X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblCdna.java;h=f60125b94b97bdef9237ed8a57e017a463680d52;hb=ef9282b464dc189faf9ce40a4b7420a204266668;hp=0a9742536236ea97f7c6399a00b6a0fe40b22509;hpb=0b8abe58b934e03c34575b06d532a99f0ba70196;p=jalview.git diff --git a/src/jalview/ext/ensembl/EnsemblCdna.java b/src/jalview/ext/ensembl/EnsemblCdna.java index 0a97425..f60125b 100644 --- a/src/jalview/ext/ensembl/EnsemblCdna.java +++ b/src/jalview/ext/ensembl/EnsemblCdna.java @@ -1,14 +1,21 @@ package jalview.ext.ensembl; import jalview.datamodel.SequenceFeature; -import jalview.io.gff.SequenceOntology; +import jalview.io.gff.SequenceOntologyFactory; +import jalview.io.gff.SequenceOntologyI; + +import java.util.List; import com.stevesoft.pat.Regex; public class EnsemblCdna extends EnsemblSeqProxy { + // TODO modify to accept other species e.g. ENSMUSPnnn + private static final Regex ACCESSION_REGEX = new Regex( + "(ENST|ENSG|CCDS)[0-9.]{3,}$"); + /* - * fetch exon features on genomic sequence (to identify the cdnaregions) + * 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 = { @@ -35,7 +42,7 @@ public class EnsemblCdna extends EnsemblSeqProxy @Override public Regex getAccessionValidator() { - return new Regex("((ENST|ENSG|CCDS)[0-9.]{3,})"); + return ACCESSION_REGEX; } @Override @@ -45,18 +52,13 @@ public class EnsemblCdna extends EnsemblSeqProxy } /** - * Answers true unless the feature type is 'transcript' or 'exon' (or a - * sub-type in the Sequence Ontology). These features are only retrieved in - * order to identify the exon sequence loci, and are redundant information on - * the exon sequence itself. + * Answers true unless the feature type is 'transcript' (or a sub-type in the + * Sequence Ontology). */ @Override protected boolean retainFeature(SequenceFeature sf, String accessionId) { - SequenceOntology so = SequenceOntology.getInstance(); - String type = sf.getType(); - - if (isTranscript(type) || so.isA(type, SequenceOntology.EXON)) + if (isTranscript(sf.getType())) { return false; } @@ -71,8 +73,8 @@ public class EnsemblCdna extends EnsemblSeqProxy @Override protected boolean identifiesSequence(SequenceFeature sf, String accId) { - if (SequenceOntology.getInstance().isA(sf.getType(), - SequenceOntology.EXON)) + if (SequenceOntologyFactory.getInstance().isA(sf.getType(), + SequenceOntologyI.EXON)) { String parentFeature = (String) sf.getValue(PARENT); if (("transcript:" + accId).equals(parentFeature)) @@ -83,4 +85,12 @@ public class EnsemblCdna extends EnsemblSeqProxy return false; } + @Override + protected List getCrossReferenceDatabases() + { + return super.getCrossReferenceDatabases(); + // 30/01/16 also found Vega_transcript, OTTT, ENS_LRG_transcript, UCSC, + // HGNC_trans_name, RefSeq_mRNA, RefSeq_mRNA_predicted + } + }