jalview.release=releases/Release_2_10_3_Branch
-jalview.version=2.10.3
+jalview.version=2.10.3b1
This builds a jalview.jar file and puts it into dist/
+
2. Make a lib directory in benchmarking/ if not already present and cd into this directory.
+
3. Purge any previous maven dependencies:
mvn dependency:purge-local-repository -DactTransitively=false -DreResolve=false
+
4. Run
mvn install:install-file -Dfile=../dist/jalview.jar -DgroupId=jalview.org -DartifactId=jalview -Dversion=1.0 -Dpackaging=jar -DlocalRepositoryPath=lib
-
to install the jalview.jar file in the local maven repository. The pom.xml in the benchmarking references this installation, so if you change the names the pom.xml file will also need to be updated.
+
5. Build and run jmh benchmarking. In the benchmarking directory:
mvn clean install
java -jar target/benchmarks.jar
To get JSON output instead use:
java -jar target/benchmarks.jar -rf json
- JSON output can be viewed quickly by drag-dropping on http://jmh.morethan.io/
\ No newline at end of file
+ JSON output can be viewed quickly by drag-dropping on http://jmh.morethan.io/
+
+ To get help use the standard -h option:
+ java -jar target/benchmarks.jar -h
+
+ More information here:
+ http://openjdk.java.net/projects/code-tools/jmh/
+ http://java-performance.info/jmh/
+
+
+ 6. If you make changes to the Jalview code everything will need to be refreshed, by performing steps 3-5 again.
</td>
</tr>
<tr>
- <td width=="60" nowrap>
+ <td width="60" nowrap>
<div align="center">
- <strong><a name="Jalview.2.10.3b1">2.10.3b1</a><br /> <em>5/12/2017</em></strong>
+ <strong><a name="Jalview.2.10.3b1">2.10.3b1</a><br /> <em>23/1/2018</em></strong>
</div>
</td>
<td><div align="left">
<li><!-- JAL-2827-->Helix annotation has 'notches' when scrolled into view if columns are hidden</li>
<li><!-- JAL-2740-->Annotation column filter can be slow to reset (ie after hitting cancel) for large numbers of hidden columns</li>
<li><!-- JAL-2849-->User preference for disabling inclusion of sequence limits when exporting as flat file has no effect</li>
- <ul>
+ <li><!-- JAL-2679-->Reproducible cross-reference relationships when retrieving sequences from EnsemblGenomes</li>
+ </ul>
</td>
</tr>
<tr>
label.2d_rna_sequence_name = 2D RNA - {0}
label.edit_name_and_description_current_group = Edit name and description of current group
label.from_file = From File
-label.enter_pdb_id = Enter PDB Id (or pdbid:chaincode)
+label.enter_pdb_id = Enter PDB Id
+label.enter_pdb_id_tip = Enter PDB Id (or pdbid:chaincode)
label.text_colour = Text Colour...
label.structure = Structure
label.show_pdbstruct_dialog = 3D Structure Data...
label.overview = Overview
label.reset_to_defaults = Reset to defaults
label.oview_calc = Recalculating overview...
-option.enable_disable_autosearch = When ticked, search is performed automatically.
+option.enable_disable_autosearch = When ticked, search is performed automatically
option.autosearch = Autosearch
-label.retrieve_ids = Retrieve IDs
\ No newline at end of file
+label.retrieve_ids = Retrieve IDs
+label.best_quality = Best Quality
+label.best_resolution = Best Resolution
+label.most_protein_chain = Most Protein Chain
+label.most_bound_molecules = Most Bound Molecules
+label.most_polymer_residues = Most Polymer Residues
+label.cached_structures = Cached Structures
+label.free_text_search = Free Text Search
label.edit_name_and_description_current_group = Editar el nombre y la descripción del grupo actual
label.from_file = desde fichero
label.enter_pdb_id = Introducir PDB Id
+label.enter_pdb_id_tip = Introducir PDB Id (o pdbid:chaincode)
label.text_colour = Color de texto...
label.structure = Estructura
label.create_sequence_details_report_annotation_for = Anotación para {0}
label.overview = Resumen
label.reset_to_defaults = Restablecen a los predeterminados
label.oview_calc = Recalculando resumen
+option.enable_disable_autosearch = Marcar para buscar automáticamente
+option.autosearch = Auto búsqueda
+label.retrieve_ids = Recuperar IDs
+label.best_quality = Mejor Calidad
+label.best_resolution = Mejor Resolución
+label.most_protein_chain = Más Cadena de Proteína
+label.most_bound_molecules = Más Moléculas Ligadas
+label.most_polymer_residues = Más Residuos de Polímeros
+label.cached_structures = Estructuras en Caché
+label.free_text_search = Búsqueda de texto libre
import jalview.io.gff.SequenceOntologyFactory;
import jalview.io.gff.SequenceOntologyI;
-import java.util.HashMap;
-import java.util.Map;
-
import com.stevesoft.pat.Regex;
/**
private static final Regex ACCESSION_REGEX = new Regex(
"(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
- private static Map<String, String> params = new HashMap<String, String>();
-
- static
- {
- params.put("object_type", "transcript");
- }
-
/*
* fetch exon features on genomic sequence (to identify the cdna regions)
* and cds and variation features (to retain)
}
/**
- * Parameter object_type=cdna added to ensure cdna and not peptide is returned
- * (JAL-2529)
+ * Parameter object_type=Transcaript added to ensure cdna and not peptide is
+ * returned (JAL-2529)
*/
@Override
- protected Map<String, String> getAdditionalParameters()
+ protected String getObjectType()
{
- return params;
+ return OBJECT_TYPE_TRANSCRIPT;
}
}
public AlignmentI getSequenceRecords(String query) throws IOException
{
// TODO: use a vararg String... for getSequenceRecords instead?
- List<String> queries = new ArrayList<String>();
+ List<String> queries = new ArrayList<>();
queries.add(query);
FileParse fp = getSequenceReader(queries);
if (fp == null || !fp.isValid())
urlstring.append("?content-type=text/x-gff3");
/*
+ * specify object_type=gene in case is shared by transcript and/or protein;
+ * currently only fetching features for gene sequences;
+ * refactor in future if needed to fetch for transcripts
+ */
+ urlstring.append("&").append(OBJECT_TYPE).append("=")
+ .append(OBJECT_TYPE_GENE);
+
+ /*
* specify features to retrieve
* @see http://rest.ensembl.org/documentation/info/overlap_id
- * could make the list a configurable entry in jalview.properties
+ * could make the list a configurable entry in .jalview_properties
*/
for (EnsemblFeatureType feature : featuresWanted)
{
return EnsemblSeqType.GENOMIC;
}
+ @Override
+ protected String getObjectType()
+ {
+ return OBJECT_TYPE_GENE;
+ }
+
/**
* Returns an alignment containing the gene(s) for the given gene or
* transcript identifier, or external identifier (e.g. Uniprot id). If given a
}
if (geneAlignment.getHeight() == 1)
{
+ // ensure id has 'correct' case for the Ensembl identifier
+ geneId = geneAlignment.getSequenceAt(0).getName();
getTranscripts(geneAlignment, geneId);
}
if (al == null)
*/
List<String> getGeneIds(String accessions)
{
- List<String> geneIds = new ArrayList<String>();
+ List<String> geneIds = new ArrayList<>();
for (String acc : accessions.split(getAccessionSeparator()))
{
int transcriptLength = 0;
final char[] geneChars = gene.getSequence();
int offset = gene.getStart(); // to convert to 0-based positions
- List<int[]> mappedFrom = new ArrayList<int[]>();
+ List<int[]> mappedFrom = new ArrayList<>();
for (SequenceFeature sf : splices)
{
* transfer features to the new sequence; we use EnsemblCdna to do this,
* to filter out unwanted features types (see method retainFeature)
*/
- List<int[]> mapTo = new ArrayList<int[]>();
+ List<int[]> mapTo = new ArrayList<>();
mapTo.add(new int[] { 1, transcriptLength });
MapList mapping = new MapList(mappedFrom, mapTo, 1, 1);
EnsemblCdna cdna = new EnsemblCdna(getDomain());
protected List<SequenceFeature> getTranscriptFeatures(String accId,
SequenceI geneSequence)
{
- List<SequenceFeature> transcriptFeatures = new ArrayList<SequenceFeature>();
+ List<SequenceFeature> transcriptFeatures = new ArrayList<>();
String parentIdentifier = GENE_PREFIX + accId;
for (SequenceFeature sf : sfs)
{
String parent = (String) sf.getValue(PARENT);
- if (parentIdentifier.equals(parent))
+ if (parentIdentifier.equalsIgnoreCase(parent))
{
transcriptFeatures.add(sf);
}
if (SequenceOntologyFactory.getInstance().isA(sf.getType(),
SequenceOntologyI.GENE))
{
- String id = (String) sf.getValue(ID);
- if ((GENE_PREFIX + accId).equals(id))
+ // NB features as gff use 'ID'; rest services return as 'id'
+ String id = (String) sf.getValue("ID");
+ if ((GENE_PREFIX + accId).equalsIgnoreCase(id))
{
return true;
}
if (isTranscript(type))
{
String parent = (String) sf.getValue(PARENT);
- if (!(GENE_PREFIX + accessionId).equals(parent))
+ if (!(GENE_PREFIX + accessionId).equalsIgnoreCase(parent))
{
return false;
}
{
if (isTranscript(sf.getType()))
{
- String id = (String) sf.getValue(ID);
+ String id = (String) sf.getValue("ID");
if (("transcript:" + accId).equals(id))
{
return true;
import org.json.simple.parser.ParseException;
/**
- * A client for the Ensembl lookup REST endpoint; used to find the Parent gene
- * identifier given a transcript identifier.
+ * 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";
-
/**
* Default constructor (to use rest.ensembl.org)
*/
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 = 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 getGeneId(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 (url != null)
{
br = getHttpResponse(url, ids);
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();
- try
- {
- geneId = getGeneId(transcriptId);
- } catch (StackOverflowError e)
- {
- /*
- * unlikely data condition error!
- */
- System.err
- .println("** Ensembl lookup "
- + getUrl(transcriptId).toString()
- + " looping on Parent!");
- }
+ geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
}
} catch (ParseException e)
{
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
-import java.util.Map;
-import java.util.Map.Entry;
/**
* Base class for Ensembl sequence fetchers
{
private static final String ALLELES = "alleles";
- protected static final String PARENT = "Parent";
-
- protected static final String ID = "ID";
-
protected static final String NAME = "Name";
protected static final String DESCRIPTION = "description";
try
{
/*
- * get 'dummy' genomic sequence with exon, cds and variation features
+ * get 'dummy' genomic sequence with gene, transcript,
+ * exon, cds and variation features
*/
SequenceI genomicSequence = null;
EnsemblFeatures gffFetcher = new EnsemblFeatures(getDomain());
/*
* transfer features to the query sequence
*/
- SequenceI querySeq = alignment.findName(accId);
+ SequenceI querySeq = alignment.findName(accId, true);
if (transferFeatures(accId, genomicSequence, querySeq))
{
urlstring.append("?type=").append(getSourceEnsemblType().getType());
urlstring.append(("&Accept=text/x-fasta"));
- Map<String, String> params = getAdditionalParameters();
- if (params != null)
+ String objectType = getObjectType();
+ if (objectType != null)
{
- for (Entry<String, String> entry : params.entrySet())
- {
- urlstring.append("&").append(entry.getKey()).append("=")
- .append(entry.getValue());
- }
+ urlstring.append("&").append(OBJECT_TYPE).append("=")
+ .append(objectType);
}
URL url = new URL(urlstring.toString());
}
/**
- * Override this method to add any additional x=y URL parameters needed
+ * Override this method to specify object_type request parameter
*
* @return
*/
- protected Map<String, String> getAdditionalParameters()
+ protected String getObjectType()
{
return null;
}
protected MapList getGenomicRangesFromFeatures(SequenceI sourceSequence,
String accId, int start)
{
- // SequenceFeature[] sfs = sourceSequence.getSequenceFeatures();
List<SequenceFeature> sfs = sourceSequence.getFeatures()
.getPositionalFeatures();
if (sfs.isEmpty())
* generously initial size for number of cds regions
* (worst case titin Q8WZ42 has c. 313 exons)
*/
- List<int[]> regions = new ArrayList<int[]>(100);
+ List<int[]> regions = new ArrayList<>(100);
int mappedLength = 0;
int direction = 1; // forward
boolean directionSet = false;
{
String parent = (String) sf.getValue(PARENT);
// using contains to allow for prefix "gene:", "transcript:" etc
- if (parent != null && !parent.contains(identifier))
+ if (parent != null
+ && !parent.toUpperCase().contains(identifier.toUpperCase()))
{
// this genomic feature belongs to a different transcript
return false;
protected List<SequenceFeature> findFeatures(SequenceI sequence,
String term, String parentId)
{
- List<SequenceFeature> result = new ArrayList<SequenceFeature>();
+ List<SequenceFeature> result = new ArrayList<>();
List<SequenceFeature> sfs = sequence.getFeatures()
.getFeaturesByOntology(term);
for (SequenceFeature sf : sfs)
{
String parent = (String) sf.getValue(PARENT);
- if (parent != null && parent.equals(parentId))
+ if (parent != null && parent.equalsIgnoreCase(parentId))
{
result.add(sf);
}
protected static final String ENSEMBL_REST = "http://rest.ensembl.org";
+ protected static final String OBJECT_TYPE_TRANSLATION = "Translation";
+
+ protected static final String OBJECT_TYPE_TRANSCRIPT = "Transcript";
+
+ protected static final String OBJECT_TYPE_GENE = "Gene";
+
+ protected static final String PARENT = "Parent";
+
+ protected static final String ID = "id";
+
+ protected static final String OBJECT_TYPE = "object_type";
+
/*
* possible values for the 'feature' parameter of the /overlap REST service
* @see http://rest.ensembl.org/documentation/info/overlap_id
{
private static final String GENE = "gene";
private static final String TYPE = "type";
- private static final String ID = "id";
-
/**
* Constructor given the target domain to fetch data from
*
protected JTabbedPane tabs = new JTabbedPane();
protected IProgressIndicator progressIndicator;
- protected JComboBox<FTSDataColumnI> cmb_searchTarget = new JComboBox<FTSDataColumnI>();
+ protected JComboBox<FTSDataColumnI> cmb_searchTarget = new JComboBox<>();
protected JButton btn_ok = new JButton();
protected int pageLimit;
- protected HashSet<String> paginatorCart = new HashSet<String>();
+ protected HashSet<String> paginatorCart = new HashSet<>();
private static final int MIN_WIDTH = 670;
private void jbInit() throws Exception
{
- txt_search = new JvCacheableInputBox<String>(getCacheKey());
+ txt_search = new JvCacheableInputBox<>(getCacheKey());
populateCmbSearchTargetOptions();
Integer width = getTempUserPrefs().get("FTSPanel.width") == null ? 800
: getTempUserPrefs().get("FTSPanel.width");
if (tabs != null)
{
tabs.setOpaque(true);
- tabs.insertTab("Free Text Search", null, this, "", 0);
+ tabs.insertTab(MessageManager.getString("label.free_text_search"),
+ null, this, "", 0);
mainFrame.setContentPane(tabs);
tabs.setVisible(true);
}
*/
public void populateCmbSearchTargetOptions()
{
- List<FTSDataColumnI> searchableTargets = new ArrayList<FTSDataColumnI>();
+ List<FTSDataColumnI> searchableTargets = new ArrayList<>();
try
{
Collection<FTSDataColumnI> foundFTSTargets = getFTSRestClient()
* structures
*/
protected void populateFilterComboBox(boolean haveData,
- boolean cachedPDBExists)
+ boolean cachedPDBExist)
{
/*
* temporarily suspend the change listener behaviour
cmb_filterOption.removeAllItems();
if (haveData)
{
- cmb_filterOption.addItem(new FilterOption("Best Quality",
+ cmb_filterOption.addItem(new FilterOption(
+ MessageManager.getString("label.best_quality"),
"overall_quality", VIEWS_FILTER, false));
- cmb_filterOption.addItem(new FilterOption("Best Resolution",
+ cmb_filterOption.addItem(new FilterOption(
+ MessageManager.getString("label.best_resolution"),
"resolution", VIEWS_FILTER, false));
- cmb_filterOption.addItem(new FilterOption("Most Protein Chain",
+ cmb_filterOption.addItem(new FilterOption(
+ MessageManager.getString("label.most_protein_chain"),
"number_of_protein_chains", VIEWS_FILTER, false));
- cmb_filterOption.addItem(new FilterOption("Most Bound Molecules",
+ cmb_filterOption.addItem(new FilterOption(
+ MessageManager.getString("label.most_bound_molecules"),
"number_of_bound_molecules", VIEWS_FILTER, false));
- cmb_filterOption.addItem(new FilterOption("Most Polymer Residues",
+ cmb_filterOption.addItem(new FilterOption(
+ MessageManager.getString("label.most_polymer_residues"),
"number_of_polymer_residues", VIEWS_FILTER, true));
}
cmb_filterOption.addItem(
- new FilterOption("Enter PDB Id", "-", VIEWS_ENTER_ID, false));
+ new FilterOption(MessageManager.getString("label.enter_pdb_id"),
+ "-", VIEWS_ENTER_ID, false));
cmb_filterOption.addItem(
- new FilterOption("From File", "-", VIEWS_FROM_FILE, false));
+ new FilterOption(MessageManager.getString("label.from_file"),
+ "-", VIEWS_FROM_FILE, false));
- if (cachedPDBExists)
+ if (cachedPDBExist)
{
- FilterOption cachedOption = new FilterOption("Cached Structures",
+ FilterOption cachedOption = new FilterOption(
+ MessageManager.getString("label.cached_structures"),
"-", VIEWS_LOCAL_PDB, false);
cmb_filterOption.addItem(cachedOption);
cmb_filterOption.setSelectedItem(cachedOption);
protected JInternalFrame mainFrame = new JInternalFrame(frameTitle);
- protected JComboBox<FilterOption> cmb_filterOption = new JComboBox<FilterOption>();
+ protected JComboBox<FilterOption> cmb_filterOption = new JComboBox<>();
protected AlignmentPanel ap;
protected FTSDataColumnI[] previousWantedFields;
- protected static Map<String, Integer> tempUserPrefs = new HashMap<String, Integer>();
+ protected static Map<String, Integer> tempUserPrefs = new HashMap<>();
private JTable tbl_summary = new JTable()
{
chk_rememberSettings.setFont(new java.awt.Font("Verdana", 0, 12));
chk_rememberSettings.setVisible(false);
txt_search.setToolTipText(JvSwingUtils.wrapTooltip(true,
- MessageManager.getString("label.enter_pdb_id")));
+ MessageManager.getString("label.enter_pdb_id_tip")));
cmb_filterOption.setToolTipText(
MessageManager.getString("info.select_filter_option"));
txt_search.getDocument().addDocumentListener(new DocumentListener()
*/
public class AssciateSeqPanel extends JPanel implements ItemListener
{
- private JComboBox<AssociateSeqOptions> cmb_assSeq = new JComboBox<AssociateSeqOptions>();
+ private JComboBox<AssociateSeqOptions> cmb_assSeq = new JComboBox<>();
private JLabel lbl_associateSeq = new JLabel();
sf.setValue("Parent", "transcript:" + accId);
assertTrue(testee.retainFeature(sf, accId));
+ // test is not case-sensitive
+ assertTrue(testee.retainFeature(sf, accId.toLowerCase()));
+
// feature with wrong parent is not retained
sf.setValue("Parent", "transcript:XYZ");
assertFalse(testee.retainFeature(sf, accId));
// NMD_transcript_variant treated like transcript in Ensembl
SequenceFeature sf3 = new SequenceFeature("NMD_transcript_variant", "",
22000, 22500, 0f, null);
- sf3.setValue("Parent", "gene:" + geneId);
+ // id matching should not be case-sensitive
+ sf3.setValue("Parent", "gene:" + geneId.toLowerCase());
sf3.setValue("transcript_id", "transcript3");
genomic.addSequenceFeature(sf3);
sf.setValue("ID", "gene:" + accId);
assertTrue(testee.identifiesSequence(sf, accId));
+ // test is not case-sensitive
+ assertTrue(testee.identifiesSequence(sf, accId.toLowerCase()));
+
// transcript not valid:
sf = new SequenceFeature("transcript", "", 1, 2, 0f, null);
sf.setValue("ID", "gene:" + accId);
PDBEntry dbRef = new PDBEntry();
dbRef.setId("1tim");
- Vector<PDBEntry> pdbIds = new Vector<PDBEntry>();
+ Vector<PDBEntry> pdbIds = new Vector<>();
pdbIds.add(dbRef);
seq.setPDBId(pdbIds);
assertTrue(sc.getCmbFilterOption().getSelectedItem() != null);
FilterOption filterOpt = (FilterOption) sc.getCmbFilterOption()
.getSelectedItem();
- assertEquals("Cached PDB Entries", filterOpt.getName());
+ assertEquals("Cached Structures", filterOpt.getName());
}
@Test(groups = { "Network" })