*/
package jalview.ws.dbsources;
+import jalview.bin.Cache;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
-import jalview.datamodel.UniprotEntry;
-import jalview.datamodel.UniprotFile;
-import jalview.ws.ebi.EBIFetchClient;
+import jalview.datamodel.xdb.uniprot.UniprotEntry;
+import jalview.datamodel.xdb.uniprot.UniprotFeature;
+import jalview.datamodel.xdb.uniprot.UniprotFile;
+import jalview.schemes.ResidueProperties;
+import jalview.util.StringUtils;
import jalview.ws.seqfetcher.DbSourceProxyImpl;
-import java.io.File;
-import java.io.FileReader;
+import java.io.InputStream;
+import java.io.InputStreamReader;
import java.io.Reader;
import java.net.URL;
+import java.net.URLConnection;
import java.util.ArrayList;
+import java.util.List;
import java.util.Vector;
import org.exolab.castor.mapping.Mapping;
*/
public class Uniprot extends DbSourceProxyImpl
{
+ private static final String DEFAULT_UNIPROT_DOMAIN = "https://www.uniprot.org";
+
private static final String BAR_DELIMITER = "|";
/*
super();
}
+ private String getDomain()
+ {
+ return Cache.getDefault("UNIPROT_DOMAIN", DEFAULT_UNIPROT_DOMAIN);
+ }
+
/*
* (non-Javadoc)
*
queries = queries.toUpperCase().replaceAll(
"(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
AlignmentI al = null;
- EBIFetchClient ebi = new EBIFetchClient();
- // uniprotxml parameter required since december 2007
- // uniprotkb dbname changed introduced december 2008
- File file = ebi.fetchDataAsFile("uniprotkb:" + queries, "uniprotxml",
- null);
- Vector<UniprotEntry> entries = getUniprotEntries(new FileReader(file));
+
+ String downloadstring = getDomain() + "/uniprot/" + queries
+ + ".xml";
+ URL url = null;
+ URLConnection urlconn = null;
+
+ url = new URL(downloadstring);
+ urlconn = url.openConnection();
+ InputStream istr = urlconn.getInputStream();
+ Vector<UniprotEntry> entries = getUniprotEntries(
+ new InputStreamReader(istr, "UTF-8"));
if (entries != null)
{
- ArrayList<SequenceI> seqs = new ArrayList<SequenceI>();
+ ArrayList<SequenceI> seqs = new ArrayList<>();
for (UniprotEntry entry : entries)
{
seqs.add(uniprotEntryToSequenceI(entry));
return al;
} catch (Exception e)
{
- stopQuery();
throw (e);
+ } finally
+ {
+ stopQuery();
}
}
* UniprotEntry
* @return SequenceI instance created from the UniprotEntry instance
*/
- public SequenceI uniprotEntryToSequenceI(UniprotEntry entry){
+ public SequenceI uniprotEntryToSequenceI(UniprotEntry entry)
+ {
String id = getUniprotEntryId(entry);
- SequenceI sequence = new Sequence(id, entry.getUniprotSequence()
- .getContent());
+ SequenceI sequence = new Sequence(id,
+ entry.getUniprotSequence().getContent());
sequence.setDescription(getUniprotEntryDescription(entry));
final String dbVersion = getDbVersion();
- ArrayList<DBRefEntry> dbRefs = new ArrayList<DBRefEntry>();
+ ArrayList<DBRefEntry> dbRefs = new ArrayList<>();
for (String accessionId : entry.getAccession())
{
DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
accessionId);
+
+ // mark dbRef as a primary reference for this sequence
dbRefs.add(dbRef);
}
- sequence.setSourceDBRef((dbRefs != null && dbRefs.size() > 0) ? dbRefs
- .get(0) : null);
- Vector<PDBEntry> onlyPdbEntries = new Vector<PDBEntry>();
+ Vector<PDBEntry> onlyPdbEntries = new Vector<>();
for (PDBEntry pdb : entry.getDbReference())
{
DBRefEntry dbr = new DBRefEntry();
{
onlyPdbEntries.addElement(pdb);
}
+ if ("EMBL".equals(pdb.getType()))
+ {
+ // look for a CDS reference and add it, too.
+ String cdsId = (String) pdb.getProperty("protein sequence ID");
+ if (cdsId != null && cdsId.trim().length() > 0)
+ {
+ // remove version
+ String[] vrs = cdsId.split("\\.");
+ dbr = new DBRefEntry(DBRefSource.EMBLCDS, vrs.length > 1 ? vrs[1]
+ : DBRefSource.UNIPROT + ":" + dbVersion, vrs[0]);
+ dbRefs.add(dbr);
+ }
+ }
+ if ("Ensembl".equals(pdb.getType()))
+ {
+ /*UniprotXML
+ * <dbReference type="Ensembl" id="ENST00000321556">
+ * <molecule id="Q9BXM7-1"/>
+ * <property type="protein sequence ID" value="ENSP00000364204"/>
+ * <property type="gene ID" value="ENSG00000158828"/>
+ * </dbReference>
+ */
+ String cdsId = (String) pdb.getProperty("protein sequence ID");
+ if (cdsId != null && cdsId.trim().length() > 0)
+ {
+ dbr = new DBRefEntry(DBRefSource.ENSEMBL,
+ DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
+ dbRefs.add(dbr);
+
+ }
+ }
}
sequence.setPDBId(onlyPdbEntries);
if (entry.getFeature() != null)
{
- for (SequenceFeature sf : entry.getFeature())
+ for (UniprotFeature uf : entry.getFeature())
{
- sf.setFeatureGroup("Uniprot");
- sequence.addSequenceFeature(sf);
+ SequenceFeature copy = new SequenceFeature(uf.getType(),
+ getDescription(uf), uf.getBegin(), uf.getEnd(), "Uniprot");
+ copy.setStatus(uf.getStatus());
+ sequence.addSequenceFeature(copy);
}
}
- sequence.setDBRefs(dbRefs.toArray(new DBRefEntry[0]));
+ for (DBRefEntry dbr : dbRefs)
+ {
+ sequence.addDBRef(dbr);
+ }
return sequence;
}
/**
+ * Constructs a feature description from the description and (optionally)
+ * original and variant fields of the Uniprot XML feature
+ *
+ * @param uf
+ * @return
+ */
+ protected static String getDescription(UniprotFeature uf)
+ {
+ String orig = uf.getOriginal();
+ List<String> variants = uf.getVariation();
+ StringBuilder sb = new StringBuilder();
+
+ /*
+ * append variant in standard format if present
+ * e.g. p.Arg59Lys
+ * multiple variants are split over lines using <br>
+ */
+ boolean asHtml = false;
+ if (orig != null && !orig.isEmpty() && variants != null
+ && !variants.isEmpty())
+ {
+ int p = 0;
+ for (String var : variants)
+ {
+ // TODO proper HGVS nomenclature for delins structural variations
+ // http://varnomen.hgvs.org/recommendations/protein/variant/delins/
+ // for now we are pragmatic - any orig/variant sequence longer than
+ // three characters is shown with single-character notation rather than
+ // three-letter notation
+ sb.append("p.");
+ if (orig.length() < 4)
+ {
+ for (int c = 0, clen = orig.length(); c < clen; c++)
+ {
+ char origchar = orig.charAt(c);
+ String orig3 = ResidueProperties.aa2Triplet.get("" + origchar);
+ sb.append(orig3 == null ? origchar
+ : StringUtils.toSentenceCase(orig3));
+ }
+ }
+ else
+ {
+ sb.append(orig);
+ }
+
+ sb.append(Integer.toString(uf.getPosition()));
+
+ if (var.length() < 4)
+ {
+ for (int c = 0, clen = var.length(); c < clen; c++)
+ {
+ char varchar = var.charAt(c);
+ String var3 = ResidueProperties.aa2Triplet.get("" + varchar);
+
+ sb.append(var3 != null ? StringUtils.toSentenceCase(var3)
+ : "" + varchar);
+ }
+ }
+ else
+ {
+ sb.append(var);
+ }
+ if (++p != variants.size())
+ {
+ sb.append("<br/> ");
+ asHtml = true;
+ }
+ else
+ {
+ sb.append(" ");
+ }
+ }
+ }
+ String description = uf.getDescription();
+ if (description != null)
+ {
+ sb.append(description);
+ }
+ if (asHtml)
+ {
+ sb.insert(0, "<html>");
+ sb.append("</html>");
+ }
+
+ return sb.toString();
+ }
+
+ /**
*
* @param entry
* UniportEntry
StringBuilder desc = new StringBuilder(32);
if (entry.getProtein() != null && entry.getProtein().getName() != null)
{
+ boolean first = true;
for (String nm : entry.getProtein().getName())
{
- desc.append(nm).append(" ");
+ if (!first)
+ {
+ desc.append(" ");
+ }
+ first = false;
+ desc.append(nm);
}
}
return desc.toString();
/**
*
* @param entry
- * UniportEntry
+ * UniprotEntry
* @return The accession id(s) and name(s) delimited by '|'.
*/
public static String getUniprotEntryId(UniprotEntry entry)
{
StringBuilder name = new StringBuilder(32);
- name.append("UniProt/Swiss-Prot");
- for (String accessionId : entry.getAccession())
- {
- name.append(BAR_DELIMITER);
- name.append(accessionId);
- }
for (String n : entry.getName())
{
- name.append(BAR_DELIMITER);
+ if (name.length() > 0)
+ {
+ name.append(BAR_DELIMITER);
+ }
name.append(n);
}
return name.toString();
git://source.jalview.org / jalview.git / blobdiff