+/*
+ * 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 <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
import jalview.datamodel.AlignmentI;
import org.json.simple.parser.JSONParser;
import org.json.simple.parser.ParseException;
+/**
+ * A client for the Ensembl lookup REST endpoint, used to find the gene
+ * identifier given a gene, transcript or protein identifier.
+ *
+ * @author gmcarstairs
+ */
public class EnsemblLookup extends EnsemblRestClient
{
+ private static final String OBJECT_TYPE_TRANSLATION = "Translation";
+ private static final String PARENT = "Parent";
+ private static final String OBJECT_TYPE_TRANSCRIPT = "Transcript";
+ private static final String ID = "id";
+ private static final String OBJECT_TYPE_GENE = "Gene";
+ private static final String OBJECT_TYPE = "object_type";
+
+ /**
+ * keep track of last identifier retrieved to break loops
+ */
+ private String lastId;
+
+ /**
+ * Default constructor (to use rest.ensembl.org)
+ */
+ public EnsemblLookup()
+ {
+ super();
+ }
+
+ /**
+ * Constructor given the target domain to fetch data from
+ *
+ * @param
+ */
+ public EnsemblLookup(String d)
+ {
+ super(d);
+ }
+
@Override
public String getDbName()
{
protected URL getUrl(List<String> ids) throws MalformedURLException
{
String identifier = ids.get(0);
- return getUrl(identifier);
+ return getUrl(identifier, null);
}
/**
+ * Gets the url for lookup of the given identifier, optionally with objectType
+ * also specified in the request
+ *
* @param identifier
+ * @param objectType
* @return
*/
- protected URL getUrl(String identifier)
+ protected URL getUrl(String identifier, String objectType)
{
- String url = ENSEMBL_REST + "/lookup/id/" + identifier
- + "?content-type=application/json";
+ String url = getDomain() + "/lookup/id/" + identifier
+ + CONTENT_TYPE_JSON;
+ if (objectType != null)
+ {
+ url += "&" + OBJECT_TYPE + "=" + objectType;
+ }
+
try
{
return new URL(url);
}
/**
+ * Returns the gene id related to the given identifier, which may be for a
+ * gene, transcript or protein
+ *
+ * @param identifier
+ * @return
+ */
+ public String getGeneId(String identifier)
+ {
+ return getGeneId(identifier, null);
+ }
+
+ /**
* Calls the Ensembl lookup REST endpoint and retrieves the 'Parent' for the
* given identifier, or null if not found
*
* @param identifier
+ * @param objectType
+ * (optional)
* @return
*/
- public String getParent(String identifier)
+ public String getGeneId(String identifier, String objectType)
{
List<String> ids = Arrays.asList(new String[] { identifier });
-
+
BufferedReader br = null;
try
{
- URL url = getUrl(identifier);
+
+ URL url = getUrl(identifier, objectType);
+
+ if (identifier.equals(lastId))
+ {
+ System.err.println("** Ensembl lookup " + url.toString()
+ + " looping on Parent!");
+ return null;
+ }
+
+ lastId = identifier;
+
if (url != null)
{
br = getHttpResponse(url, ids);
}
- return (parseResponse(br));
+ return br == null ? null : parseResponse(br);
} catch (IOException e)
{
// ignore
}
/**
- * Parses "Parent" from the JSON response and returns the value, or null if
- * not found
+ * Parses the JSON response and returns the gene identifier, or null if not
+ * found. If the returned object_type is Gene, returns the id, if Transcript
+ * returns the Parent. If it is Translation (peptide identifier), then the
+ * Parent is the transcript identifier, so we redo the search with this value.
*
* @param br
* @return
*/
protected String parseResponse(BufferedReader br) throws IOException
{
- String parent = null;
+ String geneId = null;
JSONParser jp = new JSONParser();
try
{
JSONObject val = (JSONObject) jp.parse(br);
- parent = val.get("Parent").toString();
+ String type = val.get(OBJECT_TYPE).toString();
+ if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
+ {
+ // got the gene - just returns its id
+ geneId = val.get(ID).toString();
+ }
+ else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
+ {
+ // got the transcript - return its (Gene) Parent
+ geneId = val.get(PARENT).toString();
+ }
+ else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
+ {
+ // got the protein - get its Parent, restricted to type Transcript
+ String transcriptId = val.get(PARENT).toString();
+ geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
+ }
} catch (ParseException e)
{
// ignore
}
- return parent;
+ return geneId;
}
}
git://source.jalview.org / jalview.git / blobdiff