X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FCrossRef.java;h=95d23964f2f88ca582278e734fe44d37a8a3d59e;hb=ef80b989a1f514d58980401ddefffd2c25299ef7;hp=09f1bc6073714251ce86b1d44f226957b299ed8a;hpb=59d682209891099d46b960509907c79e3fb276fe;p=jalview.git
diff --git a/src/jalview/analysis/CrossRef.java b/src/jalview/analysis/CrossRef.java
index 09f1bc6..95d2396 100644
--- a/src/jalview/analysis/CrossRef.java
+++ b/src/jalview/analysis/CrossRef.java
@@ -1,37 +1,41 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
- * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
+ * 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.
+ * 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 .
+ * 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.analysis;
-import java.util.Enumeration;
-import java.util.List;
-import java.util.Vector;
-import java.util.Hashtable;
-
import jalview.datamodel.AlignedCodonFrame;
import jalview.datamodel.Alignment;
import jalview.datamodel.AlignmentI;
-import jalview.datamodel.DBRefSource;
import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
+import jalview.datamodel.Mapping;
import jalview.datamodel.Sequence;
import jalview.datamodel.SequenceI;
+import jalview.util.DBRefUtils;
import jalview.ws.SequenceFetcher;
import jalview.ws.seqfetcher.ASequenceFetcher;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Vector;
+
/**
* Functions for cross-referencing sequence databases. user must first specify
* if cross-referencing from protein or dna (set dna==true)
@@ -42,39 +46,22 @@ import jalview.ws.seqfetcher.ASequenceFetcher;
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)
}
/**
@@ -101,45 +88,55 @@ public class CrossRef
SequenceI[] seqs, AlignmentI dataset)
{
String[] dbrefs = null;
- Vector refs = new Vector();
- for (int s = 0; s < seqs.length; s++)
+ List refs = new ArrayList();
+ for (SequenceI seq : seqs)
{
- if (seqs[s] != null)
+ if (seq != null)
{
-
- SequenceI dss = seqs[s];
+ SequenceI dss = seq;
while (dss.getDatasetSequence() != null)
{
dss = dss.getDatasetSequence();
}
DBRefEntry[] rfs = findXDbRefs(dna, dss.getDBRef());
- for (int r = 0; rfs != null && r < rfs.length; r++)
+ if (rfs != null)
{
- if (!refs.contains(rfs[r].getSource()))
+ for (DBRefEntry ref : rfs)
{
- refs.addElement(rfs[r].getSource());
+ if (!refs.contains(ref.getSource()))
+ {
+ refs.add(ref.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();
- CrossRef.searchDatasetXrefs(seqs[s], !dna, lrfs, dataset, rseqs,
+ DBRefEntry[] lrfs = CrossRef.findXDbRefs(!dna, seq.getDBRef());
+ List rseqs = new ArrayList();
+ CrossRef.searchDatasetXrefs(seq, !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());
- for (int r = 0; rfs != null && r < rfs.length; r++)
+ if (xrs != null)
{
- if (!refs.contains(rfs[r].getSource()))
+ for (DBRefEntry ref : xrs)
{
- refs.addElement(rfs[r].getSource());
+ if (!refs.contains(ref.getSource()))
+ {
+ refs.add(ref.getSource());
+ }
}
}
+ // looks like copy and paste - change rfs to xrs?
+ // for (int r = 0; rfs != null && r < rfs.length; r++)
+ // {
+ // if (!refs.contains(rfs[r].getSource()))
+ // {
+ // refs.add(rfs[r].getSource());
+ // }
+ // }
}
}
}
@@ -147,18 +144,14 @@ public class CrossRef
if (refs.size() > 0)
{
dbrefs = new String[refs.size()];
- refs.copyInto(dbrefs);
+ refs.toArray(dbrefs);
}
return dbrefs;
}
- /*
- * if (dna) { if (rfs[r].hasMap()) { // most likely this is a protein cross
- * reference if (!refs.contains(rfs[r].getSource())) {
- * refs.addElement(rfs[r].getSource()); } } }
- */
public static boolean hasCdnaMap(SequenceI[] seqs)
{
+ // TODO unused - remove?
String[] reftypes = findSequenceXrefTypes(false, seqs);
for (int s = 0; s < reftypes.length; s++)
{
@@ -173,6 +166,7 @@ public class CrossRef
public static SequenceI[] getCdnaMap(SequenceI[] seqs)
{
+ // TODO unused - remove?
Vector cseqs = new Vector();
for (int s = 0; s < seqs.length; s++)
{
@@ -216,7 +210,9 @@ public class CrossRef
/**
*
* @param seqs
+ * sequences whose xrefs are being retrieved
* @param dna
+ * true if sequences are nucleotide
* @param source
* @param dataset
* alignment to search for product sequences.
@@ -225,12 +221,11 @@ public class CrossRef
public static Alignment findXrefSequences(SequenceI[] seqs, boolean dna,
String source, AlignmentI dataset)
{
- Vector rseqs = new Vector();
- Alignment ral = null;
- AlignedCodonFrame cf = new AlignedCodonFrame(0); // nominal width
- for (int s = 0; s < seqs.length; s++)
+ List rseqs = new ArrayList();
+ AlignedCodonFrame cf = new AlignedCodonFrame();
+ for (SequenceI seq : seqs)
{
- SequenceI dss = seqs[s];
+ SequenceI dss = seq;
while (dss.getDatasetSequence() != null)
{
dss = dss.getDatasetSequence();
@@ -240,14 +235,9 @@ public class CrossRef
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.
+ // FIXME should be dss not seq here?
+ DBRefEntry[] lrfs = CrossRef.findXDbRefs(!dna, seq.getDBRef());
+ // less ambiguous would be a 'find primary dbRefEntry' method.
// filter for desired source xref here
found = CrossRef.searchDatasetXrefs(dss, !dna, lrfs, dataset,
rseqs, cf);
@@ -255,13 +245,15 @@ public class CrossRef
for (int r = 0; xrfs != null && r < xrfs.length; r++)
{
if (source != null && !source.equals(xrfs[r].getSource()))
+ {
continue;
+ }
if (xrfs[r].hasMap())
{
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())
{
@@ -288,7 +280,9 @@ public class CrossRef
{
found |= searchDataset(dss, xrfs[r], dataset, rseqs, cf); // ,false,!dna);
if (found)
+ {
xrfs[r] = null; // we've recovered seqs for this one.
+ }
}
}
}
@@ -325,7 +319,9 @@ public class CrossRef
for (int r = 0; r < xrfs.length; r++)
{
if (xrfs[r] != null)
+ {
t[l++] = xrfs[r];
+ }
}
xrfs = t;
try
@@ -338,7 +334,7 @@ public class CrossRef
{
System.err
.println("Problem whilst retrieving cross references for Sequence : "
- + seqs[s].getName());
+ + seq.getName());
e.printStackTrace();
}
if (retrieved != null)
@@ -346,15 +342,14 @@ public class CrossRef
for (int rs = 0; rs < retrieved.length; rs++)
{
// TODO: examine each sequence for 'redundancy'
- jalview.datamodel.DBRefEntry[] dbr = retrieved[rs]
- .getDBRef();
+ DBRefEntry[] dbr = retrieved[rs].getDBRef();
if (dbr != null && dbr.length > 0)
{
for (int di = 0; di < dbr.length; di++)
{
// find any entry where we should put in the sequence being
// cross-referenced into the map
- jalview.datamodel.Mapping map = dbr[di].getMap();
+ Mapping map = dbr[di].getMap();
if (map != null)
{
if (map.getTo() != null && map.getMap() != null)
@@ -392,17 +387,19 @@ public class CrossRef
}
}
retrieved[rs].updatePDBIds();
- rseqs.addElement(retrieved[rs]);
+ rseqs.add(retrieved[rs]);
}
}
}
}
}
}
+
+ Alignment ral = null;
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)
{
@@ -424,12 +421,14 @@ public class CrossRef
* @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 rseqs, AlignedCodonFrame cf)
{
boolean found = false;
if (lrfs == null)
+ {
return false;
+ }
for (int i = 0; i < lrfs.length; i++)
{
DBRefEntry xref = new DBRefEntry(lrfs[i]);
@@ -454,7 +453,7 @@ public class CrossRef
* @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 rseqs, AlignedCodonFrame cf)
{
return searchDataset(sequenceI, xrf, dataset, rseqs, cf, true, false);
}
@@ -475,13 +474,15 @@ public class CrossRef
* @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 rseqs, AlignedCodonFrame cf,
boolean direct, boolean dna)
{
boolean found = false;
SequenceI[] typer = new SequenceI[1];
if (dataset == null)
+ {
return false;
+ }
if (dataset.getSequences() == null)
{
System.err.println("Empty dataset sequence set - NO VECTOR");
@@ -491,6 +492,7 @@ public class CrossRef
synchronized (ds = dataset.getSequences())
{
for (SequenceI nxt : ds)
+ {
if (nxt != null)
{
if (nxt.getDatasetSequence() != null)
@@ -526,10 +528,9 @@ public class CrossRef
{
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())
@@ -563,6 +564,7 @@ public class CrossRef
}
}
+ }
}
return found;
}