-/**
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b1)
+ * Copyright (C) 2015 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.ws.dbsources;
-import java.io.File;
-import java.io.FileReader;
-import java.io.IOException;
-import java.util.Enumeration;
-import java.util.Hashtable;
-import java.util.Vector;
-
-import org.exolab.castor.xml.Unmarshaller;
-
-import com.stevesoft.pat.Regex;
-
-import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.datamodel.DBRefSource;
import jalview.datamodel.SequenceI;
import jalview.datamodel.UniprotEntry;
import jalview.datamodel.UniprotFile;
-import jalview.io.FormatAdapter;
-import jalview.io.IdentifyFile;
-import jalview.ws.DBRefFetcher;
import jalview.ws.ebi.EBIFetchClient;
import jalview.ws.seqfetcher.DbSourceProxy;
import jalview.ws.seqfetcher.DbSourceProxyImpl;
+import java.io.File;
+import java.io.FileReader;
+import java.io.Reader;
+import java.util.Vector;
+
+import org.exolab.castor.xml.Unmarshaller;
+
+import com.stevesoft.pat.Regex;
+
/**
* @author JimP
*
*/
public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy
{
- public Uniprot() {
+
+ private static final String BAR_DELIMITER = "|";
+
+ private static final String NEWLINE = "\n";
+
+ private static org.exolab.castor.mapping.Mapping map;
+
+ /**
+ * Constructor
+ */
+ public Uniprot()
+ {
super();
addDbSourceProperty(DBRefSource.SEQDB, DBRefSource.SEQDB);
addDbSourceProperty(DBRefSource.PROTSEQDB);
-// addDbSourceProperty(DBRefSource.MULTIACC, new Integer(50));
+ // addDbSourceProperty(DBRefSource.MULTIACC, new Integer(50));
}
/*
*/
public Regex getAccessionValidator()
{
- return null;
+ return new Regex("([A-Z]+[0-9]+[A-Z0-9]+|[A-Z0-9]+_[A-Z0-9]+)");
}
/*
return "0"; // we really don't know what version we're on.
}
- private EBIFetchClient ebi = null;
-
- public Vector getUniprotEntries(File file)
+ /**
+ * Reads a file containing the reply to the EBI Fetch Uniprot data query,
+ * unmarshals it to a UniprotFile object, and returns the list of UniprotEntry
+ * data models (mapped from <entry> elements)
+ *
+ * @param fileReader
+ * @return
+ */
+ public Vector<UniprotEntry> getUniprotEntries(Reader fileReader)
{
UniprotFile uni = new UniprotFile();
try
{
- // 1. Load the mapping information from the file
- org.exolab.castor.mapping.Mapping map = new org.exolab.castor.mapping.Mapping(uni.getClass().getClassLoader());
- java.net.URL url = getClass().getResource("/uniprot_mapping.xml");
- map.loadMapping(url);
+ if (map == null)
+ {
+ // 1. Load the mapping information from the file
+ map = new org.exolab.castor.mapping.Mapping(uni.getClass()
+ .getClassLoader());
+ java.net.URL url = getClass().getResource("/uniprot_mapping.xml");
+ map.loadMapping(url);
+ }
// 2. Unmarshal the data
Unmarshaller unmar = new Unmarshaller(uni);
unmar.setIgnoreExtraElements(true);
unmar.setMapping(map);
-
- uni = (UniprotFile) unmar.unmarshal(new FileReader(file));
- }
- catch (Exception e)
+ if (fileReader != null)
+ {
+ uni = (UniprotFile) unmar.unmarshal(fileReader);
+ }
+ } catch (Exception e)
{
System.out.println("Error getUniprotEntries() " + e);
}
startQuery();
try
{
- Alignment al=null;
- ebi = new EBIFetchClient();
- StringBuffer result=new StringBuffer();
+ queries = queries.toUpperCase().replaceAll(
+ "(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
+ AlignmentI al = null;
+ EBIFetchClient ebi = new EBIFetchClient();
// uniprotxml parameter required since december 2007
- File file = ebi.fetchDataAsFile("uniprot:" + queries, "uniprotxml", null);
- Vector entries = getUniprotEntries(file);
+ // uniprotkb dbname changed introduced december 2008
+ File file = ebi.fetchDataAsFile("uniprotkb:" + queries, "uniprotxml",
+ null);
+ Vector<UniprotEntry> entries = getUniprotEntries(new FileReader(file));
if (entries != null)
{
+ /*
+ * If Castor binding included sequence@length, we could guesstimate the
+ * size of buffer to hold the alignment
+ */
+ StringBuffer result = new StringBuffer(128);
// First, make the new sequences
- Enumeration en = entries.elements();
- while (en.hasMoreElements())
+ for (UniprotEntry entry : entries)
{
- UniprotEntry entry = (UniprotEntry) en.nextElement();
-
- StringBuffer name = new StringBuffer(">UniProt/Swiss-Prot");
- Enumeration en2 = entry.getAccession().elements();
- while (en2.hasMoreElements())
- {
- name.append("|");
- name.append(en2.nextElement());
- }
- en2 = entry.getName().elements();
- while (en2.hasMoreElements())
- {
- name.append("|");
- name.append(en2.nextElement());
- }
-
- if (entry.getProtein()!=null && entry.getProtein().getName()!=null)
- {
- for (int nm=0,nmSize=entry.getProtein().getName().size(); nm<nmSize;nm++)
- {
- name.append(" " + entry.getProtein().getName().elementAt(nm));
- }
- }
-
- result.append(name + "\n"
- + entry.getUniprotSequence().getContent() + "\n");
+ StringBuilder name = constructSequenceFastaHeader(entry);
+ result.append(name).append(NEWLINE)
+ .append(entry.getUniprotSequence().getContent())
+ .append(NEWLINE);
}
// Then read in the features and apply them to the dataset
al = parseResult(result.toString());
- if (al!=null)
+ if (al != null)
{
// Decorate the alignment with database entries.
addUniprotXrefs(al, entries);
- } else {
+ }
+ else
+ {
results = result;
}
}
} catch (Exception e)
{
stopQuery();
- throw(e);
+ throw (e);
}
}
/**
+ * Construct a Fasta-format sequence header by concatenating the source,
+ * accession id(s) and name(s), delimited by '|', plus any protein names, now
+ * with space rather than bar delimiter
+ *
+ * @param entry
+ * @return
+ */
+ public static StringBuilder constructSequenceFastaHeader(
+ 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);
+ name.append(n);
+ }
+
+ if (entry.getProtein() != null && entry.getProtein().getName() != null)
+ {
+ for (String nm : entry.getProtein().getName())
+ {
+ name.append(" ").append(nm);
+ }
+ }
+ return name;
+ }
+
+ /**
* add an ordered set of UniprotEntry objects to an ordered set of seuqences.
*
- * @param al -
- * a sequence of n sequences
+ * @param al
+ * - a sequence of n sequences
* @param entries
- * a seuqence of n uniprot entries to be analysed.
+ * a list of n uniprot entries to be analysed.
*/
- public void addUniprotXrefs(Alignment al, Vector entries)
+ public void addUniprotXrefs(AlignmentI al, Vector<UniprotEntry> entries)
{
+ final String dbVersion = getDbVersion();
+
for (int i = 0; i < entries.size(); i++)
{
- UniprotEntry entry = (UniprotEntry) entries.elementAt(i);
- Enumeration e = entry.getDbReference().elements();
- Vector onlyPdbEntries = new Vector();
- Vector dbxrefs = new Vector();
- while (e.hasMoreElements())
+ UniprotEntry entry = entries.elementAt(i);
+ Vector<PDBEntry> onlyPdbEntries = new Vector<PDBEntry>();
+ Vector<DBRefEntry> dbxrefs = new Vector<DBRefEntry>();
+
+ for (PDBEntry pdb : entry.getDbReference())
{
- PDBEntry pdb = (PDBEntry) e.nextElement();
DBRefEntry dbr = new DBRefEntry();
dbr.setSource(pdb.getType());
dbr.setAccessionId(pdb.getId());
- dbr.setVersion(DBRefSource.UNIPROT+":"+getDbVersion());
+ dbr.setVersion(DBRefSource.UNIPROT + ":" + dbVersion);
dbxrefs.addElement(dbr);
- if (!pdb.getType().equals("PDB"))
+ if ("PDB".equals(pdb.getType()))
{
- continue;
+ onlyPdbEntries.addElement(pdb);
}
-
- onlyPdbEntries.addElement(pdb);
}
+
SequenceI sq = al.getSequenceAt(i);
- while (sq.getDatasetSequence()!=null)
+ while (sq.getDatasetSequence() != null)
{
sq = sq.getDatasetSequence();
}
- Enumeration en2 = entry.getAccession().elements();
- while (en2.hasMoreElements())
+ for (String accessionId : entry.getAccession())
{
- // we always add as uniprot if we retrieved from uniprot or uniprot name
- sq.addDBRef(
- new DBRefEntry(DBRefSource.UNIPROT, getDbVersion(), en2.nextElement()
- .toString()));
+ /*
+ * add as uniprot whether retrieved from uniprot or uniprot_name
+ */
+ sq.addDBRef(new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
+ accessionId));
}
- en2 = dbxrefs.elements();
- while (en2.hasMoreElements())
+
+ for (DBRefEntry dbRef : dbxrefs)
{
- // we always add as uniprot if we retrieved from uniprot or uniprot name
- sq.addDBRef((DBRefEntry) en2.nextElement());
-
+ sq.addDBRef(dbRef);
}
sq.setPDBId(onlyPdbEntries);
if (entry.getFeature() != null)
{
- e = entry.getFeature().elements();
- while (e.hasMoreElements())
+ for (SequenceFeature sf : entry.getFeature())
{
- SequenceFeature sf = (SequenceFeature) e.nextElement();
sf.setFeatureGroup("Uniprot");
sq.addSequenceFeature(sf);
}
*/
public boolean isValidReference(String accession)
{
- return true;
+ // TODO: make the following a standard validator
+ return (accession == null || accession.length() < 2) ? false
+ : getAccessionValidator().search(accession);
}
+
/**
* return LDHA_CHICK uniprot entry
*/
{
return "P00340";
}
+
public String getDbName()
{
return "Uniprot"; // getDbSource();
}
+
+ @Override
+ public int getTier()
+ {
+ return 0;
+ }
}