X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FCrossRef.java;h=1a56393de39cce9c3423ba8e1bdf99008f454862;hb=3d0101179759ef157b088ea135423cd909512d9f;hp=cd71bbd20c703be438bb95d6e2fb32b5bad328c6;hpb=0463fb03eb6a32ce4d39ab7c146b82549c5a5e0e;p=jalview.git diff --git a/src/jalview/analysis/CrossRef.java b/src/jalview/analysis/CrossRef.java index cd71bbd..1a56393 100644 --- a/src/jalview/analysis/CrossRef.java +++ b/src/jalview/analysis/CrossRef.java @@ -164,8 +164,8 @@ public class CrossRef */ for (SequenceI rs : foundSeqs) { - DBRefEntry[] xrs = DBRefUtils - .selectDbRefs(!fromDna, rs.getDBRefs()); + DBRefEntry[] xrs = DBRefUtils.selectDbRefs(!fromDna, + rs.getDBRefs()); addXrefsToSources(xrs, sources); } } @@ -220,8 +220,7 @@ public class CrossRef rseqs = new ArrayList(); AlignedCodonFrame cf = new AlignedCodonFrame(); - matcher = new SequenceIdMatcher( - dataset.getSequences()); + matcher = new SequenceIdMatcher(dataset.getSequences()); for (SequenceI seq : fromSeqs) { @@ -231,8 +230,8 @@ public class CrossRef dss = dss.getDatasetSequence(); } boolean found = false; - DBRefEntry[] xrfs = DBRefUtils - .selectDbRefs(!fromDna, dss.getDBRefs()); + DBRefEntry[] xrfs = DBRefUtils.selectDbRefs(!fromDna, + dss.getDBRefs()); // ENST & ENSP comes in to both Protein and nucleotide, so we need to // filter them // out later. @@ -292,13 +291,10 @@ public class CrossRef if (matchInDataset != null && xref.getMap().getTo() != null && matchInDataset != xref.getMap().getTo()) { - System.err - .println("Implementation problem (reopen JAL-2154): CrossRef.findInDataset seems to have recovered a different sequence than the one explicitly mapped for xref." - + "Found:" - + matchInDataset - + "\nExpected:" - + xref.getMap().getTo() - + "\nFor xref:" + System.err.println( + "Implementation problem (reopen JAL-2154): CrossRef.findInDataset seems to have recovered a different sequence than the one explicitly mapped for xref." + + "Found:" + matchInDataset + "\nExpected:" + + xref.getMap().getTo() + "\nFor xref:" + xref); } /*matcher.findIdMatch(mappedTo);*/ @@ -324,8 +320,9 @@ public class CrossRef } else { - cf.addMap(matchInDataset, dss, xref.getMap().getMap() - .getInverse(), xref.getMap().getMappedFromId()); + cf.addMap(matchInDataset, dss, + xref.getMap().getMap().getInverse(), + xref.getMap().getMappedFromId()); } } @@ -341,8 +338,8 @@ public class CrossRef if (fromDna) { // map is from dna seq to a protein product - cf.addMap(dss, rsq, xref.getMap().getMap(), xref.getMap() - .getMappedFromId()); + cf.addMap(dss, rsq, xref.getMap().getMap(), + xref.getMap().getMappedFromId()); } else { @@ -356,8 +353,8 @@ public class CrossRef if (!found) { - SequenceI matchedSeq = matcher.findIdMatch(xref.getSource() + "|" - + xref.getAccessionId()); + SequenceI matchedSeq = matcher.findIdMatch( + xref.getSource() + "|" + xref.getAccessionId()); // if there was a match, check it's at least the right type of // molecule! if (matchedSeq != null && matchedSeq.isProtein() == fromDna) @@ -407,8 +404,8 @@ public class CrossRef { ASequenceFetcher sftch = SequenceFetcherFactory.getSequenceFetcher(); SequenceI[] retrieved = null; - SequenceI dss = seq.getDatasetSequence() == null ? seq : seq - .getDatasetSequence(); + SequenceI dss = seq.getDatasetSequence() == null ? seq + : seq.getDatasetSequence(); // first filter in case we are retrieving crossrefs that have already been // retrieved. this happens for cases where a database record doesn't yield // protein products for CDS @@ -424,8 +421,8 @@ public class CrossRef retrieved = sftch.getSequences(sourceRefs, !fromDna); } catch (Exception e) { - System.err - .println("Problem whilst retrieving cross references for Sequence : " + System.err.println( + "Problem whilst retrieving cross references for Sequence : " + seq.getName()); e.printStackTrace(); } @@ -433,14 +430,16 @@ public class CrossRef if (retrieved != null) { boolean addedXref = false; - List newDsSeqs = new ArrayList(), doNotAdd = new ArrayList(); + List newDsSeqs = new ArrayList(), + doNotAdd = new ArrayList(); for (SequenceI retrievedSequence : retrieved) { // dataset gets contaminated ccwith non-ds sequences. why ??! // try: Ensembl -> Nuc->Ensembl, Nuc->Uniprot-->Protein->EMBL-> - SequenceI retrievedDss = retrievedSequence.getDatasetSequence() == null ? retrievedSequence - : retrievedSequence.getDatasetSequence(); + SequenceI retrievedDss = retrievedSequence + .getDatasetSequence() == null ? retrievedSequence + : retrievedSequence.getDatasetSequence(); addedXref |= importCrossRefSeq(cf, newDsSeqs, doNotAdd, dss, retrievedDss); } @@ -453,8 +452,9 @@ public class CrossRef { // dataset gets contaminated ccwith non-ds sequences. why ??! // try: Ensembl -> Nuc->Ensembl, Nuc->Uniprot-->Protein->EMBL-> - SequenceI retrievedDss = retrievedSequence.getDatasetSequence() == null ? retrievedSequence - : retrievedSequence.getDatasetSequence(); + SequenceI retrievedDss = retrievedSequence + .getDatasetSequence() == null ? retrievedSequence + : retrievedSequence.getDatasetSequence(); addedXref |= importCrossRefSeq(cf, newDsSeqs, doNotAdd, dss, retrievedDss); } @@ -578,9 +578,8 @@ public class CrossRef int sf = map.getMap().getToLowest(); int st = map.getMap().getToHighest(); SequenceI mappedrg = ms.getSubSequence(sf, st); - if (mappedrg.getLength() > 0 - && ms.getSequenceAsString().equals( - matched.getSequenceAsString())) + if (mappedrg.getLength() > 0 && ms.getSequenceAsString() + .equals(matched.getSequenceAsString())) { /* * sequences were a match, @@ -598,8 +597,8 @@ public class CrossRef */ for (DBRefEntry ref : toRefs) { - if (dbref.getSrcAccString().equals( - ref.getSrcAccString())) + if (dbref.getSrcAccString() + .equals(ref.getSrcAccString())) { continue; // avoid overwriting the ref on source sequence } @@ -630,8 +629,7 @@ public class CrossRef * attribute in equality test; this avoids creating many * otherwise duplicate exon features on genomic sequence */ - SequenceFeature newFeature = new SequenceFeature( - feat) + SequenceFeature newFeature = new SequenceFeature(feat) { @Override public boolean equals(Object o) @@ -647,8 +645,8 @@ public class CrossRef cf.addMap(retrievedSequence, map.getTo(), map.getMap()); } catch (Exception e) { - System.err - .println("Exception when consolidating Mapped sequence set..."); + System.err.println( + "Exception when consolidating Mapped sequence set..."); e.printStackTrace(System.err); } } @@ -667,6 +665,7 @@ public class CrossRef } return imported; } + /** * Sets the inverse sequence mapping in the corresponding dbref of the mapped * to sequence (if any). This is used after fetching a cross-referenced @@ -726,8 +725,8 @@ public class CrossRef SequenceI mapsTo = xref.getMap().getTo(); String name = xref.getAccessionId(); String name2 = xref.getSource() + "|" + name; - SequenceI dss = mapsTo.getDatasetSequence() == null ? mapsTo : mapsTo - .getDatasetSequence(); + SequenceI dss = mapsTo.getDatasetSequence() == null ? mapsTo + : mapsTo.getDatasetSequence(); // first check ds if ds is directly referenced if (dataset.findIndex(dss) > -1) { @@ -742,8 +741,8 @@ public class CrossRef for (SequenceI seq : dataset.getSequences()) { // first check primary refs. - List match = DBRefUtils.searchRefs(seq.getPrimaryDBRefs() - .toArray(new DBRefEntry[0]), template); + List match = DBRefUtils.searchRefs( + seq.getPrimaryDBRefs().toArray(new DBRefEntry[0]), template); if (match != null && match.size() == 1 && sameSequence(seq, dss)) { return seq; @@ -753,9 +752,8 @@ public class CrossRef * returns sequences with a dbref to the matched accession id * which we don't want */ - if (firstIdMatch == null - && (name.equals(seq.getName()) || seq.getName().startsWith( - name2))) + if (firstIdMatch == null && (name.equals(seq.getName()) + || seq.getName().startsWith(name2))) { if (sameSequence(seq, dss)) { @@ -951,7 +949,8 @@ public class CrossRef * @return true if matches were found. */ private boolean searchDatasetXrefs(boolean fromDna, SequenceI sequenceI, - DBRefEntry[] lrfs, List foundSeqs, AlignedCodonFrame cf) + DBRefEntry[] lrfs, List foundSeqs, + AlignedCodonFrame cf) { boolean found = false; if (lrfs == null) @@ -964,7 +963,8 @@ public class CrossRef // add in wildcards xref.setVersion(null); xref.setMap(null); - found |= searchDataset(fromDna, sequenceI, xref, foundSeqs, cf, false); + found |= searchDataset(fromDna, sequenceI, xref, foundSeqs, cf, + false); } return found; } @@ -1020,10 +1020,9 @@ public class CrossRef { if (nxt.getDatasetSequence() != null) { - System.err - .println("Implementation warning: CrossRef initialised with a dataset alignment with non-dataset sequences in it! (" - + nxt.getDisplayId(true) - + " has ds reference " + System.err.println( + "Implementation warning: CrossRef initialised with a dataset alignment with non-dataset sequences in it! (" + + nxt.getDisplayId(true) + " has ds reference " + nxt.getDatasetSequence().getDisplayId(true) + ")"); }