/*
* 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.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.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;
import org.exolab.castor.xml.Unmarshaller;
import com.stevesoft.pat.Regex;
/**
* @author JimP
*
*/
public class Uniprot extends DbSourceProxyImpl
{
private static final String DEFAULT_UNIPROT_DOMAIN = "https://www.uniprot.org";
private static final String BAR_DELIMITER = "|";
/*
* Castor mapping loaded from uniprot_mapping.xml
*/
private static Mapping map;
/**
* 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.
}
/**
* 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;
String downloadstring = getDomain() + "/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)
{
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)
{
throw (e);
} finally
{
stopQuery();
}
}
/**
*
* @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);
// mark dbRef as a primary reference for this sequence
dbRefs.add(dbRef);
}
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);
}
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
*
*
*
*
*
*/
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 (UniprotFeature uf : entry.getFeature())
{
SequenceFeature copy = new SequenceFeature(uf.getType(),
getDescription(uf), uf.getBegin(), uf.getEnd(), "Uniprot");
copy.setStatus(uf.getStatus());
sequence.addSequenceFeature(copy);
}
}
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 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
*/
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("
");
asHtml = true;
}
else
{
sb.append(" ");
}
}
}
String description = uf.getDescription();
if (description != null)
{
sb.append(description);
}
if (asHtml)
{
sb.insert(0, "");
sb.append("");
}
return sb.toString();
}
/**
*
* @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
* UniprotEntry
* @return The accession id(s) and name(s) delimited by '|'.
*/
public static String getUniprotEntryId(UniprotEntry 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;
}
}