X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fdbsources%2FUniprot.java;h=c9beb8e2ae7b9690532e6c5a67c3ea437324bdc3;hb=d914a47dd53f43cdfd27152e6b19415a937e9a3d;hp=359f2b15c2cd3dbfc2db46c6d27ff7da6f7aec29;hpb=47168f025aefdaa044802bd5f8f510ffe43a4808;p=jalview.git diff --git a/src/jalview/ws/dbsources/Uniprot.java b/src/jalview/ws/dbsources/Uniprot.java index 359f2b1..c9beb8e 100644 --- a/src/jalview/ws/dbsources/Uniprot.java +++ b/src/jalview/ws/dbsources/Uniprot.java @@ -1,6 +1,6 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2) - * Copyright (C) 2014 The Jalview Authors + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ The Jalview Authors * * This file is part of Jalview. * @@ -20,40 +20,51 @@ */ package jalview.ws.dbsources; -import java.io.File; -import java.io.FileReader; -import java.util.Enumeration; -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.PDBEntry; +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.ws.seqfetcher.DbSourceProxy; +import jalview.datamodel.xdb.uniprot.UniprotEntry; +import jalview.datamodel.xdb.uniprot.UniprotFeature; +import jalview.datamodel.xdb.uniprot.UniprotFile; import jalview.ws.seqfetcher.DbSourceProxyImpl; +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.Vector; + +import org.exolab.castor.mapping.Mapping; +import org.exolab.castor.xml.Unmarshaller; + +import com.stevesoft.pat.Regex; + /** * @author JimP * */ -public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy +public class Uniprot extends DbSourceProxyImpl { + private static final String BAR_DELIMITER = "|"; + + /* + * Castor mapping loaded from uniprot_mapping.xml + */ + private static Mapping map; + + /** + * Constructor + */ public Uniprot() { super(); - addDbSourceProperty(DBRefSource.SEQDB, DBRefSource.SEQDB); - addDbSourceProperty(DBRefSource.PROTSEQDB); - // addDbSourceProperty(DBRefSource.MULTIACC, new Integer(50)); } /* @@ -61,9 +72,10 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#getAccessionSeparator() */ + @Override public String getAccessionSeparator() { - return null; // ";"; + return null; } /* @@ -71,6 +83,7 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#getAccessionValidator() */ + @Override public Regex getAccessionValidator() { return new Regex("([A-Z]+[0-9]+[A-Z0-9]+|[A-Z0-9]+_[A-Z0-9]+)"); @@ -81,6 +94,7 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#getDbSource() */ + @Override public String getDbSource() { return DBRefSource.UNIPROT; @@ -91,16 +105,21 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#getDbVersion() */ + @Override public String getDbVersion() { return "0"; // we really don't know what version we're on. } - private EBIFetchClient ebi = null; - - private static org.exolab.castor.mapping.Mapping map; - - 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 getUniprotEntries(Reader fileReader) { UniprotFile uni = new UniprotFile(); try @@ -108,9 +127,8 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy 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 = new Mapping(uni.getClass().getClassLoader()); + URL url = getClass().getResource("/uniprot_mapping.xml"); map.loadMapping(url); } @@ -118,9 +136,9 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy Unmarshaller unmar = new Unmarshaller(uni); unmar.setIgnoreExtraElements(true); unmar.setMapping(map); - if (file != null) + if (fileReader != null) { - uni = (UniprotFile) unmar.unmarshal(new FileReader(file)); + uni = (UniprotFile) unmar.unmarshal(fileReader); } } catch (Exception e) { @@ -135,6 +153,7 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[]) */ + @Override public AlignmentI getSequenceRecords(String queries) throws Exception { startQuery(); @@ -142,135 +161,175 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy { queries = queries.toUpperCase().replaceAll( "(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", ""); - Alignment al = null; - ebi = new EBIFetchClient(); - StringBuffer result = new StringBuffer(); - // uniprotxml parameter required since december 2007 - // uniprotkb dbname changed introduced december 2008 - File file = ebi.fetchDataAsFile("uniprotkb:" + queries, "uniprotxml", - null); - Vector entries = getUniprotEntries(file); + AlignmentI al = null; + + String downloadstring = "http://www.uniprot.org/uniprot/" + queries + + ".xml"; + URL url = null; + URLConnection urlconn = null; + + url = new URL(downloadstring); + urlconn = url.openConnection(); + InputStream istr = urlconn.getInputStream(); + Vector entries = getUniprotEntries( + new InputStreamReader(istr, "UTF-8")); if (entries != null) { - // First, make the new sequences - Enumeration en = entries.elements(); - while (en.hasMoreElements()) + ArrayList seqs = new ArrayList<>(); + 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"); - + seqs.add(uniprotEntryToSequenceI(entry)); } + al = new Alignment(seqs.toArray(new SequenceI[0])); - // Then read in the features and apply them to the dataset - al = parseResult(result.toString()); - if (al != null) - { - // Decorate the alignment with database entries. - addUniprotXrefs(al, entries); - } - else - { - results = result; - } } stopQuery(); return al; } catch (Exception e) { - stopQuery(); throw (e); + } finally + { + stopQuery(); } } /** - * add an ordered set of UniprotEntry objects to an ordered set of seuqences. * - * @param al - * - a sequence of n sequences - * @param entries - * a seuqence of n uniprot entries to be analysed. + * @param entry + * UniprotEntry + * @return SequenceI instance created from the UniprotEntry instance */ - public void addUniprotXrefs(Alignment al, Vector entries) + public SequenceI uniprotEntryToSequenceI(UniprotEntry entry) { - for (int i = 0; i < entries.size(); i++) + String id = getUniprotEntryId(entry); + SequenceI sequence = new Sequence(id, + entry.getUniprotSequence().getContent()); + sequence.setDescription(getUniprotEntryDescription(entry)); + + final String dbVersion = getDbVersion(); + ArrayList 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); + } + + Vector onlyPdbEntries = new Vector<>(); + for (PDBEntry pdb : entry.getDbReference()) { - UniprotEntry entry = (UniprotEntry) entries.elementAt(i); - Enumeration e = entry.getDbReference().elements(); - Vector onlyPdbEntries = new Vector(); - Vector dbxrefs = new Vector(); - while (e.hasMoreElements()) + DBRefEntry dbr = new DBRefEntry(); + dbr.setSource(pdb.getType()); + dbr.setAccessionId(pdb.getId()); + dbr.setVersion(DBRefSource.UNIPROT + ":" + dbVersion); + dbRefs.add(dbr); + if ("PDB".equals(pdb.getType())) { - PDBEntry pdb = (PDBEntry) e.nextElement(); - DBRefEntry dbr = new DBRefEntry(); - dbr.setSource(pdb.getType()); - dbr.setAccessionId(pdb.getId()); - dbr.setVersion(DBRefSource.UNIPROT + ":" + getDbVersion()); - dbxrefs.addElement(dbr); - if (!pdb.getType().equals("PDB")) + 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) { - continue; + // remove version + String[] vrs = cdsId.split("\\."); + dbr = new DBRefEntry(DBRefSource.EMBLCDS, vrs.length > 1 ? vrs[1] + : DBRefSource.UNIPROT + ":" + dbVersion, vrs[0]); + dbRefs.add(dbr); } - - onlyPdbEntries.addElement(pdb); } - SequenceI sq = al.getSequenceAt(i); - while (sq.getDatasetSequence() != null) + if ("Ensembl".equals(pdb.getType())) { - sq = sq.getDatasetSequence(); + /*UniprotXML + * + * + * + * + * + */ + 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); + + } } + } - Enumeration en2 = entry.getAccession().elements(); - while (en2.hasMoreElements()) + sequence.setPDBId(onlyPdbEntries); + if (entry.getFeature() != null) + { + for (UniprotFeature uf : entry.getFeature()) { - // we always add as uniprot if we retrieved from uniprot or uniprot name - sq.addDBRef(new DBRefEntry(DBRefSource.UNIPROT, getDbVersion(), en2 - .nextElement().toString())); + SequenceFeature copy = new SequenceFeature(uf.getType(), + uf.getDescription(), uf.getBegin(), uf.getEnd(), "Uniprot"); + copy.setStatus(uf.getStatus()); + sequence.addSequenceFeature(copy); } - en2 = dbxrefs.elements(); - while (en2.hasMoreElements()) - { - // we always add as uniprot if we retrieved from uniprot or uniprot name - sq.addDBRef((DBRefEntry) en2.nextElement()); + } + for (DBRefEntry dbr : dbRefs) + { + sequence.addDBRef(dbr); + } + return sequence; + } - } - sq.setPDBId(onlyPdbEntries); - if (entry.getFeature() != null) + /** + * + * @param entry + * UniportEntry + * @return protein name(s) delimited by a white space character + */ + public static String getUniprotEntryDescription(UniprotEntry entry) + { + StringBuilder desc = new StringBuilder(32); + if (entry.getProtein() != null && entry.getProtein().getName() != null) + { + boolean first = true; + for (String nm : entry.getProtein().getName()) { - e = entry.getFeature().elements(); - while (e.hasMoreElements()) + if (!first) { - SequenceFeature sf = (SequenceFeature) e.nextElement(); - sf.setFeatureGroup("Uniprot"); - sq.addSequenceFeature(sf); + desc.append(" "); } + first = false; + desc.append(nm); } } + return desc.toString(); + } + + /** + * + * @param entry + * UniportEntry + * @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"); + // use 'canonicalised' name for optimal id matching + name.append(DBRefSource.UNIPROT); + for (String accessionId : entry.getAccession()) + { + name.append(BAR_DELIMITER); + name.append(accessionId); + } + for (String n : entry.getName()) + { + name.append(BAR_DELIMITER); + name.append(n); + } + return name.toString(); } /* @@ -278,6 +337,7 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy * * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String) */ + @Override public boolean isValidReference(String accession) { // TODO: make the following a standard validator @@ -288,11 +348,13 @@ public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy /** * return LDHA_CHICK uniprot entry */ + @Override public String getTestQuery() { return "P00340"; } + @Override public String getDbName() { return "Uniprot"; // getDbSource();