X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fdbsources%2FUniprot.java;h=17f1842af68e78de06c2f132520ea8fb28872df0;hb=86e1bfc3ed99bee91069b3238eb291c3955338d3;hp=8e7893fe2907a3cbc7305f771b3b3cc5d0726bf1;hpb=5c7ef5c5b65be30aebbc132324cef8e9e5b783c6;p=jalview.git
diff --git a/src/jalview/ws/dbsources/Uniprot.java b/src/jalview/ws/dbsources/Uniprot.java
index 8e7893f..17f1842 100644
--- a/src/jalview/ws/dbsources/Uniprot.java
+++ b/src/jalview/ws/dbsources/Uniprot.java
@@ -1,254 +1,323 @@
-/**
- *
- */
-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.PDBEntry;
-import jalview.datamodel.SequenceFeature;
-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;
-
-/**
- * @author JimP
- *
- */
-public class Uniprot extends DbSourceProxyImpl implements DbSourceProxy
-{
- public Uniprot() {
- super();
- addDbSourceProperty(DBRefSource.SEQDB, DBRefSource.SEQDB);
- addDbSourceProperty(DBRefSource.PROTSEQDB);
-// addDbSourceProperty(DBRefSource.MULTIACC, new Integer(50));
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
- */
- public String getAccessionSeparator()
- {
- return null; // ";";
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#getAccessionValidator()
- */
- public Regex getAccessionValidator()
- {
- return null;
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#getDbSource()
- */
- public String getDbSource()
- {
- return DBRefSource.UNIPROT;
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#getDbVersion()
- */
- public String getDbVersion()
- {
- return "0"; // we really don't know what version we're on.
- }
-
- private EBIFetchClient ebi = null;
-
- public Vector getUniprotEntries(File file)
- {
- 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);
-
- // 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)
- {
- System.out.println("Error getUniprotEntries() " + e);
- }
-
- return uni.getUniprotEntries();
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
- */
- public AlignmentI getSequenceRecords(String queries) throws Exception
- {
- startQuery();
- try
- {
- Alignment al=null;
- ebi = new EBIFetchClient();
- StringBuffer result=new StringBuffer();
- // uniprotxml parameter required since december 2007
- File file = ebi.fetchDataAsFile("uniprot:" + queries, "uniprotxml", null);
- Vector entries = getUniprotEntries(file);
-
- if (entries != null)
- {
- // First, make the new sequences
- Enumeration en = entries.elements();
- while (en.hasMoreElements())
- {
- 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)
- {
- name.append(" " + entry.getProtein().getName().elementAt(0));
- }
-
- result.append(name + "\n"
- + entry.getUniprotSequence().getContent() + "\n");
-
- }
-
- // 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);
- }
- }
-
- /**
- * 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.
- */
- public void addUniprotXrefs(Alignment al, Vector entries)
- {
- for (int i = 0; i < entries.size(); i++)
- {
- UniprotEntry entry = (UniprotEntry) entries.elementAt(i);
- Enumeration e = entry.getDbReference().elements();
- Vector onlyPdbEntries = new Vector();
- while (e.hasMoreElements())
- {
- PDBEntry pdb = (PDBEntry) e.nextElement();
- if (!pdb.getType().equals("PDB"))
- {
- continue;
- }
-
- onlyPdbEntries.addElement(pdb);
- }
- SequenceI sq = al.getSequenceAt(i);
- while (sq.getDatasetSequence()!=null)
- {
- sq = sq.getDatasetSequence();
- }
-
- Enumeration en2 = entry.getAccession().elements();
- while (en2.hasMoreElements())
- {
- // we always add as uniprot if we retrieved from uniprot or uniprot name
- sq.addDBRef(
- new DBRefEntry(DBRefSource.UNIPROT, getDbVersion(), en2.nextElement()
- .toString()));
- }
- sq.setPDBId(onlyPdbEntries);
- if (entry.getFeature() != null)
- {
- e = entry.getFeature().elements();
- while (e.hasMoreElements())
- {
- SequenceFeature sf = (SequenceFeature) e.nextElement();
- sf.setFeatureGroup("Uniprot");
- sq.addSequenceFeature(sf);
- }
- }
- }
- }
-
- /*
- * (non-Javadoc)
- *
- * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
- */
- public boolean isValidReference(String accession)
- {
- return true;
- }
- /**
- * return LDHA_CHICK uniprot entry
- */
- public String getTestQuery()
- {
- return "P00340";
- }
- public String getDbName()
- {
- return getDbSource();
- }
-}
+/*
+ * 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 .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.ws.dbsources;
+
+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.DbSourceProxyImpl;
+
+import java.io.File;
+import java.io.FileReader;
+import java.io.Reader;
+import java.net.URL;
+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
+{
+ private static final String BAR_DELIMITER = "|";
+
+ /*
+ * Castor mapping loaded from uniprot_mapping.xml
+ */
+ private static Mapping map;
+
+ /**
+ * Constructor
+ */
+ public Uniprot()
+ {
+ super();
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
+ */
+ @Override
+ public String getAccessionSeparator()
+ {
+ return null;
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @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]+)");
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see jalview.ws.DbSourceProxy#getDbSource()
+ */
+ @Override
+ public String getDbSource()
+ {
+ return DBRefSource.UNIPROT;
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see jalview.ws.DbSourceProxy#getDbVersion()
+ */
+ @Override
+ public String getDbVersion()
+ {
+ return "0"; // we really don't know what version we're on.
+ }
+
+ /**
+ * 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
+ {
+ if (map == null)
+ {
+ // 1. Load the mapping information from the file
+ map = new Mapping(uni.getClass().getClassLoader());
+ 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);
+ if (fileReader != null)
+ {
+ uni = (UniprotFile) unmar.unmarshal(fileReader);
+ }
+ } catch (Exception e)
+ {
+ System.out.println("Error getUniprotEntries() " + e);
+ }
+
+ return uni.getUniprotEntries();
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
+ */
+ @Override
+ public AlignmentI getSequenceRecords(String queries) throws Exception
+ {
+ startQuery();
+ try
+ {
+ 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, ".xml");
+ Vector entries = getUniprotEntries(new FileReader(file));
+
+ if (entries != null)
+ {
+ ArrayList seqs = new ArrayList();
+ for (UniprotEntry entry : entries)
+ {
+ seqs.add(uniprotEntryToSequenceI(entry));
+ }
+ al = new Alignment(seqs.toArray(new SequenceI[0]));
+
+ }
+ stopQuery();
+ return al;
+ } catch (Exception e)
+ {
+ stopQuery();
+ throw (e);
+ }
+ }
+
+ /**
+ *
+ * @param entry
+ * UniprotEntry
+ * @return SequenceI instance created from the UniprotEntry instance
+ */
+ public SequenceI uniprotEntryToSequenceI(UniprotEntry entry){
+ 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);
+ dbRefs.add(dbRef);
+ }
+ sequence.setSourceDBRef((dbRefs != null && dbRefs.size() > 0) ? dbRefs
+ .get(0) : null);
+
+ Vector onlyPdbEntries = new Vector();
+ for (PDBEntry pdb : entry.getDbReference())
+ {
+ 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()))
+ {
+ onlyPdbEntries.addElement(pdb);
+ }
+ }
+
+ sequence.setPDBId(onlyPdbEntries);
+ if (entry.getFeature() != null)
+ {
+ for (SequenceFeature sf : entry.getFeature())
+ {
+ sf.setFeatureGroup("Uniprot");
+ sequence.addSequenceFeature(sf);
+ }
+ }
+ sequence.setDBRefs(dbRefs.toArray(new DBRefEntry[0]));
+ return sequence;
+ }
+
+ /**
+ *
+ * @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())
+ {
+ if (!first)
+ {
+ 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();
+ }
+
+ /*
+ * (non-Javadoc)
+ *
+ * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
+ */
+ @Override
+ public boolean isValidReference(String accession)
+ {
+ // TODO: make the following a standard validator
+ return (accession == null || accession.length() < 2) ? false
+ : getAccessionValidator().search(accession);
+ }
+
+ /**
+ * return LDHA_CHICK uniprot entry
+ */
+ @Override
+ public String getTestQuery()
+ {
+ return "P00340";
+ }
+
+ @Override
+ public String getDbName()
+ {
+ return "Uniprot"; // getDbSource();
+ }
+
+ @Override
+ public int getTier()
+ {
+ return 0;
+ }
+}