import jalview.datamodel.DBRefSource;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceI;
+import jalview.util.DBRefUtils;
import jalview.ws.SequenceFetcher;
import jalview.ws.seqfetcher.ASequenceFetcher;
-import java.util.Enumeration;
-import java.util.Hashtable;
+import java.util.ArrayList;
import java.util.List;
import java.util.Vector;
public class CrossRef
{
/**
- * get the DNA or protein references for a protein or dna sequence
+ * Select just the DNA or protein references for a protein or dna sequence
*
- * @param dna
- * @param rfs
+ * @param fromDna
+ * if true, select references from DNA (i.e. Protein databases), else
+ * DNA database references
+ * @param refs
+ * a set of references to select from
* @return
*/
- public static DBRefEntry[] findXDbRefs(boolean dna, DBRefEntry[] rfs)
- {
- if (dna)
- {
- rfs = jalview.util.DBRefUtils.selectRefs(rfs, DBRefSource.PROTEINDBS);
- }
- else
- {
- rfs = jalview.util.DBRefUtils.selectRefs(rfs,
- DBRefSource.DNACODINGDBS); // could attempt to find other cross
- // refs and return here - ie PDB xrefs
- // (not dna, not protein seq)
- }
- return rfs;
- }
-
- public static Hashtable classifyDbRefs(DBRefEntry[] rfs)
+ public static DBRefEntry[] findXDbRefs(boolean fromDna, DBRefEntry[] refs)
{
- Hashtable classes = new Hashtable();
- classes.put(DBRefSource.PROTEINDBS,
- jalview.util.DBRefUtils.selectRefs(rfs, DBRefSource.PROTEINDBS));
- classes.put(DBRefSource.DNACODINGDBS, jalview.util.DBRefUtils
- .selectRefs(rfs, DBRefSource.DNACODINGDBS));
- classes.put(DBRefSource.DOMAINDBS,
- jalview.util.DBRefUtils.selectRefs(rfs, DBRefSource.DOMAINDBS));
- // classes.put(OTHER, )
- return classes;
+ return DBRefUtils.selectRefs(refs, fromDna ? DBRefSource.PROTEINDBS
+ : DBRefSource.DNACODINGDBS);
+ // could attempt to find other cross
+ // refs here - ie PDB xrefs
+ // (not dna, not protein seq)
}
/**
SequenceI[] seqs, AlignmentI dataset)
{
String[] dbrefs = null;
- Vector refs = new Vector();
+ List<String> refs = new ArrayList<String>();
for (int s = 0; s < seqs.length; s++)
{
if (seqs[s] != null)
{
-
SequenceI dss = seqs[s];
while (dss.getDatasetSequence() != null)
{
dss = dss.getDatasetSequence();
}
- DBRefEntry[] rfs = findXDbRefs(dna, dss.getDBRef());
+ DBRefEntry[] rfs = findXDbRefs(dna, dss.getDBRefs());
for (int r = 0; rfs != null && r < rfs.length; r++)
{
if (!refs.contains(rfs[r].getSource()))
{
- refs.addElement(rfs[r].getSource());
+ refs.add(rfs[r].getSource());
}
}
if (dataset != null)
{
// search for references to this sequence's direct references.
DBRefEntry[] lrfs = CrossRef
- .findXDbRefs(!dna, seqs[s].getDBRef());
- Vector rseqs = new Vector();
+ .findXDbRefs(!dna, seqs[s].getDBRefs());
+ List<SequenceI> rseqs = new ArrayList<SequenceI>();
CrossRef.searchDatasetXrefs(seqs[s], !dna, lrfs, dataset, rseqs,
null); // don't need to specify codon frame for mapping here
- Enumeration lr = rseqs.elements();
- while (lr.hasMoreElements())
+ for (SequenceI rs : rseqs)
{
- SequenceI rs = (SequenceI) lr.nextElement();
- DBRefEntry[] xrs = findXDbRefs(dna, rs.getDBRef());
+ DBRefEntry[] xrs = findXDbRefs(dna, rs.getDBRefs()); // not used??
for (int r = 0; rfs != null && r < rfs.length; r++)
{
if (!refs.contains(rfs[r].getSource()))
{
- refs.addElement(rfs[r].getSource());
+ refs.add(rfs[r].getSource());
}
}
}
if (refs.size() > 0)
{
dbrefs = new String[refs.size()];
- refs.copyInto(dbrefs);
+ refs.toArray(dbrefs);
}
return dbrefs;
}
Vector cseqs = new Vector();
for (int s = 0; s < seqs.length; s++)
{
- DBRefEntry[] cdna = findXDbRefs(true, seqs[s].getDBRef());
+ DBRefEntry[] cdna = findXDbRefs(true, seqs[s].getDBRefs());
for (int c = 0; c < cdna.length; c++)
{
if (cdna[c].getSource().equals(DBRefSource.EMBLCDS))
public static Alignment findXrefSequences(SequenceI[] seqs, boolean dna,
String source, AlignmentI dataset)
{
- Vector rseqs = new Vector();
+ List<SequenceI> rseqs = new ArrayList<SequenceI>();
Alignment ral = null;
AlignedCodonFrame cf = new AlignedCodonFrame(); // nominal width
for (int s = 0; s < seqs.length; s++)
dss = dss.getDatasetSequence();
}
boolean found = false;
- DBRefEntry[] xrfs = CrossRef.findXDbRefs(dna, dss.getDBRef());
+ DBRefEntry[] xrfs = CrossRef.findXDbRefs(dna, dss.getDBRefs());
if ((xrfs == null || xrfs.length == 0) && dataset != null)
{
System.out.println("Attempting to find ds Xrefs refs.");
- DBRefEntry[] lrfs = CrossRef.findXDbRefs(!dna, seqs[s].getDBRef()); // less
- // ambiguous
- // would
- // be a
- // 'find
- // primary
- // dbRefEntry'
- // method.
+ DBRefEntry[] lrfs = CrossRef.findXDbRefs(!dna, seqs[s].getDBRefs());
+ // less ambiguous would be a 'find primary dbRefEntry' method.
// filter for desired source xref here
found = CrossRef.searchDatasetXrefs(dss, !dna, lrfs, dataset,
rseqs, cf);
{
if (xrfs[r].getMap().getTo() != null)
{
- Sequence rsq = new Sequence(xrfs[r].getMap().getTo());
- rseqs.addElement(rsq);
+ SequenceI rsq = new Sequence(xrfs[r].getMap().getTo());
+ rseqs.add(rsq);
if (xrfs[r].getMap().getMap().getFromRatio() != xrfs[r]
.getMap().getMap().getToRatio())
{
{
found |= searchDataset(dss, xrfs[r], dataset, rseqs, cf); // ,false,!dna);
if (found)
- {
+ {
xrfs[r] = null; // we've recovered seqs for this one.
}
}
{
// TODO: examine each sequence for 'redundancy'
jalview.datamodel.DBRefEntry[] dbr = retrieved[rs]
- .getDBRef();
+ .getDBRefs();
if (dbr != null && dbr.length > 0)
{
for (int di = 0; di < dbr.length; di++)
}
}
retrieved[rs].updatePDBIds();
- rseqs.addElement(retrieved[rs]);
+ rseqs.add(retrieved[rs]);
}
}
}
if (rseqs.size() > 0)
{
SequenceI[] rsqs = new SequenceI[rseqs.size()];
- rseqs.copyInto(rsqs);
+ rseqs.toArray(rsqs);
ral = new Alignment(rsqs);
if (cf != null && cf.getProtMappings() != null)
{
* @return true if matches were found.
*/
private static boolean searchDatasetXrefs(SequenceI sequenceI,
- boolean dna, DBRefEntry[] lrfs, AlignmentI dataset, Vector rseqs,
- AlignedCodonFrame cf)
+ boolean dna, DBRefEntry[] lrfs, AlignmentI dataset,
+ List<SequenceI> rseqs, AlignedCodonFrame cf)
{
boolean found = false;
if (lrfs == null)
* @return true if one or more unique sequences were found and added
*/
public static boolean searchDataset(SequenceI sequenceI, DBRefEntry xrf,
- AlignmentI dataset, Vector rseqs, AlignedCodonFrame cf)
+ AlignmentI dataset, List<SequenceI> rseqs, AlignedCodonFrame cf)
{
return searchDataset(sequenceI, xrf, dataset, rseqs, cf, true, false);
}
* @return true if relationship found and sequence added.
*/
public static boolean searchDataset(SequenceI sequenceI, DBRefEntry xrf,
- AlignmentI dataset, Vector rseqs, AlignedCodonFrame cf,
+ AlignmentI dataset, List<SequenceI> rseqs, AlignedCodonFrame cf,
boolean direct, boolean dna)
{
boolean found = false;
}
// look for direct or indirect references in common
- DBRefEntry[] poss = nxt.getDBRef(), cands = null;
+ DBRefEntry[] poss = nxt.getDBRefs(), cands = null;
if (direct)
{
cands = jalview.util.DBRefUtils.searchRefs(poss, xrf);
{
if (!rseqs.contains(nxt))
{
- rseqs.addElement(nxt);
- boolean foundmap = cf != null; // don't search if we aren't
- // given
- // a codon map object
+ rseqs.add(nxt);
+ boolean foundmap = cf != null;
+ // don't search if we aren't given a codon map object
for (int r = 0; foundmap && r < cands.length; r++)
{
if (cands[r].hasMap())