X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblCdna.java;h=952f01e9fb57cbfddd4f0b2ac46fbdc090fa6dfe;hb=f9aad5b4cbba002593a7d7f5ba7079e8637ba006;hp=373286fb9f323d3ceaf819dbb9fd7df1d466d2f2;hpb=3cccac4697c371b1964236e17b532fd3d180e1c4;p=jalview.git
diff --git a/src/jalview/ext/ensembl/EnsemblCdna.java b/src/jalview/ext/ensembl/EnsemblCdna.java
index 373286f..952f01e 100644
--- a/src/jalview/ext/ensembl/EnsemblCdna.java
+++ b/src/jalview/ext/ensembl/EnsemblCdna.java
@@ -1,28 +1,75 @@
+/*
+ * 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 .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
import jalview.datamodel.SequenceFeature;
import jalview.io.gff.SequenceOntologyFactory;
import jalview.io.gff.SequenceOntologyI;
-import java.util.List;
-
import com.stevesoft.pat.Regex;
+/**
+ * A client to fetch CDNA sequence from Ensembl (i.e. that part of the genomic
+ * sequence that is transcribed to RNA, but not necessarily translated to
+ * protein)
+ *
+ * @author gmcarstairs
+ *
+ */
public class EnsemblCdna extends EnsemblSeqProxy
{
/*
- * fetch exon features on genomic sequence (to identify the cdnaregions)
+ * accepts ENST or ENSTG with 11 digits
+ * or ENSMUST or similar for other species
+ * or CCDSnnnnn.nn with at least 3 digits
+ */
+ private static final Regex ACCESSION_REGEX = new Regex(
+ "(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
+
+ /*
+ * fetch exon features on genomic sequence (to identify the cdna regions)
* and cds and variation features (to retain)
*/
private static final EnsemblFeatureType[] FEATURES_TO_FETCH = {
EnsemblFeatureType.exon, EnsemblFeatureType.cds,
EnsemblFeatureType.variation };
+ /**
+ * Default constructor (to use rest.ensembl.org)
+ */
public EnsemblCdna()
{
super();
}
+ /**
+ * Constructor given the target domain to fetch data from
+ *
+ * @param d
+ */
+ public EnsemblCdna(String d)
+ {
+ super(d);
+ }
+
@Override
public String getDbName()
{
@@ -38,7 +85,7 @@ public class EnsemblCdna extends EnsemblSeqProxy
@Override
public Regex getAccessionValidator()
{
- return new Regex("((ENST|ENSG|CCDS)[0-9.]{3,})");
+ return ACCESSION_REGEX;
}
@Override
@@ -81,12 +128,14 @@ public class EnsemblCdna extends EnsemblSeqProxy
return false;
}
+ /**
+ * Parameter object_type=Transcaript added to ensure cdna and not peptide is
+ * returned (JAL-2529)
+ */
@Override
- protected List getCrossReferenceDatabases()
+ protected String getObjectType()
{
- return super.getCrossReferenceDatabases();
- // 30/01/16 also found Vega_transcript, OTTT, ENS_LRG_transcript, UCSC,
- // HGNC_trans_name, RefSeq_mRNA, RefSeq_mRNA_predicted
+ return OBJECT_TYPE_TRANSCRIPT;
}
}