X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FAlignmentUtils.java;h=fdc74e2fed6f1f8cf4ba65a040c99374255163c0;hb=57738a1f3c19b1c3a00bd3ac5108f8cd0af32f99;hp=4cd1fc497b0ad3b4bf180647b9d9c6ca79254dea;hpb=0b573ed90b14079f7326281f50c0c9cffdace586;p=jalview.git diff --git a/src/jalview/analysis/AlignmentUtils.java b/src/jalview/analysis/AlignmentUtils.java index 4cd1fc4..fdc74e2 100644 --- a/src/jalview/analysis/AlignmentUtils.java +++ b/src/jalview/analysis/AlignmentUtils.java @@ -20,6 +20,25 @@ */ package jalview.analysis; +import java.util.Locale; + +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collection; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Iterator; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; +import java.util.NoSuchElementException; +import java.util.Set; +import java.util.SortedMap; +import java.util.TreeMap; + +import jalview.bin.Console; import jalview.commands.RemoveGapColCommand; import jalview.datamodel.AlignedCodon; import jalview.datamodel.AlignedCodonFrame; @@ -44,22 +63,6 @@ import jalview.util.IntRangeComparator; import jalview.util.MapList; import jalview.util.MappingUtils; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.Collection; -import java.util.Collections; -import java.util.HashMap; -import java.util.HashSet; -import java.util.Iterator; -import java.util.LinkedHashMap; -import java.util.List; -import java.util.Map; -import java.util.Map.Entry; -import java.util.NoSuchElementException; -import java.util.Set; -import java.util.SortedMap; -import java.util.TreeMap; - /** * grab bag of useful alignment manipulation operations Expect these to be * refactored elsewhere at some point. @@ -181,10 +184,10 @@ public class AlignmentUtils // TODO use Character.toLowerCase to avoid creating String objects? char[] upstream = new String(ds .getSequence(s.getStart() - 1 - ustream_ds, s.getStart() - 1)) - .toLowerCase().toCharArray(); + .toLowerCase(Locale.ROOT).toCharArray(); char[] downstream = new String( - ds.getSequence(s_end - 1, s_end + dstream_ds)).toLowerCase() - .toCharArray(); + ds.getSequence(s_end - 1, s_end + dstream_ds)) + .toLowerCase(Locale.ROOT).toCharArray(); char[] coreseq = s.getSequence(); char[] nseq = new char[offset + upstream.length + downstream.length + coreseq.length]; @@ -462,7 +465,8 @@ public class AlignmentUtils if (cdnaLength != mappedLength && cdnaLength > 2) { String lastCodon = String.valueOf(cdnaSeqChars, - cdnaLength - CODON_LENGTH, CODON_LENGTH).toUpperCase(); + cdnaLength - CODON_LENGTH, CODON_LENGTH) + .toUpperCase(Locale.ROOT); for (String stop : ResidueProperties.STOP_CODONS) { if (lastCodon.equals(stop)) @@ -479,7 +483,8 @@ public class AlignmentUtils */ int startOffset = 0; if (cdnaLength != mappedLength && cdnaLength > 2 - && String.valueOf(cdnaSeqChars, 0, CODON_LENGTH).toUpperCase() + && String.valueOf(cdnaSeqChars, 0, CODON_LENGTH) + .toUpperCase(Locale.ROOT) .equals(ResidueProperties.START)) { startOffset += CODON_LENGTH; @@ -973,8 +978,8 @@ public class AlignmentUtils mapList = mapList.getInverse(); } final int cdsLength = cdsDss.getLength(); - int mappedFromLength = MappingUtils.getLength(mapList - .getFromRanges()); + int mappedFromLength = MappingUtils + .getLength(mapList.getFromRanges()); int mappedToLength = MappingUtils .getLength(mapList.getToRanges()); boolean addStopCodon = (cdsLength == mappedFromLength @@ -1648,8 +1653,8 @@ public class AlignmentUtils productSeqs = new HashSet<>(); for (SequenceI seq : products) { - productSeqs.add(seq.getDatasetSequence() == null ? seq : seq - .getDatasetSequence()); + productSeqs.add(seq.getDatasetSequence() == null ? seq + : seq.getDatasetSequence()); } } @@ -1732,15 +1737,8 @@ public class AlignmentUtils cdsSeqs.add(cdsSeq); - if (!dataset.getSequences().contains(cdsSeqDss)) - { - // check if this sequence is a newly created one - // so needs adding to the dataset - dataset.addSequence(cdsSeqDss); - } - /* - * add a mapping from CDS to the (unchanged) mapped to range + * build the mapping from CDS to protein */ List cdsRange = Collections .singletonList(new int[] @@ -1749,16 +1747,26 @@ public class AlignmentUtils MapList cdsToProteinMap = new MapList(cdsRange, mapList.getToRanges(), mapList.getFromRatio(), mapList.getToRatio()); - AlignedCodonFrame cdsToProteinMapping = new AlignedCodonFrame(); - cdsToProteinMapping.addMap(cdsSeqDss, proteinProduct, - cdsToProteinMap); - /* - * guard against duplicating the mapping if repeating this action - */ - if (!mappings.contains(cdsToProteinMapping)) + if (!dataset.getSequences().contains(cdsSeqDss)) { - mappings.add(cdsToProteinMapping); + /* + * if this sequence is a newly created one, add it to the dataset + * and made a CDS to protein mapping (if sequence already exists, + * CDS-to-protein mapping _is_ the transcript-to-protein mapping) + */ + dataset.addSequence(cdsSeqDss); + AlignedCodonFrame cdsToProteinMapping = new AlignedCodonFrame(); + cdsToProteinMapping.addMap(cdsSeqDss, proteinProduct, + cdsToProteinMap); + + /* + * guard against duplicating the mapping if repeating this action + */ + if (!mappings.contains(cdsToProteinMapping)) + { + mappings.add(cdsToProteinMapping); + } } propagateDBRefsToCDS(cdsSeqDss, dnaSeq.getDatasetSequence(), @@ -1803,20 +1811,21 @@ public class AlignmentUtils List primrefs = dnaDss.getPrimaryDBRefs(); for (int ip = 0, np = primrefs.size(); ip < np; ip++) { - DBRefEntry primRef = primrefs.get(ip); + DBRefEntry primRef = primrefs.get(ip); /* * create a cross-reference from CDS to the source sequence's * primary reference and vice versa */ String source = primRef.getSource(); String version = primRef.getVersion(); - DBRefEntry cdsCrossRef = new DBRefEntry(source, source + ":" - + version, primRef.getAccessionId()); - cdsCrossRef.setMap(new Mapping(dnaDss, new MapList(cdsToDnaMap))); + DBRefEntry cdsCrossRef = new DBRefEntry(source, + source + ":" + version, primRef.getAccessionId()); + cdsCrossRef + .setMap(new Mapping(dnaDss, new MapList(cdsToDnaMap))); cdsSeqDss.addDBRef(cdsCrossRef); - dnaSeq.addDBRef(new DBRefEntry(source, version, cdsSeq - .getName(), new Mapping(cdsSeqDss, dnaToCdsMap))); + dnaSeq.addDBRef(new DBRefEntry(source, version, + cdsSeq.getName(), new Mapping(cdsSeqDss, dnaToCdsMap))); // problem here is that the cross-reference is synthesized - // cdsSeq.getName() may be like 'CDS|dnaaccession' or // 'CDS|emblcdsacc' @@ -1825,8 +1834,8 @@ public class AlignmentUtils DBRefEntry proteinToCdsRef = new DBRefEntry(source, version, cdsSeq.getName()); // - proteinToCdsRef.setMap(new Mapping(cdsSeqDss, cdsToProteinMap - .getInverse())); + proteinToCdsRef.setMap( + new Mapping(cdsSeqDss, cdsToProteinMap.getInverse())); proteinProduct.addDBRef(proteinToCdsRef); } /* @@ -1838,8 +1847,8 @@ public class AlignmentUtils } } - AlignmentI cds = new Alignment(cdsSeqs.toArray(new SequenceI[cdsSeqs - .size()])); + AlignmentI cds = new Alignment( + cdsSeqs.toArray(new SequenceI[cdsSeqs.size()])); cds.setDataset(dataset); return cds; @@ -1992,45 +2001,31 @@ public class AlignmentUtils SequenceI newSeq = null; - final MapList maplist = mapping.getMap(); - if (maplist.isContiguous() && maplist.isFromForwardStrand()) - { - /* - * just a subsequence, keep same dataset sequence - */ - int start = maplist.getFromLowest(); - int end = maplist.getFromHighest(); - newSeq = seq.getSubSequence(start - 1, end); - newSeq.setName(seqId); - } - else - { - /* - * construct by splicing mapped from ranges - */ - char[] seqChars = seq.getSequence(); - List fromRanges = maplist.getFromRanges(); - int cdsWidth = MappingUtils.getLength(fromRanges); - char[] newSeqChars = new char[cdsWidth]; + /* + * construct CDS sequence by splicing mapped from ranges + */ + char[] seqChars = seq.getSequence(); + List fromRanges = mapping.getMap().getFromRanges(); + int cdsWidth = MappingUtils.getLength(fromRanges); + char[] newSeqChars = new char[cdsWidth]; - int newPos = 0; - for (int[] range : fromRanges) + int newPos = 0; + for (int[] range : fromRanges) + { + if (range[0] <= range[1]) + { + // forward strand mapping - just copy the range + int length = range[1] - range[0] + 1; + System.arraycopy(seqChars, range[0] - 1, newSeqChars, newPos, + length); + newPos += length; + } + else { - if (range[0] <= range[1]) + // reverse strand mapping - copy and complement one by one + for (int i = range[0]; i >= range[1]; i--) { - // forward strand mapping - just copy the range - int length = range[1] - range[0] + 1; - System.arraycopy(seqChars, range[0] - 1, newSeqChars, newPos, - length); - newPos += length; - } - else - { - // reverse strand mapping - copy and complement one by one - for (int i = range[0]; i >= range[1]; i--) - { - newSeqChars[newPos++] = Dna.getComplement(seqChars[i - 1]); - } + newSeqChars[newPos++] = Dna.getComplement(seqChars[i - 1]); } } @@ -2064,8 +2059,8 @@ public class AlignmentUtils } else { - System.err.println( - "JAL-2154 regression: warning - found (and ignnored a duplicate CDS sequence):" + Console.error( + "JAL-2154 regression: warning - found (and ignored) a duplicate CDS sequence:" + mtch.toString()); } } @@ -2190,9 +2185,9 @@ public class AlignmentUtils /* * get features, optionally restricted by an ontology term */ - List sfs = select == null ? fromSeq.getFeatures() - .getPositionalFeatures() : fromSeq.getFeatures() - .getFeaturesByOntology(select); + List sfs = select == null + ? fromSeq.getFeatures().getPositionalFeatures() + : fromSeq.getFeatures().getFeaturesByOntology(select); int count = 0; for (SequenceFeature sf : sfs) @@ -2337,8 +2332,8 @@ public class AlignmentUtils { List result = new ArrayList<>(); - List sfs = dnaSeq.getFeatures().getFeaturesByOntology( - SequenceOntologyI.CDS); + List sfs = dnaSeq.getFeatures() + .getFeaturesByOntology(SequenceOntologyI.CDS); if (sfs.isEmpty()) { return result; @@ -2350,11 +2345,11 @@ public class AlignmentUtils int phase = 0; try { - String s = sf.getPhase(); - if (s != null) - { - phase = Integer.parseInt(s); - } + String s = sf.getPhase(); + if (s != null) + { + phase = Integer.parseInt(s); + } } catch (NumberFormatException e) { // leave as zero @@ -2410,11 +2405,11 @@ public class AlignmentUtils SequenceIdMatcher matcher = new SequenceIdMatcher(seqs); if (xrefs != null) { - // BH 2019.01.25 recoded to remove iterators - + // BH 2019.01.25 recoded to remove iterators + for (int ix = 0, nx = xrefs.length; ix < nx; ix++) { - SequenceI xref = xrefs[ix]; + SequenceI xref = xrefs[ix]; List dbrefs = xref.getDBRefs(); if (dbrefs != null) { @@ -2529,10 +2524,10 @@ public class AlignmentUtils * true; else returns false * * @param unaligned - * - sequences to be aligned based on aligned + * - sequences to be aligned based on aligned * @param aligned - * - 'guide' alignment containing sequences derived from same - * dataset as unaligned + * - 'guide' alignment containing sequences derived from same dataset + * as unaligned * @return */ static boolean alignAsSameSequences(AlignmentI unaligned, @@ -2568,8 +2563,7 @@ public class AlignmentUtils { return false; } - SequenceI alignedSeq = alignedDatasets.get(ds) - .get(0); + SequenceI alignedSeq = alignedDatasets.get(ds).get(0); int startCol = alignedSeq.findIndex(seq.getStart()); // 1.. leftmost = Math.min(leftmost, startCol); } @@ -2584,6 +2578,13 @@ public class AlignmentUtils { List alignedSequences = alignedDatasets .get(seq.getDatasetSequence()); + if (alignedSequences.isEmpty()) + { + /* + * defensive check - shouldn't happen! (JAL-3536) + */ + continue; + } SequenceI alignedSeq = alignedSequences.get(0); /*