X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblLookup.java;h=e55605d92effa83d313b57fd886a1d4818b34d3d;hb=948bd3bcbacc509da0cefaae3eedd97300a6ccce;hp=0ddef2b999ef57de300f6c4f511414086bf61a66;hpb=a2703f9c2948fba9747b304fed02b7bbc5d32b37;p=jalview.git diff --git a/src/jalview/ext/ensembl/EnsemblLookup.java b/src/jalview/ext/ensembl/EnsemblLookup.java index 0ddef2b..e55605d 100644 --- a/src/jalview/ext/ensembl/EnsemblLookup.java +++ b/src/jalview/ext/ensembl/EnsemblLookup.java @@ -20,13 +20,17 @@ */ 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; @@ -34,14 +38,15 @@ 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. + * 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"; private static final String OBJECT_TYPE_TRANSLATION = "Translation"; private static final String PARENT = "Parent"; private static final String OBJECT_TYPE_TRANSCRIPT = "Transcript"; @@ -136,27 +141,49 @@ public class EnsemblLookup extends EnsemblRestClient } /** - * 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 */ public String getGeneId(String identifier) { - return getGeneId(identifier, null); + return parseGeneId(getResult(identifier, null)); } /** - * Calls the Ensembl lookup REST endpoint and retrieves the 'Parent' for the + * 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 */ - public String getGeneId(String identifier, String objectType) + protected JSONObject getResult(String identifier, String objectType) { List ids = Arrays.asList(new String[] { identifier }); @@ -179,10 +206,11 @@ public class EnsemblLookup extends EnsemblRestClient { br = getHttpResponse(url, ids); } - return br == null ? null : parseResponse(br); - } catch (IOException e) + return br == null ? null : (JSONObject) (new JSONParser().parse(br)); + } catch (IOException | ParseException e) { - // ignore + System.err.println("Error parsing " + identifier + " lookup response " + + e.getMessage()); return null; } finally { @@ -203,41 +231,119 @@ public class EnsemblLookup extends EnsemblRestClient * 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. + * Parent is the transcript identifier, so we redo the search with this value, + * specifying that object_type should be Transcript. * - * @param br + * @param jsonObject * @return - * @throws IOException */ - protected String parseResponse(BufferedReader br) throws IOException + protected String parseGeneId(JSONObject json) { + if (json == null) + { + // e.g. lookup failed with 404 not found + return null; + } + String geneId = null; - JSONParser jp = new JSONParser(); + String type = json.get(OBJECT_TYPE).toString(); + if (OBJECT_TYPE_GENE.equalsIgnoreCase(type)) + { + // got the gene - just returns its id + geneId = json.get(JSON_ID).toString(); + } + else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type)) + { + // got the transcript - return its (Gene) Parent + geneId = json.get(PARENT).toString(); + } + else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type)) + { + // got the protein - look up its Parent, restricted to type Transcript + String transcriptId = json.get(PARENT).toString(); + geneId = parseGeneId(getResult(transcriptId, OBJECT_TYPE_TRANSCRIPT)); + } + + return geneId; + } + + /** + * 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 { - JSONObject val = (JSONObject) jp.parse(br); - 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)) + 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 fromRange = Collections.singletonList(new int[] { 1, + fromEnd }); + List toRange = Collections.singletonList(new int[] { toStart, + toEnd }); + final MapList map = new MapList(fromRange, toRange, 1, 1); + return new GeneLociI() { - // 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) + + @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) { - // ignore + Cache.log.error("Error looking up gene loci: " + e.getMessage()); + e.printStackTrace(); } - return geneId; + return null; } }