
- if (entries != null)
+ HttpURLConnection urlconn = (HttpURLConnection) url.openConnection();
+ // anything other than 200 means we don't have data
+ // TODO: JAL-3882 reuse the EnsemblRestClient's fair
+ // use/backoff logic to retry when the server tells us to go away
+ if (urlconn.getResponseCode() == 200)
{
- List<SequenceI> seqs = new ArrayList<>();
- for (Entry entry : entries)
+ InputStream istr = urlconn.getInputStream();
+ List<Entry> entries = getUniprotEntries(istr);
+ if (entries != null)
{
- seqs.add(uniprotEntryToSequence(entry));
+ List<SequenceI> seqs = new ArrayList<>();
+ for (Entry entry : entries)
+ {
+ seqs.add(uniprotEntryToSequence(entry));
+ }
+ al = new Alignment(seqs.toArray(new SequenceI[seqs.size()]));
}
- al = new Alignment(seqs.toArray(new SequenceI[seqs.size()]));
}
-
stopQuery();
return al;
+
} catch (Exception e)
{
throw (e);
String seqString = entry.getSequence().getValue().replaceAll("\\s*",
"");
- SequenceI sequence = new Sequence(id,
- seqString);
+ SequenceI sequence = new Sequence(id, seqString);
sequence.setDescription(getUniprotEntryDescription(entry));
-
+ final String uniprotRecordVersion = "" + entry.getVersion();
/*
* add a 'self' DBRefEntry for each accession
*/
final String dbVersion = getDbVersion();
List<DBRefEntry> dbRefs = new ArrayList<>();
+ boolean canonical = true;
for (String accessionId : entry.getAccession())
{
- DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
- accessionId);
+ DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT,
+ uniprotRecordVersion, accessionId, null, canonical);
+ canonical = false;
dbRefs.add(dbRef);
}
// remove version
String[] vrs = cdsId.split("\\.");
String version = vrs.length > 1 ? vrs[1]
- : DBRefSource.UNIPROT + ":" + dbVersion;
+ : DBRefSource.UNIPROT + ":" + uniprotRecordVersion;
dbr = new DBRefEntry(DBRefSource.EMBLCDS, version, vrs[0]);
+ // TODO: process VARIANT features to allow EMBLCDS record's product to
+ // match Uniprot
+ dbr.setCanonical(true);
dbRefs.add(dbr);
}
}
- if ("Ensembl".equals(type))
+ if (type != null
+ && type.toLowerCase(Locale.ROOT).startsWith("ensembl"))
{
+ // remove version
+ String[] vrs = dbref.getId().split("\\.");
+ String version = vrs.length > 1 ? vrs[1]
+ : DBRefSource.UNIPROT + ":" + uniprotRecordVersion;
+ dbr.setAccessionId(vrs[0]);
+ dbr.setVersion(version);
/*
* e.g. Uniprot accession Q9BXM7 has
* <dbReference type="Ensembl" id="ENST00000321556">
"protein sequence ID");
if (cdsId != null && cdsId.trim().length() > 0)
{
+ // remove version
+ String[] cdsVrs = cdsId.split("\\.");
+ String cdsVersion = cdsVrs.length > 1 ? cdsVrs[1]
+ : DBRefSource.UNIPROT + ":" + uniprotRecordVersion;
dbr = new DBRefEntry(DBRefSource.ENSEMBL,
- DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
+ DBRefSource.UNIPROT + ":" + cdsVersion, cdsVrs[0]);
dbRefs.add(dbr);
}
}
LocationType location = uf.getLocation();
int start = 0;
int end = 0;
+ String uncertain_start = null, uncertain_end = null,
+ uncertain_pos = null;
if (location.getPosition() != null)
{
- start = location.getPosition().getPosition().intValue();
- end = start;
+ if (location.getPosition().getPosition() == null
+ || !"unknown".equals(location.getPosition().getStatus()))
+ {
+ Console.warn(
+ "Ignoring single position feature with uncertain location "
+ + uf.getType() + ":" + getDescription(uf));
+ uncertain_pos = location.getPosition().getStatus() == null
+ ? "unknown"
+ : location.getPosition().getStatus();
+ }
+ else
+ {
+ start = location.getPosition().getPosition().intValue();
+ end = start;
+ }
}
else
{
- start = location.getBegin().getPosition().intValue();
- end = location.getEnd().getPosition().intValue();
+ if (location.getBegin().getPosition() == null)
+ {
+ Console.warn(
+ "Setting start position of feature with uncertain start to 1: "
+ + uf.getType() + ":" + getDescription(uf));
+ start = sequence.getStart();
+ uncertain_start = location.getBegin().getStatus();
+ }
+ else
+ {
+ start = location.getBegin().getPosition().intValue();
+ }
+ if (location.getEnd().getPosition() == null)
+ {
+ Console.warn(
+ "Setting start position of feature with uncertain start to 1: "
+ + uf.getType() + ":" + getDescription(uf));
+ end = sequence.getEnd();
+ uncertain_end = location.getEnd().getStatus();
+ }
+ else
+ {
+ end = location.getEnd().getPosition().intValue();
+ }
}
SequenceFeature sf = new SequenceFeature(uf.getType(),
getDescription(uf), start, end, "Uniprot");
sf.setStatus(uf.getStatus());
+ if (uncertain_end != null)
+ {
+ sf.setValue("end_status", uncertain_end);
+ }
+ if (uncertain_start != null)
+ {
+ sf.setValue("start_status", uncertain_start);
+ }
+ if (uncertain_pos != null)
+ {
+ sf.setValue("pos_status", uncertain_pos);
+ }
sequence.addSequenceFeature(sf);
}
}
XMLStreamReader streamReader = XMLInputFactory.newInstance()
.createXMLStreamReader(is);
javax.xml.bind.Unmarshaller um = jc.createUnmarshaller();
- jalview.xml.binding.uniprot.Uniprot uniprot = (jalview.xml.binding.uniprot.Uniprot) um.unmarshal(streamReader);
+ JAXBElement<jalview.xml.binding.uniprot.Uniprot> uniprotElement = um
+ .unmarshal(streamReader,
+ jalview.xml.binding.uniprot.Uniprot.class);
+ jalview.xml.binding.uniprot.Uniprot uniprot = uniprotElement
+ .getValue();
+
if (uniprot != null && !uniprot.getEntry().isEmpty())
{
entries = uniprot.getEntry();
} catch (JAXBException | XMLStreamException
| FactoryConfigurationError e)
{
+ if (e instanceof javax.xml.bind.UnmarshalException
+ && e.getCause() != null
+ && e.getCause() instanceof XMLStreamException
+ && e.getCause().getMessage().contains("[row,col]:[1,1]"))
+ {
+ // trying to parse an empty stream
+ return null;
+ }
e.printStackTrace();
}
return entries;