*/
package jalview.ext.ensembl;
+import jalview.bin.Cache;
import jalview.datamodel.AlignmentI;
+import jalview.datamodel.GeneLociI;
+import jalview.util.MapList;
import java.io.BufferedReader;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.Arrays;
+import java.util.Collections;
import java.util.List;
import org.json.simple.JSONObject;
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.
+ * A client for the Ensembl /lookup REST endpoint, used to find the gene
+ * identifier given a gene, transcript or protein identifier, or to extract the
+ * species or chromosomal coordinates from the same service response
*
* @author gmcarstairs
*/
public class EnsemblLookup extends EnsemblRestClient
{
+ private static final String SPECIES = "species";
+
/**
* Default constructor (to use rest.ensembl.org)
*/
}
/**
- * Returns the gene id related to the given identifier, which may be for a
- * gene, transcript or protein
+ * Returns the gene id related to the given identifier (which may be for a
+ * gene, transcript or protein)
*
* @param identifier
* @return
if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
{
// got the gene - just returns its id
- geneId = val.get(ID).toString();
+ geneId = val.get(JSON_ID).toString();
}
else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
{
return geneId;
}
+ /**
+ * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
+ * given identifier, or null if not found
+ *
+ * @param identifier
+ * @return
+ */
+ public String getSpecies(String identifier)
+ {
+ String species = null;
+ JSONObject json = getResult(identifier, null);
+ if (json != null)
+ {
+ Object o = json.get(SPECIES);
+ if (o != null)
+ {
+ species = o.toString();
+ }
+ }
+ return species;
+ }
+
+ /**
+ * Calls the /lookup/id rest service and returns the response as a JSONObject,
+ * or null if any error
+ *
+ * @param identifier
+ * @param objectType
+ * (optional)
+ * @return
+ */
+ protected JSONObject getResult(String identifier, String objectType)
+ {
+ List<String> ids = Arrays.asList(new String[] { identifier });
+
+ BufferedReader br = null;
+ try
+ {
+ URL url = getUrl(identifier, objectType);
+
+ if (url != null)
+ {
+ br = getHttpResponse(url, ids);
+ }
+ return br == null ? null : (JSONObject) (new JSONParser().parse(br));
+ } catch (IOException | ParseException e)
+ {
+ System.err.println("Error parsing " + identifier + " lookup response "
+ + e.getMessage());
+ return null;
+ } finally
+ {
+ if (br != null)
+ {
+ try
+ {
+ br.close();
+ } catch (IOException e)
+ {
+ // ignore
+ }
+ }
+ }
+ }
+
+ /**
+ * Calls the /lookup/id rest service for the given id, and if successful,
+ * parses and returns the gene's chromosomal coordinates
+ *
+ * @param geneId
+ * @return
+ */
+ public GeneLociI getGeneLoci(String geneId)
+ {
+ return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
+ }
+
+ /**
+ * Parses the /lookup/id response for species, asssembly_name,
+ * seq_region_name, start, end and returns an object that wraps them, or null
+ * if unsuccessful
+ *
+ * @param json
+ * @return
+ */
+ GeneLociI parseGeneLoci(JSONObject json)
+ {
+ if (json == null)
+ {
+ return null;
+ }
+
+ try
+ {
+ final String species = json.get("species").toString();
+ final String assembly = json.get("assembly_name").toString();
+ final String chromosome = json.get("seq_region_name").toString();
+ String strand = json.get("strand").toString();
+ int start = Integer.parseInt(json.get("start").toString());
+ int end = Integer.parseInt(json.get("end").toString());
+ int fromEnd = end - start + 1;
+ boolean reverseStrand = "-1".equals(strand);
+ int toStart = reverseStrand ? end : start;
+ int toEnd = reverseStrand ? start : end;
+ List<int[]> fromRange = Collections.singletonList(new int[] { 1,
+ fromEnd });
+ List<int[]> toRange = Collections.singletonList(new int[] { toStart,
+ toEnd });
+ final MapList map = new MapList(fromRange, toRange, 1, 1);
+ return new GeneLociI()
+ {
+
+ @Override
+ public String getSpeciesId()
+ {
+ return species == null ? "" : species;
+ }
+
+ @Override
+ public String getAssemblyId()
+ {
+ return assembly;
+ }
+
+ @Override
+ public String getChromosomeId()
+ {
+ return chromosome;
+ }
+
+ @Override
+ public MapList getMap()
+ {
+ return map;
+ }
+ };
+ } catch (NullPointerException | NumberFormatException e)
+ {
+ Cache.log.error("Error looking up gene loci: " + e.getMessage());
+ e.printStackTrace();
+ }
+ return null;
+ }
+
}