package jalview.datamodel;
/**
+ * BH 2018 SwingJS note: If additional final static Strings are added to this
+ * file, they should be added to public static final String[] allTypes.
+ *
* Defines internal constants for unambiguous annotation of DbRefEntry source
* strings and describing the data retrieved from external database sources (see
- * jalview.ws.DbSourcProxy)
+ * jalview.ws.DbSourcProxy) <br/>
+ * TODO: replace with ontology to allow recognition of particular attributes
+ * (e.g. protein coding, alignment (ortholog db, paralog db, domain db),
+ * genomic, transcriptomic, 3D structure providing (PDB, MODBASE, etc) ..).
+ *
+ *
*
* @author JimP
*
*/
public class DBRefSource
{
- /**
- * UNIPROT Accession Number
- */
- public static String UNIPROT = "UNIPROT";
-
- /**
- * UNIPROT Entry Name
- */
- public static String UP_NAME = "UNIPROT_NAME".toUpperCase();
-
+
+
+
+ public static final String UNIPROT = "UNIPROT";
+ public static final String UP_NAME = "UNIPROT_NAME".toUpperCase();
/**
* Uniprot Knowledgebase/TrEMBL as served from EMBL protein products.
*/
public static final String UNIPROTKB = "UniProtKB/TrEMBL".toUpperCase();
- public static final String EMBLCDSProduct = "EMBLCDSProtein"
- .toUpperCase();
-
- /**
- * PDB Entry Code
- */
- public static String PDB = "PDB";
-
- /**
- * EMBL ID
- */
- public static String EMBL = "EMBL";
-
- /**
- * EMBLCDS ID
- */
- public static String EMBLCDS = "EMBLCDS";
-
- /**
- * PFAM ID
- */
- public static String PFAM = "PFAM";
-
- /**
- * RFAM ID
- */
- public static String RFAM = "RFAM";
+ public static final String ENSEMBL = "ENSEMBL";
+ public static final String ENSEMBLGENOMES = "ENSEMBLGENOMES";
+
+ public static final String EMBL = "EMBL";
+ public static final String EMBLCDS = "EMBLCDS";
+ public static final String EMBLCDSProduct = "EMBLCDSProtein".toUpperCase();
- /**
- * GeneDB ID
- */
+ public static final String PDB = "PDB";
+ public static final String PFAM = "PFAM";
+ public static final String RFAM = "RFAM";
public static final String GENEDB = "GeneDB".toUpperCase();
- /**
- * List of databases whose sequences might have coding regions annotated
- */
- public static final String[] DNACODINGDBS = { EMBL, EMBLCDS, GENEDB };
-
- public static final String[] CODINGDBS = { EMBLCDS, GENEDB };
-
- public static final String[] PROTEINDBS = { UNIPROT, PDB, UNIPROTKB,
- EMBLCDSProduct };
-
- public static final String[] PROTEINSEQ = { UNIPROT, UNIPROTKB,
- EMBLCDSProduct };
-
- public static final String[] PROTEINSTR = { PDB };
-
- public static final String[] DOMAINDBS = { PFAM, RFAM };
-
- /**
- * set of unique DBRefSource property constants. These could be used to
- * reconstruct the above groupings
- */
- public static final Object SEQDB = "SQ";
-
- /**
- * database of nucleic acid sequences
- */
- public static final Object DNASEQDB = "NASQ";
-
- /**
- * database of amino acid sequences
- */
- public static final Object PROTSEQDB = "PROTSQ";
+ public static final String PDB_CANONICAL_NAME = PDB;
+
+
+ public static final String[] allSources = new String[] {
+ UNIPROT,
+ UP_NAME, UNIPROTKB,
+ ENSEMBL, ENSEMBLGENOMES,
+ EMBL, EMBLCDS, EMBLCDSProduct,
+ PDB, PFAM, RFAM, GENEDB
+ };
+
+ public static final int UNIPROT_MASK = 1<<0;
+ public static final int UP_NAME_MASK = 1<<1;
+ public static final int UNIPROT_KB_MASK = 1<<2;
+ public static final int ENSEMBL_MASK = 1<<3;
+ public static final int ENSEMBL_GENOMES_MASK = 1<<4;
+ public static final int EMBL_MASK = 1<<5;
+ public static final int EMBL_CDS_MASK = 1<<6;
+ public static final int EMBL_CDS_PRODUCT_MASK = 1<<7;
+ public static final int PDB_MASK = 1<<8;
+ public static final int PFAM_MASK = 1<<9;
+ public static final int RFAM_MASK = 1<<10;
+ public static final int GENE_DB_MASK = 1<<11;
+
+ public static final int MASK_COUNT = 12;
+
+ public static final int ALL_MASKS = (1 << MASK_COUNT) - 1;
+
+ public static int getSourceKey(String name) {
+ for (int i = 0; i < MASK_COUNT; i++) {
+ if (name.equals(allSources[i]))
+ {
+ return 1<<i;
+ }
+ }
+ return 0;
+ }
+
+ public static final int PRIMARY_MASK = UNIPROT_MASK | ENSEMBL_MASK;
+
+ /**
+ * List of databases whose sequences might have coding regions annotated
+ */
+ public static final String[] DNACODINGDBS = {
+ ENSEMBL, ENSEMBLGENOMES,
+ EMBL, EMBLCDS, GENEDB
+ };
+
+ public static final int DNA_CODING_MASK =
+ ENSEMBL_MASK | ENSEMBL_GENOMES_MASK
+ | EMBL_MASK | EMBL_CDS_MASK | GENE_DB_MASK;
+
+
+
+ public static final String[] CODINGDBS = { EMBLCDS, GENEDB, ENSEMBL };
+
+ public static final int CODING_MASK = EMBL_CDS_MASK | GENE_DB_MASK | ENSEMBL_MASK;
+
+
+
+ public static final String[] PROTEINDBS = {
+ UNIPROT, UNIPROTKB,
+ ENSEMBL, EMBLCDSProduct }; // Ensembl ENSP* entries are protein
+
+ public static final int PROTEIN_MASK =
+ UNIPROT_MASK | UNIPROT_KB_MASK
+ | ENSEMBL_MASK | EMBL_CDS_PRODUCT_MASK ;
+
+
+ // for SequenceAnnotationReport only
+
+// public static final String[][] PRIMARY_SOURCES = new String[][] {
+// CODINGDBS, DNACODINGDBS, PROTEINDBS };
+//
+ public static final int PRIMARY_SOURCES_MASK = CODING_MASK | DNA_CODING_MASK | PROTEIN_MASK;
+
+ public static boolean isPrimarySource(String source)
+ {
+ return ((PRIMARY_SOURCES_MASK & getSourceKey(source)) != 0);
+ }
+
+ public static boolean isPrimaryCandidate(String ucversion) {
+ // tricky - this test really needs to search the sequence's set of dbrefs to
+ // see if there is a primary reference that derived this reference.
+ for (int i = allSources.length; --i >= 0;)
+ {
+ if (ucversion.startsWith(allSources[i])) // BH 2019.01.25 .toUpperCase() unnecessary here for allSources
+ {
+ // by convention, many secondary references inherit the primary
+ // reference's
+ // source string as a prefix for any version information from the
+ // secondary reference.
+ return false;
+ }
+ }
+ return true;
+}
- /**
- * database of cDNA sequences
- */
- public static final Object CODINGSEQDB = "CODING";
- /**
- * database of na sequences with exon annotation
- */
- public static final Object DNACODINGSEQDB = "XONCODING";
- /**
- * DB returns several sequences associated with a protein/nucleotide domain
- */
- public static final Object DOMAINDB = "DOMAIN";
-
- /**
- * DB query can take multiple accession codes concatenated by a separator.
- * Value of property indicates maximum number of accession codes to send at a
- * time.
- */
- public static final Object MULTIACC = "MULTIACC";
-
- /**
- * DB query returns an alignment for each accession provided.
- */
- public static final Object ALIGNMENTDB = "ALIGNMENTS";
+
}