<classpathentry kind="lib" path="lib/VARNAv3-93.jar"/>
<classpathentry kind="lib" path="lib/jfreesvg-2.1.jar"/>
<classpathentry kind="lib" path="lib/quaqua-filechooser-only-8.0.jar"/>
- <classpathentry kind="lib" path="lib/htsjdk-1.133.jar"/>
<classpathentry kind="con" path="org.eclipse.jdt.USER_LIBRARY/plugin"/>
<classpathentry kind="lib" path="lib/xml-apis.jar"/>
<classpathentry kind="con" path="org.eclipse.jdt.junit.JUNIT_CONTAINER/4"/>
- <classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/>
<classpathentry kind="con" path="org.eclipse.jdt.USER_LIBRARY/Plugin.jar"/>
<classpathentry kind="lib" path="lib/jersey-client-1.19.jar"/>
<classpathentry kind="lib" path="lib/jersey-core-1.19.jar"/>
<classpathentry kind="lib" path="lib/biojava-core-4.1.0.jar"/>
<classpathentry kind="lib" path="lib/biojava-ontology-4.1.0.jar"/>
<classpathentry kind="lib" path="lib/groovy-all-2.4.6-indy.jar"/>
+ <classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/JavaSE-1.8"/>
+ <classpathentry kind="lib" path="lib/htsjdk-2.12.0.jar"/>
<classpathentry kind="output" path="classes"/>
</classpath>
eclipse.preferences.version=1
org.eclipse.jdt.core.compiler.codegen.inlineJsrBytecode=enabled
org.eclipse.jdt.core.compiler.codegen.methodParameters=do not generate
-org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.7
+org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.8
org.eclipse.jdt.core.compiler.codegen.unusedLocal=preserve
-org.eclipse.jdt.core.compiler.compliance=1.7
+org.eclipse.jdt.core.compiler.compliance=1.8
org.eclipse.jdt.core.compiler.debug.lineNumber=generate
org.eclipse.jdt.core.compiler.debug.localVariable=generate
org.eclipse.jdt.core.compiler.debug.sourceFile=generate
org.eclipse.jdt.core.compiler.problem.assertIdentifier=error
org.eclipse.jdt.core.compiler.problem.enumIdentifier=error
-org.eclipse.jdt.core.compiler.source=1.7
+org.eclipse.jdt.core.compiler.source=1.8
org.eclipse.jdt.core.formatter.align_type_members_on_columns=false
org.eclipse.jdt.core.formatter.alignment_for_arguments_in_allocation_expression=16
org.eclipse.jdt.core.formatter.alignment_for_arguments_in_annotation=52
jalview.release=releases/Release_2_10_2b1_Branch
-jalview.version=2.10.2b1
+jalview.version=2.10.2b2
<offline_allowed />
</information>
<resources>
- <j2se version="9+" />
+ <j2se version="1.7+" />
<jar main="true" href="jalview.jar"/>
<fileset dir="${packageDir}">
<exclude name="jalview.jar" />
</presetdef>
<jnlpf toFile="${jnlpFile}" />
- <!-- add a j2se entry for java 9 -->
+ <!-- add the add-modules j2se attribute for java 9 -->
<replace file="${jnlpFile}" value="j2se version="1.7+" initial-heap-size="${inih}" max-heap-size="${maxh}" java-vm-args="--add-modules=java.se.ee"">
- <replacetoken>j2se version="1.9+"</replacetoken>
+ <replacetoken>j2se version="1.7+"</replacetoken>
</replace>
</target>
rendering of sequence features
</li>
</ul>
- </div></td>
+ </td>
<td><div align="left">
<em></em>
<ul>
<li><!-- JAL-2728 -->Protein annotation panel too high in CDS/Protein view
+ </li>
+ </ul>
+ </td>
+ </tr>
+ <tr>
+ <td width="60" nowrap>
+ <div align="center">
+ <strong><a name="Jalview.2.10.2b2">2.10.2b2</a><br />
+ <em>2/10/2017</em></strong>
+ </div>
+ </td>
+ <td><div align="left">
+ <em>New features in Jalview Desktop</em>
+ <ul>
+ <li>
+ <!-- JAL-2748 -->Uniprot Sequence Fetcher now uses web API at uniprot.org
+ </li>
+ <li> <!-- JAL-2745 -->HTTPS used for all connections to ebi.ac.uk
</li>
</ul>
</div></td>
+ <td><div align="left">
+ </div></td>
</tr>
<tr>
<td width="60" nowrap>
*/
int index = -1;
- private SequenceFeatures sequenceFeatureStore;
+ private SequenceFeaturesI sequenceFeatureStore;
/*
* A cursor holding the approximate current view position to the sequence,
*/
public int replace(char c1, char c2);
+ /**
+ * Answers the GeneLociI, or null if not known
+ *
+ * @return
+ */
GeneLociI getGeneLoci();
+ /**
+ * Sets the mapping to gene loci for the sequence
+ *
+ * @param speciesId
+ * @param assemblyId
+ * @param chromosomeId
+ * @param map
+ */
void setGeneLoci(String speciesId, String assemblyId,
String chromosomeId, MapList map);
}
--- /dev/null
+/*
+ * 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;
+
+/**
+ * A data class to model the data and rest version of one Ensembl domain,
+ * currently for rest.ensembl.org and rest.ensemblgenomes.org
+ *
+ * @author gmcarstairs
+ */
+class EnsemblData
+{
+ /*
+ * The http domain this object is holding data values for
+ */
+ String domain;
+
+ /*
+ * The latest version Jalview has tested for, e.g. "4.5"; a minor version change should be
+ * ok, a major version change may break stuff
+ */
+ String expectedRestVersion;
+
+ /*
+ * Major / minor / point version e.g. "4.5.1"
+ * @see http://rest.ensembl.org/info/rest/?content-type=application/json
+ */
+ String restVersion;
+
+ /*
+ * data version
+ * @see http://rest.ensembl.org/info/data/?content-type=application/json
+ */
+ String dataVersion;
+
+ /*
+ * true when http://rest.ensembl.org/info/ping/?content-type=application/json
+ * returns response code 200 and not {"error":"Database is unavailable"}
+ */
+ boolean restAvailable;
+
+ /*
+ * absolute time when availability was last checked
+ */
+ long lastAvailableCheckTime;
+
+ /*
+ * absolute time when version numbers were last checked
+ */
+ long lastVersionCheckTime;
+
+ // flag set to true if REST major version is not the one expected
+ boolean restMajorVersionMismatch;
+
+ /*
+ * absolute time to wait till if we overloaded the REST service
+ */
+ long retryAfter;
+
+ /**
+ * Constructor given expected REST version number e.g 4.5 or 3.4.3
+ *
+ * @param restExpected
+ */
+ EnsemblData(String theDomain, String restExpected)
+ {
+ domain = theDomain;
+ expectedRestVersion = restExpected;
+ lastAvailableCheckTime = -1;
+ lastVersionCheckTime = -1;
+ }
+
+}
-/*
- * 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;
-/**
- * A data class to model the data and rest version of one Ensembl domain,
- * currently for rest.ensembl.org and rest.ensemblgenomes.org
- *
- * @author gmcarstairs
- */
-class EnsemblInfo
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.DBRefSource;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+import org.json.simple.JSONArray;
+import org.json.simple.parser.JSONParser;
+import org.json.simple.parser.ParseException;
+
+public class EnsemblInfo extends EnsemblRestClient
{
- /*
- * The http domain this object is holding data values for
- */
- String domain;
/*
- * The latest version Jalview has tested for, e.g. "4.5"; a minor version change should be
- * ok, a major version change may break stuff
+ * cached results of REST /info/divisions service, currently
+ * <pre>
+ * {
+ * { "ENSEMBLFUNGI", "http://rest.ensemblgenomes.org"},
+ * "ENSEMBLBACTERIA", "http://rest.ensemblgenomes.org"},
+ * "ENSEMBLPROTISTS", "http://rest.ensemblgenomes.org"},
+ * "ENSEMBLMETAZOA", "http://rest.ensemblgenomes.org"},
+ * "ENSEMBLPLANTS", "http://rest.ensemblgenomes.org"},
+ * "ENSEMBL", "http://rest.ensembl.org" }
+ * }
+ * </pre>
+ * The values for EnsemblGenomes are retrieved by a REST call, that for
+ * Ensembl is added programmatically for convenience of lookup
*/
- String expectedRestVersion;
+ private static Map<String, String> divisions;
- /*
- * Major / minor / point version e.g. "4.5.1"
- * @see http://rest.ensembl.org/info/rest/?content-type=application/json
- */
- String restVersion;
+ @Override
+ public String getDbName()
+ {
+ return "ENSEMBL";
+ }
- /*
- * data version
- * @see http://rest.ensembl.org/info/data/?content-type=application/json
- */
- String dataVersion;
+ @Override
+ public AlignmentI getSequenceRecords(String queries) throws Exception
+ {
+ return null;
+ }
- /*
- * true when http://rest.ensembl.org/info/ping/?content-type=application/json
- * returns response code 200 and not {"error":"Database is unavailable"}
- */
- boolean restAvailable;
+ @Override
+ protected URL getUrl(List<String> ids) throws MalformedURLException
+ {
+ return null;
+ }
- /*
- * absolute time when availability was last checked
+ @Override
+ protected boolean useGetRequest()
+ {
+ return true;
+ }
+
+ @Override
+ protected String getRequestMimeType(boolean multipleIds)
+ {
+ return "application/json";
+ }
+
+ @Override
+ protected String getResponseMimeType()
+ {
+ return "application/json";
+ }
+
+ /**
+ * Answers the domain (http://rest.ensembl.org or
+ * http://rest.ensemblgenomes.org) for the given division, or null if not
+ * recognised by Ensembl.
+ *
+ * @param division
+ * @return
*/
- long lastAvailableCheckTime;
+ public String getDomain(String division)
+ {
+ if (divisions == null)
+ {
+ fetchDivisions();
+ }
+ return divisions.get(division.toUpperCase());
+ }
- /*
- * absolute time when version numbers were last checked
+ /**
+ * On first request only, populate the lookup map by fetching the list of
+ * divisions known to EnsemblGenomes.
*/
- long lastVersionCheckTime;
+ void fetchDivisions()
+ {
+ divisions = new HashMap<>();
- // flag set to true if REST major version is not the one expected
- boolean restMajorVersionMismatch;
+ /*
+ * for convenience, pre-fill ensembl.org as the domain for "ENSEMBL"
+ */
+ divisions.put(DBRefSource.ENSEMBL.toUpperCase(), ENSEMBL_REST);
- /*
- * absolute time to wait till if we overloaded the REST service
+ BufferedReader br = null;
+ try
+ {
+ URL url = getDivisionsUrl(ENSEMBL_GENOMES_REST);
+ if (url != null)
+ {
+ br = getHttpResponse(url, null);
+ }
+ parseResponse(br, ENSEMBL_GENOMES_REST);
+ } catch (IOException e)
+ {
+ // ignore
+ } finally
+ {
+ if (br != null)
+ {
+ try
+ {
+ br.close();
+ } catch (IOException e)
+ {
+ // ignore
+ }
+ }
+ }
+ }
+
+ /**
+ * Parses the JSON response to /info/divisions, and add each to the lookup map
+ *
+ * @param br
+ * @param domain
*/
- long retryAfter;
+ void parseResponse(BufferedReader br, String domain)
+ {
+ JSONParser jp = new JSONParser();
+
+ try
+ {
+ JSONArray parsed = (JSONArray) jp.parse(br);
+
+ Iterator rvals = parsed.iterator();
+ while (rvals.hasNext())
+ {
+ String division = rvals.next().toString();
+ divisions.put(division.toUpperCase(), domain);
+ }
+ } catch (IOException | ParseException | NumberFormatException e)
+ {
+ // ignore
+ }
+ }
/**
- * Constructor given expected REST version number e.g 4.5 or 3.4.3
+ * Constructs the URL for the EnsemblGenomes /info/divisions REST service
+ * @param domain TODO
*
- * @param restExpected
+ * @return
+ * @throws MalformedURLException
*/
- EnsemblInfo(String theDomain, String restExpected)
+ URL getDivisionsUrl(String domain) throws MalformedURLException
{
- domain = theDomain;
- expectedRestVersion = restExpected;
- lastAvailableCheckTime = -1;
- lastVersionCheckTime = -1;
+ return new URL(domain
+ + "/info/divisions?content-type=application/json");
}
+ /**
+ * Returns the set of 'divisions' recognised by Ensembl or EnsemblGenomes
+ *
+ * @return
+ */
+ public Set<String> getDivisions() {
+ if (divisions == null)
+ {
+ fetchDivisions();
+ }
+
+ return divisions.keySet();
+ }
}
*/
public class EnsemblLookup extends EnsemblRestClient
{
+ private static final String SPECIES = "species";
+
+ private static final String PARENT = "Parent";
/**
* Default constructor (to use rest.ensembl.org)
*/
public String getParent(String identifier)
{
+ return getAttribute(identifier, PARENT);
+ }
+
+ /**
+ * 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)
+ {
+ return getAttribute(identifier, SPECIES);
+ }
+
+ /**
+ * @param identifier
+ * @param attribute
+ * @return
+ */
+ protected String getAttribute(String identifier, String attribute)
+ {
List<String> ids = Arrays.asList(new String[] { identifier });
BufferedReader br = null;
{
br = getHttpResponse(url, ids);
}
- return (parseResponse(br));
+ return (parseResponse(br, attribute));
} catch (IOException e)
{
// ignore
}
/**
- * Parses "Parent" from the JSON response and returns the value, or null if
- * not found
+ * Parses the value of 'attribute' from the JSON response and returns the
+ * value, or null if not found
*
* @param br
+ * @param attribute
* @return
* @throws IOException
*/
- protected String parseResponse(BufferedReader br) throws IOException
+ protected String parseResponse(BufferedReader br, String attribute) throws IOException
{
String parent = null;
JSONParser jp = new JSONParser();
try
{
JSONObject val = (JSONObject) jp.parse(br);
- parent = val.get("Parent").toString();
- } catch (ParseException e)
+ parent = val.get(attribute).toString();
+ } catch (ParseException | NullPointerException e)
{
// ignore
}
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefSource;
+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.ArrayList;
+import java.util.Collections;
import java.util.Iterator;
import java.util.List;
public class EnsemblMap extends EnsemblRestClient
{
+ private static final String MAPPED = "mapped";
+
+ private static final String MAPPINGS = "mappings";
+
+ private static final String CDS = "cds";
+
+ private static final String CDNA = "cdna";
/**
* Default constructor (to use rest.ensembl.org)
* @return
* @throws MalformedURLException
*/
- protected URL getUrl(String species, String chromosome, String fromRef,
+ protected URL getAssemblyMapUrl(String species, String chromosome, String fromRef,
String toRef, int startPos, int endPos)
throws MalformedURLException
{
"%s/map/%s/%s/%s:%d..%d:%s/%s?content-type=application/json",
getDomain(), species, fromRef, chromosome, start, end, strand,
toRef);
- try
- {
- return new URL(url);
- } catch (MalformedURLException e)
- {
- return null;
- }
+ return new URL(url);
}
@Override
return null; // not used
}
- public int[] getMapping(String species, String chromosome,
+ /**
+ * Calls the REST /map service to get the chromosomal coordinates (start/end)
+ * in 'toRef' that corresponding to the (start/end) queryRange in 'fromRef'
+ *
+ * @param species
+ * @param chromosome
+ * @param fromRef
+ * @param toRef
+ * @param queryRange
+ * @return
+ * @see http://rest.ensemblgenomes.org/documentation/info/assembly_map
+ */
+ public int[] getAssemblyMapping(String species, String chromosome,
String fromRef, String toRef, int[] queryRange)
{
URL url = null;
try
{
- url = getUrl(species, chromosome, fromRef, toRef, queryRange[0],
+ url = getAssemblyMapUrl(species, chromosome, fromRef, toRef, queryRange[0],
queryRange[1]);
- // System.out.println("Calling " + url);
br = getHttpResponse(url, null);
- return (parseResponse(br));
+ return (parseAssemblyMappingResponse(br));
} catch (Throwable t)
{
System.out.println("Error calling " + url + ": " + t.getMessage());
return null;
+ } finally
+ {
+ if (br != null)
+ {
+ try
+ {
+ br.close();
+ } catch (IOException e)
+ {
+ // ignore
+ }
+ }
}
}
/**
- * Parses the JSON response from the /map REST service. The format is (with
- * some fields omitted)
+ * Parses the JSON response from the /map/<species>/ REST service. The
+ * format is (with some fields omitted)
*
* <pre>
* {"mappings":
* @param br
* @return
*/
- protected int[] parseResponse(BufferedReader br)
+ protected int[] parseAssemblyMappingResponse(BufferedReader br)
{
int[] result = null;
JSONParser jp = new JSONParser();
try
{
JSONObject parsed = (JSONObject) jp.parse(br);
- JSONArray mappings = (JSONArray) parsed.get("mappings");
+ JSONArray mappings = (JSONArray) parsed.get(MAPPINGS);
Iterator rvals = mappings.iterator();
while (rvals.hasNext())
{
// todo check for "mapped"
JSONObject val = (JSONObject) rvals.next();
- JSONObject mapped = (JSONObject) val.get("mapped");
+ JSONObject mapped = (JSONObject) val.get(MAPPED);
int start = Integer.parseInt(mapped.get("start").toString());
int end = Integer.parseInt(mapped.get("end").toString());
String strand = mapped.get("strand").toString();
return result;
}
+ /**
+ * Calls the REST /map/cds/id service, and returns a DBRefEntry holding the
+ * returned chromosomal coordinates, or returns null if the call fails
+ *
+ * @param division
+ * e.g. Ensembl, EnsemblMetazoa
+ * @param accession
+ * e.g. ENST00000592782, Y55B1AR.1.1
+ * @param start
+ * @param end
+ * @return
+ */
+ public GeneLociI getCdsMapping(String division, String accession,
+ int start, int end)
+ {
+ return getIdMapping(division, accession, start, end, CDS);
+ }
+
+ /**
+ * Calls the REST /map/cdna/id service, and returns a DBRefEntry holding the
+ * returned chromosomal coordinates, or returns null if the call fails
+ *
+ * @param division
+ * e.g. Ensembl, EnsemblMetazoa
+ * @param accession
+ * e.g. ENST00000592782, Y55B1AR.1.1
+ * @param start
+ * @param end
+ * @return
+ */
+ public GeneLociI getCdnaMapping(String division, String accession,
+ int start, int end)
+ {
+ return getIdMapping(division, accession, start, end, CDNA);
+ }
+
+ GeneLociI getIdMapping(String division, String accession, int start,
+ int end, String cdsOrCdna)
+ {
+ URL url = null;
+ BufferedReader br = null;
+
+ try
+ {
+ String domain = new EnsemblInfo().getDomain(division);
+ if (domain != null)
+ {
+ url = getIdMapUrl(domain, accession, start, end, cdsOrCdna);
+ br = getHttpResponse(url, null);
+ return (parseIdMappingResponse(br, accession, domain));
+ }
+ return null;
+ } catch (Throwable t)
+ {
+ System.out.println("Error calling " + url + ": " + t.getMessage());
+ return null;
+ } finally
+ {
+ if (br != null)
+ {
+ try
+ {
+ br.close();
+ } catch (IOException e)
+ {
+ // ignore
+ }
+ }
+ }
+ }
+
+ /**
+ * Constructs a URL to the /map/cds/<id> or /map/cdna/<id> REST service. The
+ * REST call is to either ensembl or ensemblgenomes, as determined from the
+ * division, e.g. Ensembl or EnsemblProtists.
+ *
+ * @param domain
+ * @param accession
+ * @param start
+ * @param end
+ * @param cdsOrCdna
+ * @return
+ * @throws MalformedURLException
+ */
+ URL getIdMapUrl(String domain, String accession, int start, int end,
+ String cdsOrCdna) throws MalformedURLException
+ {
+ String url = String
+ .format("%s/map/%s/%s/%d..%d?include_original_region=1&content-type=application/json",
+ domain, cdsOrCdna, accession, start, end);
+ return new URL(url);
+ }
+
+ /**
+ * Parses the JSON response from the /map/cds/ or /map/cdna REST service. The
+ * format is
+ *
+ * <pre>
+ * {"mappings":
+ * [
+ * {"assembly_name":"TAIR10","end":2501311,"seq_region_name":"1","gap":0,
+ * "strand":-1,"coord_system":"chromosome","rank":0,"start":2501114},
+ * {"assembly_name":"TAIR10","end":2500815,"seq_region_name":"1","gap":0,
+ * "strand":-1,"coord_system":"chromosome","rank":0,"start":2500714}
+ * ]
+ * }
+ * </pre>
+ *
+ * @param br
+ * @param accession
+ * @param domain
+ * @return
+ */
+ GeneLociI parseIdMappingResponse(BufferedReader br, String accession,
+ String domain)
+ {
+ JSONParser jp = new JSONParser();
+
+ try
+ {
+ JSONObject parsed = (JSONObject) jp.parse(br);
+ JSONArray mappings = (JSONArray) parsed.get(MAPPINGS);
+
+ Iterator rvals = mappings.iterator();
+ String assembly = null;
+ String chromosome = null;
+ int fromEnd = 0;
+ List<int[]> regions = new ArrayList<>();
+
+ while (rvals.hasNext())
+ {
+ JSONObject val = (JSONObject) rvals.next();
+ JSONObject original = (JSONObject) val.get("original");
+ fromEnd = Integer.parseInt(original.get("end").toString());
+
+ JSONObject mapped = (JSONObject) val.get(MAPPED);
+ int start = Integer.parseInt(mapped.get("start").toString());
+ int end = Integer.parseInt(mapped.get("end").toString());
+ String ass = mapped.get("assembly_name").toString();
+ if (assembly != null && !assembly.equals(ass))
+ {
+ System.err
+ .println("EnsemblMap found multiple assemblies - can't resolve");
+ return null;
+ }
+ assembly = ass;
+ String chr = mapped.get("seq_region_name").toString();
+ if (chromosome != null && !chromosome.equals(chr))
+ {
+ System.err
+ .println("EnsemblMap found multiple chromosomes - can't resolve");
+ return null;
+ }
+ chromosome = chr;
+ String strand = mapped.get("strand").toString();
+ if ("-1".equals(strand))
+ {
+ regions.add(new int[] { end, start });
+ }
+ else
+ {
+ regions.add(new int[] { start, end });
+ }
+ }
+
+ /*
+ * processed all mapped regions on chromosome, assemble the result,
+ * having first fetched the species id for the accession
+ */
+ final String species = new EnsemblLookup(domain)
+ .getSpecies(accession);
+ final String as = assembly;
+ final String chr = chromosome;
+ List<int[]> fromRange = Collections.singletonList(new int[] { 1,
+ fromEnd });
+ final MapList map = new MapList(fromRange, regions, 1, 1);
+ return new GeneLociI()
+ {
+
+ @Override
+ public String getSpeciesId()
+ {
+ return species == null ? "" : species;
+ }
+
+ @Override
+ public String getAssemblyId()
+ {
+ return as;
+ }
+
+ @Override
+ public String getChromosomeId()
+ {
+ return chr;
+ }
+
+ @Override
+ public MapList getMap()
+ {
+ return map;
+ }
+ };
+ } catch (IOException | ParseException | NumberFormatException e)
+ {
+ // ignore
+ }
+
+ return null;
+ }
+
}
private static final String REST_CHANGE_LOG = "https://github.com/Ensembl/ensembl-rest/wiki/Change-log";
- private static Map<String, EnsemblInfo> domainData;
+ private static Map<String, EnsemblData> domainData;
// @see https://github.com/Ensembl/ensembl-rest/wiki/Output-formats
private static final String PING_URL = "http://rest.ensembl.org/info/ping.json";
static
{
- domainData = new HashMap<String, EnsemblInfo>();
+ domainData = new HashMap<String, EnsemblData>();
domainData.put(ENSEMBL_REST,
- new EnsemblInfo(ENSEMBL_REST, LATEST_ENSEMBL_REST_VERSION));
- domainData.put(ENSEMBL_GENOMES_REST, new EnsemblInfo(
+ new EnsemblData(ENSEMBL_REST, LATEST_ENSEMBL_REST_VERSION));
+ domainData.put(ENSEMBL_GENOMES_REST, new EnsemblData(
ENSEMBL_GENOMES_REST, LATEST_ENSEMBLGENOMES_REST_VERSION));
}
// to test:
// retryDelay = "5";
- EnsemblInfo info = domainData.get(getDomain());
+ EnsemblData info = domainData.get(getDomain());
if (retryDelay != null)
{
System.err.println("Ensembl REST service rate limit exceeded, wait "
*/
protected boolean isEnsemblAvailable()
{
- EnsemblInfo info = domainData.get(getDomain());
+ EnsemblData info = domainData.get(getDomain());
long now = System.currentTimeMillis();
*/
private void checkEnsemblRestVersion()
{
- EnsemblInfo info = domainData.get(getDomain());
+ EnsemblData info = domainData.get(getDomain());
JSONParser jp = new JSONParser();
URL url = null;
protected void showProductsFor(final SequenceI[] sel, final boolean _odna,
final String source)
{
- new Thread(CrossRefAction.showProductsFor(sel, _odna, source, this))
+ new Thread(CrossRefAction.getHandlerFor(sel, _odna, source, this))
.start();
}
import jalview.bin.Cache;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
+import jalview.datamodel.DBRefEntry;
import jalview.datamodel.DBRefSource;
+import jalview.datamodel.GeneLociI;
import jalview.datamodel.SequenceI;
+import jalview.ext.ensembl.EnsemblInfo;
+import jalview.ext.ensembl.EnsemblMap;
import jalview.io.gff.SequenceOntologyI;
import jalview.structure.StructureSelectionManager;
+import jalview.util.DBRefUtils;
+import jalview.util.MapList;
+import jalview.util.MappingUtils;
import jalview.util.MessageManager;
import jalview.ws.SequenceFetcher;
import java.util.ArrayList;
+import java.util.HashMap;
import java.util.List;
-
-import javax.swing.JOptionPane;
+import java.util.Map;
+import java.util.Set;
/**
* Factory constructor and runnable for discovering and displaying
private SequenceI[] sel;
- private boolean _odna;
+ private final boolean _odna;
private String source;
- List<AlignmentViewPanel> xrefViews = new ArrayList<AlignmentViewPanel>();
+ List<AlignmentViewPanel> xrefViews = new ArrayList<>();
- public List<jalview.api.AlignmentViewPanel> getXrefViews()
+ List<AlignmentViewPanel> getXrefViews()
{
return xrefViews;
}
{
return;
}
+
+ /*
+ * try to look up chromosomal coordinates for nucleotide
+ * sequences (if not already retrieved)
+ */
+ findGeneLoci(xrefs.getSequences());
+
/*
* get display scheme (if any) to apply to features
*/
if (Cache.getDefault(Preferences.ENABLE_SPLIT_FRAME, true))
{
- boolean copyAlignmentIsAligned = false;
- if (dna)
- {
- copyAlignment = AlignmentUtils.makeCdsAlignment(sel, dataset,
- xrefsAlignment.getSequencesArray());
- if (copyAlignment.getHeight() == 0)
- {
- JvOptionPane.showMessageDialog(alignFrame,
- MessageManager.getString("label.cant_map_cds"),
- MessageManager.getString("label.operation_failed"),
- JvOptionPane.OK_OPTION);
- System.err.println("Failed to make CDS alignment");
- }
-
- /*
- * pending getting Embl transcripts to 'align',
- * we are only doing this for Ensembl
- */
- // TODO proper criteria for 'can align as cdna'
- if (DBRefSource.ENSEMBL.equalsIgnoreCase(source)
- || AlignmentUtils.looksLikeEnsembl(alignment))
- {
- copyAlignment.alignAs(alignment);
- copyAlignmentIsAligned = true;
- }
- }
- else
+ copyAlignment = copyAlignmentForSplitFrame(alignment, dataset, dna,
+ xrefs, xrefsAlignment);
+ if (copyAlignment == null)
{
- copyAlignment = AlignmentUtils.makeCopyAlignment(sel,
- xrefs.getSequencesArray(), dataset);
- }
- copyAlignment
- .setGapCharacter(alignFrame.viewport.getGapCharacter());
-
- StructureSelectionManager ssm = StructureSelectionManager
- .getStructureSelectionManager(Desktop.instance);
-
- /*
- * register any new mappings for sequence mouseover etc
- * (will not duplicate any previously registered mappings)
- */
- ssm.registerMappings(dataset.getCodonFrames());
-
- if (copyAlignment.getHeight() <= 0)
- {
- System.err.println(
- "No Sequences generated for xRef type " + source);
- return;
- }
- /*
- * align protein to dna
- */
- if (dna && copyAlignmentIsAligned)
- {
- xrefsAlignment.alignAs(copyAlignment);
- }
- else
- {
- /*
- * align cdna to protein - currently only if
- * fetching and aligning Ensembl transcripts!
- */
- // TODO: generalise for other sources of locus/transcript/cds data
- if (dna && DBRefSource.ENSEMBL.equalsIgnoreCase(source))
- {
- copyAlignment.alignAs(xrefsAlignment);
- }
+ return; // failed
}
}
+
/*
* build AlignFrame(s) according to available alignment data
*/
xrefViews.add(newFrame.alignPanel);
return; // via finally clause
}
+
AlignFrame copyThis = new AlignFrame(copyAlignment,
AlignFrame.DEFAULT_WIDTH, AlignFrame.DEFAULT_HEIGHT);
copyThis.setTitle(alignFrame.getTitle());
}
/**
+ * Tries to add chromosomal coordinates to any nucleotide sequence which does
+ * not already have them. Coordinates are retrieved from Ensembl given an
+ * Ensembl identifier, either on the sequence itself or on a peptide sequence
+ * it has a reference to.
+ *
+ * <pre>
+ * Example (human):
+ * - fetch EMBLCDS cross-references for Uniprot entry P30419
+ * - the EMBL sequences do not have xrefs to Ensembl
+ * - the Uniprot entry has xrefs to
+ * ENSP00000258960, ENSP00000468424, ENST00000258960, ENST00000592782
+ * - either of the transcript ids can be used to retrieve gene loci e.g.
+ * http://rest.ensembl.org/map/cds/ENST00000592782/1..100000
+ * Example (invertebrate):
+ * - fetch EMBLCDS cross-references for Uniprot entry Q43517 (FER1_SOLLC)
+ * - the Uniprot entry has an xref to ENSEMBLPLANTS Solyc10g044520.1.1
+ * - can retrieve gene loci with
+ * http://rest.ensemblgenomes.org/map/cds/Solyc10g044520.1.1/1..100000
+ * </pre>
+ *
+ * @param sequences
+ */
+ public static void findGeneLoci(List<SequenceI> sequences)
+ {
+ Map<DBRefEntry, GeneLociI> retrievedLoci = new HashMap<>();
+ for (SequenceI seq : sequences)
+ {
+ findGeneLoci(seq, retrievedLoci);
+ }
+ }
+
+ /**
+ * Tres to find chromosomal coordinates for the sequence, by searching its
+ * direct and indirect cross-references for Ensembl. If the loci have already
+ * been retrieved, just reads them out of the map of retrievedLoci; this is
+ * the case of an alternative transcript for the same protein. Otherwise calls
+ * a REST service to retrieve the loci, and if successful, adds them to the
+ * sequence and to the retrievedLoci.
+ *
+ * @param seq
+ * @param retrievedLoci
+ */
+ static void findGeneLoci(SequenceI seq,
+ Map<DBRefEntry, GeneLociI> retrievedLoci)
+ {
+ /*
+ * don't replace any existing chromosomal coordinates
+ */
+ if (seq == null || seq.isProtein() || seq.getGeneLoci() != null
+ || seq.getDBRefs() == null)
+ {
+ return;
+ }
+
+ Set<String> ensemblDivisions = new EnsemblInfo().getDivisions();
+
+ /*
+ * first look for direct dbrefs from sequence to Ensembl
+ */
+ String[] divisionsArray = ensemblDivisions
+ .toArray(new String[ensemblDivisions.size()]);
+ DBRefEntry[] seqRefs = seq.getDBRefs();
+ DBRefEntry[] directEnsemblRefs = DBRefUtils.selectRefs(seqRefs,
+ divisionsArray);
+ if (directEnsemblRefs != null)
+ {
+ for (DBRefEntry ensemblRef : directEnsemblRefs)
+ {
+ if (fetchGeneLoci(seq, ensemblRef, retrievedLoci))
+ {
+ return;
+ }
+ }
+ }
+
+ /*
+ * else look for indirect dbrefs from sequence to Ensembl
+ */
+ for (DBRefEntry dbref : seq.getDBRefs())
+ {
+ if (dbref.getMap() != null && dbref.getMap().getTo() != null)
+ {
+ DBRefEntry[] dbrefs = dbref.getMap().getTo().getDBRefs();
+ DBRefEntry[] indirectEnsemblRefs = DBRefUtils.selectRefs(dbrefs,
+ divisionsArray);
+ if (indirectEnsemblRefs != null)
+ {
+ for (DBRefEntry ensemblRef : indirectEnsemblRefs)
+ {
+ if (fetchGeneLoci(seq, ensemblRef, retrievedLoci))
+ {
+ return;
+ }
+ }
+ }
+ }
+ }
+ }
+
+ /**
+ * Retrieves chromosomal coordinates for the Ensembl (or EnsemblGenomes)
+ * identifier in dbref. If successful, and the sequence length matches gene
+ * loci length, then add it to the sequence, and to the retrievedLoci map.
+ * Answers true if successful, else false.
+ *
+ * @param seq
+ * @param dbref
+ * @param retrievedLoci
+ * @return
+ */
+ static boolean fetchGeneLoci(SequenceI seq, DBRefEntry dbref,
+ Map<DBRefEntry, GeneLociI> retrievedLoci)
+ {
+ String accession = dbref.getAccessionId();
+ String division = dbref.getSource();
+
+ /*
+ * hack: ignore cross-references to Ensembl protein ids
+ * (can't fetch chromosomal mapping for these)
+ * todo: is there an equivalent in EnsemblGenomes?
+ */
+ if (accession.startsWith("ENSP"))
+ {
+ return false;
+ }
+ EnsemblMap mapper = new EnsemblMap();
+
+ /*
+ * try CDS mapping first
+ */
+ GeneLociI geneLoci = mapper.getCdsMapping(division, accession, 1,
+ seq.getLength());
+ if (geneLoci != null)
+ {
+ MapList map = geneLoci.getMap();
+ int mappedFromLength = MappingUtils.getLength(map.getFromRanges());
+ if (mappedFromLength == seq.getLength())
+ {
+ seq.setGeneLoci(geneLoci.getSpeciesId(), geneLoci.getAssemblyId(),
+ geneLoci.getChromosomeId(), geneLoci.getMap());
+ retrievedLoci.put(dbref, geneLoci);
+ return true;
+ }
+ }
+
+ /*
+ * else try CDNA mapping
+ */
+ geneLoci = mapper.getCdnaMapping(division, accession, 1,
+ seq.getLength());
+ if (geneLoci != null)
+ {
+ MapList map = geneLoci.getMap();
+ int mappedFromLength = MappingUtils.getLength(map.getFromRanges());
+ if (mappedFromLength == seq.getLength())
+ {
+ seq.setGeneLoci(geneLoci.getSpeciesId(), geneLoci.getAssemblyId(),
+ geneLoci.getChromosomeId(), geneLoci.getMap());
+ retrievedLoci.put(dbref, geneLoci);
+ return true;
+ }
+ }
+
+ return false;
+ }
+
+ /**
+ * @param alignment
+ * @param dataset
+ * @param dna
+ * @param xrefs
+ * @param xrefsAlignment
+ * @return
+ */
+ protected AlignmentI copyAlignmentForSplitFrame(AlignmentI alignment,
+ AlignmentI dataset, boolean dna, AlignmentI xrefs,
+ AlignmentI xrefsAlignment)
+ {
+ AlignmentI copyAlignment;
+ boolean copyAlignmentIsAligned = false;
+ if (dna)
+ {
+ copyAlignment = AlignmentUtils.makeCdsAlignment(sel, dataset,
+ xrefsAlignment.getSequencesArray());
+ if (copyAlignment.getHeight() == 0)
+ {
+ JvOptionPane.showMessageDialog(alignFrame,
+ MessageManager.getString("label.cant_map_cds"),
+ MessageManager.getString("label.operation_failed"),
+ JvOptionPane.OK_OPTION);
+ System.err.println("Failed to make CDS alignment");
+ return null;
+ }
+
+ /*
+ * pending getting Embl transcripts to 'align',
+ * we are only doing this for Ensembl
+ */
+ // TODO proper criteria for 'can align as cdna'
+ if (DBRefSource.ENSEMBL.equalsIgnoreCase(source)
+ || AlignmentUtils.looksLikeEnsembl(alignment))
+ {
+ copyAlignment.alignAs(alignment);
+ copyAlignmentIsAligned = true;
+ }
+ }
+ else
+ {
+ copyAlignment = AlignmentUtils.makeCopyAlignment(sel,
+ xrefs.getSequencesArray(), dataset);
+ }
+ copyAlignment
+ .setGapCharacter(alignFrame.viewport.getGapCharacter());
+
+ StructureSelectionManager ssm = StructureSelectionManager
+ .getStructureSelectionManager(Desktop.instance);
+
+ /*
+ * register any new mappings for sequence mouseover etc
+ * (will not duplicate any previously registered mappings)
+ */
+ ssm.registerMappings(dataset.getCodonFrames());
+
+ if (copyAlignment.getHeight() <= 0)
+ {
+ System.err.println(
+ "No Sequences generated for xRef type " + source);
+ return null;
+ }
+
+ /*
+ * align protein to dna
+ */
+ if (dna && copyAlignmentIsAligned)
+ {
+ xrefsAlignment.alignAs(copyAlignment);
+ }
+ else
+ {
+ /*
+ * align cdna to protein - currently only if
+ * fetching and aligning Ensembl transcripts!
+ */
+ // TODO: generalise for other sources of locus/transcript/cds data
+ if (dna && DBRefSource.ENSEMBL.equalsIgnoreCase(source))
+ {
+ copyAlignment.alignAs(xrefsAlignment);
+ }
+ }
+
+ return copyAlignment;
+ }
+
+ /**
* Makes an alignment containing the given sequences, and adds them to the
* given dataset, which is also set as the dataset for the new alignment
*
return al;
}
- public CrossRefAction(AlignFrame alignFrame, SequenceI[] sel,
- boolean _odna, String source)
+ /**
+ * Constructor
+ *
+ * @param af
+ * @param seqs
+ * @param fromDna
+ * @param dbSource
+ */
+ CrossRefAction(AlignFrame af, SequenceI[] seqs, boolean fromDna,
+ String dbSource)
{
- this.alignFrame = alignFrame;
- this.sel = sel;
- this._odna = _odna;
- this.source = source;
+ this.alignFrame = af;
+ this.sel = seqs;
+ this._odna = fromDna;
+ this.source = dbSource;
}
- public static CrossRefAction showProductsFor(final SequenceI[] sel,
- final boolean _odna, final String source,
+ public static CrossRefAction getHandlerFor(final SequenceI[] sel,
+ final boolean fromDna, final String source,
final AlignFrame alignFrame)
{
- return new CrossRefAction(alignFrame, sel, _odna, source);
+ return new CrossRefAction(alignFrame, sel, fromDna, source);
}
}
/*
* Comparator to order DBRefEntry by Source + accession id (case-insensitive),
- * with 'Primary' sources placed before others
+ * with 'Primary' sources placed before others, and 'chromosome' first of all
*/
private static Comparator<DBRefEntry> comparator = new Comparator<DBRefEntry>()
{
@Override
public int compare(DBRefEntry ref1, DBRefEntry ref2)
{
+ if (ref1.isChromosome())
+ {
+ return -1;
+ }
+ if (ref2.isChromosome())
+ {
+ return 1;
+ }
String s1 = ref1.getSource();
String s2 = ref2.getSource();
boolean s1Primary = isPrimarySource(s1);
/**
* Transfers VCF features to sequences to which this sequence has a mapping.
- * If the mapping is 1:3, computes peptide variants from nucleotide variants.
+ * If the mapping is 3:1, computes peptide variants from nucleotide variants.
*
* @param seq
*/
*/
VariantContext variant = variants.next();
- /*
- * we can only process SNP variants (which can be reported
- * as part of a MIXED variant record
- */
- if (!variant.isSNP() && !variant.isMixed())
- {
- // continue;
- }
-
int start = variant.getStart() - offset;
int end = variant.getEnd() - offset;
/*
* convert chromosomal location to sequence coordinates
+ * - may be reverse strand (convert to forward for sequence feature)
* - null if a partially overlapping feature
*/
int[] seqLocation = mapping.locateInFrom(start, end);
if (seqLocation != null)
{
- count += addAlleleFeatures(seq, variant, seqLocation[0],
- seqLocation[1], forwardStrand);
+ int featureStart = Math.min(seqLocation[0], seqLocation[1]);
+ int featureEnd = Math.max(seqLocation[0], seqLocation[1]);
+ count += addAlleleFeatures(seq, variant, featureStart, featureEnd,
+ forwardStrand);
}
}
String reference = variant.getReference().getBaseString();
Allele alt = variant.getAlternateAllele(altAlleleIndex);
String allele = alt.getBaseString();
- if (allele.length() != 1)
- {
- /*
- * not a SNP variant
- */
- // return 0;
- }
/*
* build the ref,alt allele description e.g. "G,A", using the base
* call (e.g.) http://rest.ensembl.org/map/human/GRCh38/17:45051610..45109016:1/GRCh37
*/
EnsemblMap mapper = new EnsemblMap();
- int[] mapping = mapper.getMapping(species, chromosome, fromRef, toRef,
+ int[] mapping = mapper.getAssemblyMapping(species, chromosome, fromRef,
+ toRef,
queryRange);
if (mapping == null)
}
/**
-<<<<<<< HEAD
-=======
- * Answers true if the feature belongs to a feature group which is not
- * currently displayed, else false
- *
- * @param sequenceFeature
- * @return
- */
- @Override
- protected boolean featureGroupNotShown(
- final SequenceFeature sequenceFeature)
- {
- return featureGroups != null && sequenceFeature.featureGroup != null
- && sequenceFeature.featureGroup.length() != 0
- && featureGroups.containsKey(sequenceFeature.featureGroup)
- && !featureGroups.get(sequenceFeature.featureGroup)
- .booleanValue();
- }
-
- /**
->>>>>>> refs/heads/develop
* Called when alignment in associated view has new/modified features to
* discover and display.
*
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
+import java.util.Map;
+
+import junit.extensions.PA;
import org.testng.Assert;
import org.testng.annotations.BeforeClass;
// . codonframes
//
//
- HashMap<String, String> dbtoviewBit = new HashMap<>();
+ Map<String, String> dbtoviewBit = new HashMap<>();
List<String> keyseq = new ArrayList<>();
- HashMap<String, File> savedProjects = new HashMap<>();
+ Map<String, File> savedProjects = new HashMap<>();
for (String[] did : new String[][] { { "UNIPROT", "P00338" } })
{
if (pass2 == 0)
{ // retrieve and show cross-refs in this thread
- cra = new CrossRefAction(af, seqs, dna, db);
+ cra = CrossRefAction.getHandlerFor(seqs, dna, db, af);
cra.run();
- if (cra.getXrefViews().size() == 0)
+ cra_views = (List<AlignmentViewPanel>) PA.getValue(cra,
+ "xrefViews");
+ if (cra_views.size() == 0)
{
failedXrefMenuItems.add("No crossrefs retrieved for "
+ first + " -> " + db);
continue;
}
- cra_views = cra.getXrefViews();
assertNucleotide(cra_views.get(0),
"Nucleotide panel included proteins for " + first
+ " -> " + db);
if (pass3 == 0)
{
-
SequenceI[] xrseqs = avp.getAlignment()
.getSequencesArray();
AlignFrame nextaf = Desktop.getAlignFrameFor(avp
.getAlignViewport());
- cra = new CrossRefAction(nextaf, xrseqs, avp
- .getAlignViewport().isNucleotide(), xrefdb);
+ cra = CrossRefAction.getHandlerFor(xrseqs, avp
+ .getAlignViewport().isNucleotide(), xrefdb,
+ nextaf);
cra.run();
- if (cra.getXrefViews().size() == 0)
+ cra_views2 = (List<AlignmentViewPanel>) PA.getValue(
+ cra, "xrefViews");
+ if (cra_views2.size() == 0)
{
failedXrefMenuItems
.add("No crossrefs retrieved for '"
+ " via '" + nextaf.getTitle() + "'");
continue;
}
- cra_views2 = cra.getXrefViews();
assertNucleotide(cra_views2.get(0),
"Nucleotide panel included proteins for '"
+ nextxref + "' to " + xrefdb
* viewpanel needs to be called with a distinct xrefpath to ensure
* each one's strings are compared)
*/
- private void stringify(HashMap<String, String> dbtoviewBit,
- HashMap<String, File> savedProjects, String xrefpath,
+ private void stringify(Map<String, String> dbtoviewBit,
+ Map<String, File> savedProjects, String xrefpath,
AlignmentViewPanel avp)
{
if (savedProjects != null)
package jalview.io.vcf;
import static org.testng.Assert.assertEquals;
-import static org.testng.Assert.fail;
+import static org.testng.Assert.assertTrue;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.DBRefEntry;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceFeature;
import jalview.datamodel.SequenceI;
+import jalview.datamodel.features.SequenceFeatures;
import jalview.gui.AlignFrame;
import jalview.io.DataSourceType;
import jalview.io.FileLoader;
public class VCFLoaderTest
{
- // columns 9717- of gene P30419 from Ensembl (modified)
- private static final String FASTA =
- // forward strand 'gene'
- ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
+ private static final float DELTA = 0.00001f;
+
+ // columns 9717- of gene P30419 from Ensembl (much modified)
+ private static final String FASTA = ""
+ +
+ /*
+ * forward strand 'gene' and 'transcript' with two exons
+ */
+ ">gene1/1-25 chromosome:GRCh38:17:45051610:45051634:1\n"
+ "CAAGCTGGCGGACGAGAGTGTGACA\n"
- // and a 'made up' mini-transcript with two exons
+ ">transcript1/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
- +
- // 'reverse strand' gene (reverse complement)
- ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
+
+ /*
+ * reverse strand gene and transcript (reverse complement alleles!)
+ */
+ + ">gene2/1-25 chromosome:GRCh38:17:45051610:45051634:-1\n"
+ "TGTCACACTCTCGTCCGCCAGCTTG\n"
- // and its 'transcript'
- + ">transcript2/1-18\n"
- + "-GTCACACTCT----CGCCAGCT--\n";
+ + ">transcript2/1-18\n" + "-GTCACACTCT----CGCCAGCT--\n"
+
+ /*
+ * 'gene' on chromosome 5 with two transcripts
+ */
+ + ">gene3/1-25 chromosome:GRCh38:5:45051610:45051634:1\n"
+ + "CAAGCTGGCGGACGAGAGTGTGACA\n"
+ + ">transcript3/1-18\n--AGCTGGCG----AGAGTGTGAC-\n"
+ + ">transcript4/1-18\n-----TGG-GGACGAGAGTGTGA-A\n";
private static final String[] VCF = { "##fileformat=VCFv4.2",
"##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency, for each ALT allele, in the same order as listed\">",
"##reference=GRCh38",
"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO",
- // SNP A/T in position 2 of gene sequence (precedes transcript)
- "17\t45051611\t.\tA\tT\t1666.64\tRF\tAC=15;AF=5.08130e-03",
+ // A/T,C variants in position 2 of gene sequence (precedes transcript)
+ // should create 2 variant features with respective scores
+ "17\t45051611\t.\tA\tT,C\t1666.64\tRF\tAC=15;AF=5.0e-03,4.0e-03",
// SNP G/C in position 4 of gene sequence, position 2 of transcript
- // this is a mixed variant, the insertion G/GA is not transferred
- "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.08130e-03" };
+ // insertion G/GA is transferred to nucleotide but not to peptide
+ "17\t45051613\t.\tG\tGA,C\t1666.64\tRF\tAC=15;AF=3.0e-03,2.0e-03" };
@Test(groups = "Functional")
public void testDoLoad() throws IOException
/*
* verify variant feature(s) added to gene
+ * NB alleles at a locus may not be processed, and features added,
+ * in the order in which they appear in the VCF record as method
+ * VariantContext.getAlternateAlleles() does not guarantee order
+ * - order of assertions here matches what we find (is not important)
*/
List<SequenceFeature> geneFeatures = al.getSequenceAt(0)
.getSequenceFeatures();
- assertEquals(geneFeatures.size(), 2);
+ SequenceFeatures.sortFeatures(geneFeatures, true);
+ assertEquals(geneFeatures.size(), 4);
SequenceFeature sf = geneFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
+ assertEquals(sf.getScore(), 4.0e-03, DELTA);
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,C");
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ sf = geneFeatures.get(1);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 2);
+ assertEquals(sf.getEnd(), 2);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 5.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 5.0e-03, DELTA);
assertEquals(sf.getValue(Gff3Helper.ALLELES), "A,T");
- sf = geneFeatures.get(1);
+ sf = geneFeatures.get(2);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 4);
assertEquals(sf.getEnd(), 4);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 2.0e-03, DELTA);
assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
+ sf = geneFeatures.get(3);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 4);
+ assertEquals(sf.getEnd(), 4);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 3.0e-03, DELTA);
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
+
/*
* verify variant feature(s) added to transcript
*/
List<SequenceFeature> transcriptFeatures = al.getSequenceAt(1)
.getSequenceFeatures();
- assertEquals(transcriptFeatures.size(), 1);
+ assertEquals(transcriptFeatures.size(), 2);
sf = transcriptFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 2);
assertEquals(sf.getEnd(), 2);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 2.0e-03, DELTA);
assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,C");
+ sf = transcriptFeatures.get(1);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 2);
+ assertEquals(sf.getEnd(), 2);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 3.0e-03, DELTA);
+ assertEquals(sf.getValue(Gff3Helper.ALLELES), "G,GA");
/*
- * verify variant feature(s) computed and added to protein
+ * verify SNP variant feature(s) computed and added to protein
* first codon AGC varies to ACC giving S/T
*/
DBRefEntry[] dbRefs = al.getSequenceAt(1).getDBRefs();
* from Ensembl and transcripts computed)
*/
AlignmentI alignment = af.getViewport().getAlignment();
- SequenceI gene1 = alignment.getSequenceAt(0);
+ SequenceI gene1 = alignment.findName("gene1");
int[] to = new int[] { 45051610, 45051634 };
int[] from = new int[] { gene1.getStart(), gene1.getEnd() };
gene1.setGeneLoci("human", "GRCh38", "17", new MapList(from, to, 1, 1));
* which is chromosome 45051612-45051619,45051624-45051633
*/
to = new int[] { 45051612, 45051619, 45051624, 45051633 };
- SequenceI transcript1 = alignment.getSequenceAt(1);
+ SequenceI transcript1 = alignment.findName("transcript1");
from = new int[] { transcript1.getStart(), transcript1.getEnd() };
transcript1.setGeneLoci("human", "GRCh38", "17", new MapList(from, to,
1, 1));
/*
* map gene2 to chromosome reverse strand
*/
- SequenceI gene2 = alignment.getSequenceAt(2);
+ SequenceI gene2 = alignment.findName("gene2");
to = new int[] { 45051634, 45051610 };
from = new int[] { gene2.getStart(), gene2.getEnd() };
gene2.setGeneLoci("human", "GRCh38", "17", new MapList(from, to, 1, 1));
* which is chromosome 45051633-45051624,45051619-45051612
*/
to = new int[] { 45051633, 45051624, 45051619, 45051612 };
- SequenceI transcript2 = alignment.getSequenceAt(3);
+ SequenceI transcript2 = alignment.findName("transcript2");
from = new int[] { transcript2.getStart(), transcript2.getEnd() };
transcript2.setGeneLoci("human", "GRCh38", "17", new MapList(from, to,
1, 1));
product = new DBRefEntry("", "", "ENSP002", map);
transcript2.addDBRef(product);
+ /*
+ * map gene3 to chromosome
+ */
+ SequenceI gene3 = alignment.findName("gene3");
+ to = new int[] { 45051610, 45051634 };
+ from = new int[] { gene3.getStart(), gene3.getEnd() };
+ gene3.setGeneLoci("human", "GRCh38", "5", new MapList(from, to, 1, 1));
+
+ /*
+ * map 'transcript3' to chromosome
+ */
+ SequenceI transcript3 = alignment.findName("transcript3");
+ to = new int[] { 45051612, 45051619, 45051624, 45051633 };
+ from = new int[] { transcript3.getStart(), transcript3.getEnd() };
+ transcript3.setGeneLoci("human", "GRCh38", "5", new MapList(from, to,
+ 1, 1));
+
+ /*
+ * map 'transcript4' to chromosome
+ */
+ SequenceI transcript4 = alignment.findName("transcript4");
+ to = new int[] { 45051615, 45051617, 45051619, 45051632, 45051634,
+ 45051634 };
+ from = new int[] { transcript4.getStart(), transcript4.getEnd() };
+ transcript4.setGeneLoci("human", "GRCh38", "5", new MapList(from, to,
+ 1, 1));
+
+ /*
+ * add a protein product as a DBRef on transcript3
+ */
+ SequenceI peptide3 = new Sequence("ENSP003", "SWRECD");
+ mapList = new MapList(new int[] { 1, 18 }, new int[] { 1, 6 }, 3, 1);
+ map = new Mapping(peptide3, mapList);
+ product = new DBRefEntry("", "", "ENSP003", map);
+ transcript3.addDBRef(product);
+
return alignment;
}
/*
* verify variant feature(s) added to gene2
* gene/1-25 maps to chromosome 45051634- reverse strand
- * variants A/T at 45051611 and G/C at 45051613 map to
- * T/A and C/G at gene positions 24 and 22 respectively
+ * variants A/T, A/C at 45051611 and G/GA,G/C at 45051613 map to
+ * T/A, T/G and C/TC,C/G at gene positions 24 and 22 respectively
*/
List<SequenceFeature> geneFeatures = al.getSequenceAt(2)
.getSequenceFeatures();
- assertEquals(geneFeatures.size(), 2);
+ SequenceFeatures.sortFeatures(geneFeatures, true);
+ assertEquals(geneFeatures.size(), 4);
SequenceFeature sf = geneFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 22);
assertEquals(sf.getEnd(), 22);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 2.0e-03, DELTA);
assertEquals("C,G", sf.getValue(Gff3Helper.ALLELES));
sf = geneFeatures.get(1);
assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 22);
+ assertEquals(sf.getEnd(), 22);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 3.0e-03, DELTA);
+ assertEquals("C,TC", sf.getValue(Gff3Helper.ALLELES));
+
+ sf = geneFeatures.get(2);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 24);
+ assertEquals(sf.getEnd(), 24);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 4.0e-03, DELTA);
+ assertEquals("T,G", sf.getValue(Gff3Helper.ALLELES));
+
+ sf = geneFeatures.get(3);
+ assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 24);
assertEquals(sf.getEnd(), 24);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 5.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 5.0e-03, DELTA);
assertEquals("T,A", sf.getValue(Gff3Helper.ALLELES));
/*
* verify variant feature(s) added to transcript2
- * variant C/G at position 22 of gene overlaps and maps to
- * position 17 of transcript
+ * variants G/GA,G/C at position 22 of gene overlap and map to
+ * C/TC,C/G at position 17 of transcript
*/
List<SequenceFeature> transcriptFeatures = al.getSequenceAt(3)
.getSequenceFeatures();
- assertEquals(transcriptFeatures.size(), 1);
+ assertEquals(transcriptFeatures.size(), 2);
sf = transcriptFeatures.get(0);
assertEquals(sf.getFeatureGroup(), "VCF");
assertEquals(sf.getBegin(), 17);
assertEquals(sf.getEnd(), 17);
assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
- assertEquals(sf.getScore(), 3.08130e-03, 0.000001f);
+ assertEquals(sf.getScore(), 2.0e-03, DELTA);
assertEquals("C,G", sf.getValue(Gff3Helper.ALLELES));
+ sf = transcriptFeatures.get(1);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 17);
+ assertEquals(sf.getEnd(), 17);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getScore(), 3.0e-03, DELTA);
+ assertEquals("C,TC", sf.getValue(Gff3Helper.ALLELES));
+
/*
* verify variant feature(s) computed and added to protein
* last codon GCT varies to GGT giving A/G in the last peptide position
}
/**
- * Tests that where variant records have more than one SNP allele, a variant
- * feature is created for each, and the corresponding data values set on it
- *
- * @throws IOException
- */
- @Test(groups = "Functional")
- public void testDoLoad_multipleAlleles() throws IOException
- {
- fail("todo");
- }
-
- /**
* Tests that if VEP consequence (CSQ) data is present in the VCF data, then
* it is added to the variant feature, but restricted where possible to the
* consequences for a specific transcript
@Test(groups = "Functional")
public void testDoLoad_vepCsq() throws IOException
{
- fail("todo");
+ AlignmentI al = buildAlignment();
+
+ VCFLoader loader = new VCFLoader(al);
+
+ /*
+ * VCF data file with variants at gene3 positions
+ * 1 C/A
+ * 5 C/T
+ * 9 CGT/C (deletion)
+ * 13 C/G, C/T
+ * 17 A/AC (insertion), A/G
+ */
+ loader.doLoad("test/jalview/io/vcf/testVcf.dat", null);
+
+ /*
+ * verify variant feature(s) added to gene3
+ */
+ List<SequenceFeature> geneFeatures = al.findName("gene3")
+ .getSequenceFeatures();
+ SequenceFeatures.sortFeatures(geneFeatures, true);
+ assertEquals(geneFeatures.size(), 7);
+ SequenceFeature sf = geneFeatures.get(0);
+ assertEquals(sf.getBegin(), 1);
+ assertEquals(sf.getEnd(), 1);
+ assertEquals(sf.getScore(), 0.1f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,A");
+ // gene features include Consequence for all transcripts
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(1);
+ assertEquals(sf.getBegin(), 5);
+ assertEquals(sf.getEnd(), 5);
+ assertEquals(sf.getScore(), 0.2f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,T");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(2);
+ assertEquals(sf.getBegin(), 9);
+ assertEquals(sf.getEnd(), 11); // deletion over 3 positions
+ assertEquals(sf.getScore(), 0.3f, DELTA);
+ assertEquals(sf.getValue("alleles"), "CGG,C");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(3);
+ assertEquals(sf.getBegin(), 13);
+ assertEquals(sf.getEnd(), 13);
+ assertEquals(sf.getScore(), 0.5f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,T");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(4);
+ assertEquals(sf.getBegin(), 13);
+ assertEquals(sf.getEnd(), 13);
+ assertEquals(sf.getScore(), 0.4f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,G");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(5);
+ assertEquals(sf.getBegin(), 17);
+ assertEquals(sf.getEnd(), 17);
+ assertEquals(sf.getScore(), 0.7f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,G");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ sf = geneFeatures.get(6);
+ assertEquals(sf.getBegin(), 17);
+ assertEquals(sf.getEnd(), 17); // insertion
+ assertEquals(sf.getScore(), 0.6f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,AC");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 2);
+
+ /*
+ * verify variant feature(s) added to transcript3
+ * at columns 5 (1), 17 (2), positions 3, 11
+ * note the deletion at columns 9-11 is not transferred since col 11
+ * has no mapping to transcript 3
+ */
+ List<SequenceFeature> transcriptFeatures = al.findName("transcript3")
+ .getSequenceFeatures();
+ SequenceFeatures.sortFeatures(transcriptFeatures, true);
+ assertEquals(transcriptFeatures.size(), 3);
+ sf = transcriptFeatures.get(0);
+ assertEquals(sf.getBegin(), 3);
+ assertEquals(sf.getEnd(), 3);
+ assertEquals(sf.getScore(), 0.2f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,T");
+ // transcript features only have Consequence for that transcripts
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript3"));
+
+ sf = transcriptFeatures.get(1);
+ assertEquals(sf.getBegin(), 11);
+ assertEquals(sf.getEnd(), 11);
+ assertEquals(sf.getScore(), 0.7f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,G");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript3"));
+
+ sf = transcriptFeatures.get(2);
+ assertEquals(sf.getBegin(), 11);
+ assertEquals(sf.getEnd(), 11);
+ assertEquals(sf.getScore(), 0.6f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,AC");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript3"));
+
+ /*
+ * verify variants computed on protein product for transcript3
+ * peptide is SWRECD
+ * codon variants are AGC/AGT position 1 which is synonymous
+ * and GAG/GGG which is E/G in position 4
+ * the insertion variant is not transferred to the peptide
+ */
+ DBRefEntry[] dbRefs = al.findName("transcript3").getDBRefs();
+ SequenceI peptide = null;
+ for (DBRefEntry dbref : dbRefs)
+ {
+ if (dbref.getMap().getMap().getFromRatio() == 3)
+ {
+ peptide = dbref.getMap().getTo();
+ }
+ }
+ List<SequenceFeature> proteinFeatures = peptide.getSequenceFeatures();
+ assertEquals(proteinFeatures.size(), 1);
+ sf = proteinFeatures.get(0);
+ assertEquals(sf.getFeatureGroup(), "VCF");
+ assertEquals(sf.getBegin(), 4);
+ assertEquals(sf.getEnd(), 4);
+ assertEquals(sf.getType(), SequenceOntologyI.SEQUENCE_VARIANT);
+ assertEquals(sf.getDescription(), "p.Glu4Gly");
+
+ /*
+ * verify variant feature(s) added to transcript4
+ * at columns 13 (2) and 17 (2), positions 7 and 11
+ */
+ transcriptFeatures = al.findName("transcript4").getSequenceFeatures();
+ SequenceFeatures.sortFeatures(transcriptFeatures, true);
+ assertEquals(transcriptFeatures.size(), 4);
+ sf = transcriptFeatures.get(0);
+ assertEquals(sf.getBegin(), 7);
+ assertEquals(sf.getEnd(), 7);
+ assertEquals(sf.getScore(), 0.5f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,T");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript4"));
+
+ sf = transcriptFeatures.get(1);
+ assertEquals(sf.getBegin(), 7);
+ assertEquals(sf.getEnd(), 7);
+ assertEquals(sf.getScore(), 0.4f, DELTA);
+ assertEquals(sf.getValue("alleles"), "C,G");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript4"));
+
+ sf = transcriptFeatures.get(2);
+ assertEquals(sf.getBegin(), 11);
+ assertEquals(sf.getEnd(), 11);
+ assertEquals(sf.getScore(), 0.7f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,G");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript4"));
+
+ sf = transcriptFeatures.get(3);
+ assertEquals(sf.getBegin(), 11);
+ assertEquals(sf.getEnd(), 11);
+ assertEquals(sf.getScore(), 0.6f, DELTA);
+ assertEquals(sf.getValue("alleles"), "A,AC");
+ assertEquals(((String) sf.getValue("CSQ")).split(",").length, 1);
+ assertTrue(sf.getValue("CSQ").toString().contains("transcript4"));
}
}
--- /dev/null
+##fileformat=VCFv4.2
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF_Female,Number=R,Type=Float,Description="Allele Frequency among Female genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence annotations from Ensembl VEP. Format: Allele|Consequence|IMPACT|SYMBOL|Gene|Feature_type|Feature|BIOTYPE|PolyPhen">
+##reference=GRCh38
+#CHROM POS ID REF ALT QUAL FILTER INFO
+5 45051610 . C A 81.96 RF;AC0 AC=1;AF=0.1;AN=0;AF_Female=2;AB_MEDIAN=6.00000e-01;CSQ=A|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,A|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad
+5 45051614 . C T 1666.64 RF AC=1;AF=0.2;AN=0;AF_Female=2;AB_MEDIAN=6.00000e-01;CSQ=T|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,T|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad
+5 45051618 . CGG C 41.94 AC0 AC=1;AF=0.3;AN=0;AF_Female=2;AB_MEDIAN=6.00000e-01;CSQ=C|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,C|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad,CSQ=CGT|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,CGT|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad
+5 45051622 . C G,T 224.23 RF;AC0 AC=1,2;AF=0.4,0.5;AN=0;AF_Female=2;AB_MEDIAN=6.00000e-01;CSQ=G|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,G|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad,T|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,T|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad
+5 45051626 . A AC,G 433.35 RF;AC0 AC=3,4;AF=0.6,0.7;AN=0;AF_Female=2;AB_MEDIAN=6.00000e-01;CSQ=G|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,G|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad,AC|missense_variant|MODIFIER|WASH7P|gene3|Transcript|transcript3|rna|Benign,AC|downstream_gene_variant|MODIFIER|WASH7P|gene3|Transcript|transcript4|mrna|Bad
toRanges = compound.getToRanges();
assertEquals(toRanges.size(), 1);
assertArrayEquals(new int[] { 47, 50, 71, 126 }, toRanges.get(0));
+
+ /*
+ * method returns null if not all regions are mapped through
+ */
+ ml1 = new MapList(new int[] { 1, 50 }, new int[] { 101, 150 }, 1, 1);
+ ml2 = new MapList(new int[] { 131, 180 }, new int[] { 201, 250 }, 1, 3);
+ compound = ml1.traverse(ml2);
+ assertNull(compound);
}
}
git://source.jalview.org / jalview.git / commitdiff