X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fdbsources%2FUniprot.java;h=d97bf692168c93a8e770b8e77bdce563e69a977a;hb=bc18effe68ba80213a6d03ca7e6175adc6be71d6;hp=a889ac922a7ccca154e44dff499bae18b1338ea6;hpb=08fbe7c3d40a4077ab519334952a079968c07cd1;p=jalview.git
diff --git a/src/jalview/ws/dbsources/Uniprot.java b/src/jalview/ws/dbsources/Uniprot.java
index a889ac9..d97bf69 100644
--- a/src/jalview/ws/dbsources/Uniprot.java
+++ b/src/jalview/ws/dbsources/Uniprot.java
@@ -1,253 +1,516 @@
-/**
- *
- */
-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 ";";
- }
-
- /*
- * (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();
- 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.bin.Cache;
+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.schemes.ResidueProperties;
+import jalview.util.StringUtils;
+import jalview.ws.seqfetcher.DbSourceProxyImpl;
+import jalview.xml.binding.uniprot.DbReferenceType;
+import jalview.xml.binding.uniprot.Entry;
+import jalview.xml.binding.uniprot.FeatureType;
+import jalview.xml.binding.uniprot.LocationType;
+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
+ * database references and sequence features)
+ *
+ * @author JimP
+ *
+ */
+public class Uniprot extends DbSourceProxyImpl
+{
+ private static final String DEFAULT_UNIPROT_DOMAIN = "https://www.uniprot.org";
+
+ private static final String BAR_DELIMITER = "|";
+
+ /**
+ * Constructor
+ */
+ public Uniprot()
+ {
+ super();
+ }
+
+ private String getDomain()
+ {
+ return Cache.getDefault("UNIPROT_DOMAIN", DEFAULT_UNIPROT_DOMAIN);
+ }
+
+ /*
+ * (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.
+ }
+
+ /*
+ * (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;
+
+ String downloadstring = getDomain() + "/uniprot/" + queries
+ + ".xml";
+
+ URL url = new URL(downloadstring);
+ URLConnection urlconn = url.openConnection();
+ InputStream istr = urlconn.getInputStream();
+ List entries = getUniprotEntries(istr);
+ if (entries != null)
+ {
+ List seqs = new ArrayList<>();
+ for (Entry entry : entries)
+ {
+ seqs.add(uniprotEntryToSequence(entry));
+ }
+ al = new Alignment(seqs.toArray(new SequenceI[seqs.size()]));
+ }
+
+ stopQuery();
+ return al;
+ } catch (Exception e)
+ {
+ throw (e);
+ } finally
+ {
+ stopQuery();
+ }
+ }
+
+ /**
+ * Converts an Entry object (bound from Uniprot XML) to a Jalview Sequence
+ *
+ * @param entry
+ * @return
+ */
+ SequenceI uniprotEntryToSequence(Entry entry)
+ {
+ String id = getUniprotEntryId(entry);
+ /*
+ * Sequence should not include any whitespace, but JAXB leaves these in
+ */
+ String seqString = entry.getSequence().getValue().replaceAll("\\s*",
+ "");
+
+ SequenceI sequence = new Sequence(id,
+ seqString);
+ sequence.setDescription(getUniprotEntryDescription(entry));
+
+ /*
+ * add a 'self' DBRefEntry for each accession
+ */
+ final String dbVersion = getDbVersion();
+ List dbRefs = new ArrayList<>();
+ for (String accessionId : entry.getAccession())
+ {
+ DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
+ accessionId);
+ dbRefs.add(dbRef);
+ }
+
+ /*
+ * add a DBRefEntry for each dbReference element in the XML;
+ * also add a PDBEntry if type="PDB";
+ * also add an EMBLCDS dbref if protein sequence id is given
+ * also add an Ensembl dbref " " " " " "
+ */
+ Vector pdbRefs = new Vector<>();
+ for (DbReferenceType dbref : entry.getDbReference())
+ {
+ String type = dbref.getType();
+ DBRefEntry dbr = new DBRefEntry(type,
+ DBRefSource.UNIPROT + ":" + dbVersion, dbref.getId());
+ dbRefs.add(dbr);
+ if ("PDB".equals(type))
+ {
+ pdbRefs.add(new PDBEntry(dbr));
+ }
+ if ("EMBL".equals(type))
+ {
+ /*
+ * e.g. Uniprot accession Q9BXM7 has
+ *
+ *
+ *
+ *
+ */
+ String cdsId = getProperty(dbref.getProperty(),
+ "protein sequence ID");
+ if (cdsId != null && cdsId.trim().length() > 0)
+ {
+ // remove version
+ String[] vrs = cdsId.split("\\.");
+ String version = vrs.length > 1 ? vrs[1]
+ : DBRefSource.UNIPROT + ":" + dbVersion;
+ dbr = new DBRefEntry(DBRefSource.EMBLCDS, version, vrs[0]);
+ dbRefs.add(dbr);
+ }
+ }
+ if ("Ensembl".equals(type))
+ {
+ /*
+ * e.g. Uniprot accession Q9BXM7 has
+ *
+ *
+ *
+ *
+ *
+ */
+ String cdsId = getProperty(dbref.getProperty(),
+ "protein sequence ID");
+ if (cdsId != null && cdsId.trim().length() > 0)
+ {
+ dbr = new DBRefEntry(DBRefSource.ENSEMBL,
+ DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
+ dbRefs.add(dbr);
+ }
+ }
+ }
+
+ /*
+ * create features; they have either begin and end, or position, in XML
+ */
+ sequence.setPDBId(pdbRefs);
+ if (entry.getFeature() != null)
+ {
+ for (FeatureType uf : entry.getFeature())
+ {
+ LocationType location = uf.getLocation();
+ int start = 0;
+ int end = 0;
+ if (location.getPosition() != null)
+ {
+ start = location.getPosition().getPosition().intValue();
+ end = start;
+ }
+ else
+ {
+ start = location.getBegin().getPosition().intValue();
+ end = location.getEnd().getPosition().intValue();
+ }
+ SequenceFeature sf = new SequenceFeature(uf.getType(),
+ getDescription(uf), start, end, "Uniprot");
+ sf.setStatus(uf.getStatus());
+ sequence.addSequenceFeature(sf);
+ }
+ }
+ for (DBRefEntry dbr : dbRefs)
+ {
+ sequence.addDBRef(dbr);
+ }
+ return sequence;
+ }
+
+ /**
+ * A helper method that builds a sequence feature description
+ *
+ * @param feature
+ * @return
+ */
+ static String getDescription(FeatureType feature)
+ {
+ String orig = feature.getOriginal();
+ List variants = feature.getVariation();
+ StringBuilder sb = new StringBuilder();
+
+ /*
+ * append variant in standard format if present
+ * e.g. p.Arg59Lys
+ * multiple variants are split over lines using
+ */
+ 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);
+ }
+
+ LocationType location = feature.getLocation();
+ PositionType start = location.getPosition() == null
+ ? location.getBegin()
+ : location.getPosition();
+ sb.append(Integer.toString(start.getPosition().intValue()));
+
+ 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("
");
+ asHtml = true;
+ }
+ else
+ {
+ sb.append(" ");
+ }
+ }
+ }
+ String description = feature.getDescription();
+ if (description != null)
+ {
+ sb.append(description);
+ }
+ if (asHtml)
+ {
+ sb.insert(0, "");
+ sb.append("");
+ }
+
+ return sb.toString();
+ }
+
+ /**
+ * A helper method that searches the list of properties for one with the given
+ * key, and if found returns the property value, else returns null
+ *
+ * @param properties
+ * @param key
+ * @return
+ */
+ static String getProperty(List properties, String key)
+ {
+ String value = null;
+ if (properties != null)
+ {
+ for (PropertyType prop : properties)
+ {
+ if (key.equals(prop.getType()))
+ {
+ value = prop.getValue();
+ break;
+ }
+ }
+ }
+ return value;
+ }
+
+ /**
+ * Extracts xml element entry/protein/recommendedName/fullName
+ *
+ * @param entry
+ * @return
+ */
+ static String getUniprotEntryDescription(Entry entry)
+ {
+ String desc = "";
+ if (entry.getProtein() != null
+ && entry.getProtein().getRecommendedName() != null)
+ {
+ // fullName is mandatory if recommendedName is present
+ desc = entry.getProtein().getRecommendedName().getFullName()
+ .getValue();
+ }
+ return desc;
+ }
+
+ /**
+ * Constructs a sequence id by concatenating all entry/name elements with '|'
+ * separator
+ *
+ * @param entry
+ * @return
+ */
+ static String getUniprotEntryId(Entry entry)
+ {
+ StringBuilder name = new StringBuilder(32);
+ for (String n : entry.getName())
+ {
+ if (name.length() > 0)
+ {
+ 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;
+ }
+
+ /**
+ * Reads the reply to the EBI Fetch Uniprot data query, unmarshals it to an
+ * Uniprot object, and returns the enclosed Entry objects, or null on any
+ * failure
+ *
+ * @param is
+ * @return
+ */
+ public List getUniprotEntries(InputStream is)
+ {
+ List entries = null;
+ try
+ {
+ JAXBContext jc = JAXBContext
+ .newInstance("jalview.xml.binding.uniprot");
+ 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);
+ if (uniprot != null && !uniprot.getEntry().isEmpty())
+ {
+ entries = uniprot.getEntry();
+ }
+ } catch (JAXBException | XMLStreamException
+ | FactoryConfigurationError e)
+ {
+ e.printStackTrace();
+ }
+ return entries;
+ }
+}