X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fanalysis%2FDna.java;h=a2b047212b5ea4991cac7adfa145d22b415b08dc;hb=d043ce47fc710d3eb2629ba926a8a7417bd67d8c;hp=c3408bdedd9d396f06d6ec1a203c06887ad7b53a;hpb=e2c3b3602486cee3f85dd8dfc7856a5ce6701669;p=jalview.git diff --git a/src/jalview/analysis/Dna.java b/src/jalview/analysis/Dna.java index c3408bd..a2b0472 100644 --- a/src/jalview/analysis/Dna.java +++ b/src/jalview/analysis/Dna.java @@ -20,6 +20,12 @@ */ package jalview.analysis; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Comparator; +import java.util.Iterator; +import java.util.List; + import jalview.api.AlignViewportI; import jalview.datamodel.AlignedCodon; import jalview.datamodel.AlignedCodonFrame; @@ -28,7 +34,6 @@ import jalview.datamodel.AlignmentAnnotation; import jalview.datamodel.AlignmentI; import jalview.datamodel.Annotation; import jalview.datamodel.DBRefEntry; -import jalview.datamodel.DBRefSource; import jalview.datamodel.FeatureProperties; import jalview.datamodel.GraphLine; import jalview.datamodel.Mapping; @@ -41,11 +46,6 @@ import jalview.util.DBRefUtils; import jalview.util.MapList; import jalview.util.ShiftList; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.Comparator; -import java.util.List; - public class Dna { private static final String STOP_ASTERIX = "*"; @@ -60,7 +60,7 @@ public class Dna private final String[] seqstring; - private final List contigs; + private final Iterator contigs; private final char gapChar; @@ -70,6 +70,10 @@ public class Dna private final AlignmentI dataset; + private ShiftList vismapping; + + private int[] startcontigs; + /* * Working variables for the translation. * @@ -91,7 +95,7 @@ public class Dna * @param viewport * @param visibleContigs */ - public Dna(AlignViewportI viewport, List visibleContigs) + public Dna(AlignViewportI viewport, Iterator visibleContigs) { this.selection = Arrays.asList(viewport.getSequenceSelection()); this.seqstring = viewport.getViewAsString(true); @@ -100,6 +104,45 @@ public class Dna this.annotations = viewport.getAlignment().getAlignmentAnnotation(); this.dnaWidth = viewport.getAlignment().getWidth(); this.dataset = viewport.getAlignment().getDataset(); + initContigs(); + } + + /** + * Initialise contigs used as starting point for translateCodingRegion + */ + private void initContigs() + { + vismapping = new ShiftList(); // map from viscontigs to seqstring + // intervals + + int npos = 0; + int[] lastregion = null; + ArrayList tempcontigs = new ArrayList<>(); + while (contigs.hasNext()) + { + int[] region = contigs.next(); + if (lastregion == null) + { + vismapping.addShift(npos, region[0]); + } + else + { + // hidden region + vismapping.addShift(npos, region[0] - lastregion[1] + 1); + } + lastregion = region; + tempcontigs.add(region[0]); + tempcontigs.add(region[1]); + } + + startcontigs = new int[tempcontigs.size()]; + int i = 0; + for (Integer val : tempcontigs) + { + startcontigs[i] = val; + i++; + } + tempcontigs = null; } /** @@ -119,7 +162,8 @@ public class Dna * @param ac2 * @return */ - public static final int compareCodonPos(AlignedCodon ac1, AlignedCodon ac2) + public static final int compareCodonPos(AlignedCodon ac1, + AlignedCodon ac2) { return comparator.compare(ac1, ac2); // return jalview_2_8_2compare(ac1, ac2); @@ -150,10 +194,11 @@ public class Dna } /** + * Translates cDNA using the specified code table * * @return */ - public AlignmentI translateCdna() + public AlignmentI translateCdna(GeneticCodeI codeTable) { AlignedCodonFrame acf = new AlignedCodonFrame(); @@ -165,7 +210,7 @@ public class Dna for (s = 0; s < sSize; s++) { SequenceI newseq = translateCodingRegion(selection.get(s), - seqstring[s], acf, pepseqs); + seqstring[s], acf, pepseqs, codeTable); if (newseq != null) { @@ -208,29 +253,30 @@ public class Dna for (int gd = 0; gd < selection.length; gd++) { SequenceI dna = selection[gd]; - DBRefEntry[] dnarefs = DBRefUtils.selectRefs(dna.getDBRefs(), + List dnarefs = DBRefUtils.selectRefs(dna.getDBRefs(), jalview.datamodel.DBRefSource.DNACODINGDBS); if (dnarefs != null) { // intersect with pep List mappedrefs = new ArrayList<>(); - DBRefEntry[] refs = dna.getDBRefs(); - for (int d = 0; d < refs.length; d++) + List refs = dna.getDBRefs(); + for (int d = 0, nd = refs.size(); d < nd; d++) { - if (refs[d].getMap() != null && refs[d].getMap().getMap() != null - && refs[d].getMap().getMap().getFromRatio() == 3 - && refs[d].getMap().getMap().getToRatio() == 1) + DBRefEntry ref = refs.get(d); + if (ref.getMap() != null && ref.getMap().getMap() != null + && ref.getMap().getMap().getFromRatio() == 3 + && ref.getMap().getMap().getToRatio() == 1) { - mappedrefs.add(refs[d]); // add translated protein maps + mappedrefs.add(ref); // add translated protein maps } } - dnarefs = mappedrefs.toArray(new DBRefEntry[mappedrefs.size()]); - for (int d = 0; d < dnarefs.length; d++) + dnarefs = mappedrefs;// .toArray(new DBRefEntry[mappedrefs.size()]); + for (int d = 0, nd = dnarefs.size(); d < nd; d++) { - Mapping mp = dnarefs[d].getMap(); + Mapping mp = dnarefs.get(d).getMap(); if (mp != null) { - for (int vc = 0; vc < viscontigs.length; vc += 2) + for (int vc = 0, nv = viscontigs.length; vc < nv; vc += 2) { int[] mpr = mp.locateMappedRange(viscontigs[vc], viscontigs[vc + 1]); @@ -385,37 +431,21 @@ public class Dna * @param acf * Definition of global ORF alignment reference frame * @param proteinSeqs + * @param codeTable * @return sequence ready to be added to alignment. */ protected SequenceI translateCodingRegion(SequenceI selection, String seqstring, AlignedCodonFrame acf, - List proteinSeqs) + List proteinSeqs, GeneticCodeI codeTable) { List skip = new ArrayList<>(); - int skipint[] = null; - ShiftList vismapping = new ShiftList(); // map from viscontigs to seqstring - // intervals - int vc = 0; - int[] scontigs = new int[contigs.size() * 2]; + int[] skipint = null; + int npos = 0; - int[] lastregion = null; - for (int[] region : contigs) - { - if (lastregion == null) - { - vismapping.addShift(npos, region[0]); - } - else - { - // hidden region - vismapping.addShift(npos, region[0] - lastregion[1] + 1); - } - lastregion = region; + int vc = 0; - scontigs[vc] = region[0]; - scontigs[vc + 1] = region[1]; - vc++; - } + int[] scontigs = new int[startcontigs.length]; + System.arraycopy(startcontigs, 0, scontigs, 0, startcontigs.length); // allocate a roughly sized buffer for the protein sequence StringBuilder protein = new StringBuilder(seqstring.length() / 2); @@ -441,7 +471,7 @@ public class Dna */ AlignedCodon alignedCodon = new AlignedCodon(cdp[0], cdp[1], cdp[2]); - String aa = ResidueProperties.codonTranslate(new String(codon)); + String aa = codeTable.translate(new String(codon)); rf = 0; final String gapString = String.valueOf(gapChar); if (aa == null) @@ -548,7 +578,7 @@ public class Dna skip.add(skipint); skipint = null; } - if (aa.equals("STOP")) + if (aa.equals(ResidueProperties.STOP)) { aa = STOP_ASTERIX; } @@ -769,28 +799,29 @@ public class Dna private static void transferCodedFeatures(SequenceI dna, SequenceI pep, MapList map) { - DBRefEntry[] dnarefs = DBRefUtils.selectRefs(dna.getDBRefs(), - DBRefSource.DNACODINGDBS); - if (dnarefs != null) - { - // intersect with pep - for (int d = 0; d < dnarefs.length; d++) - { - Mapping mp = dnarefs[d].getMap(); - if (mp != null) - { - } - } - } + // BH 2019.01.25 nop? + // List dnarefs = DBRefUtils.selectRefs(dna.getDBRefs(), + // DBRefSource.DNACODINGDBS); + // if (dnarefs != null) + // { + // // intersect with pep + // for (int d = 0, nd = dnarefs.size(); d < nd; d++) + // { + // Mapping mp = dnarefs.get(d).getMap(); + // if (mp != null) + // { + // } + // } + // } for (SequenceFeature sf : dna.getFeatures().getAllFeatures()) { - if (FeatureProperties.isCodingFeature(null, sf.getType())) + if (FeatureProperties.isCodingFeature(null, sf.getType())) + { + // if (map.intersectsFrom(sf[f].begin, sf[f].end)) { - // if (map.intersectsFrom(sf[f].begin, sf[f].end)) - { - } } + } } } @@ -855,6 +886,23 @@ public class Dna } /** + * Answers the reverse complement of the input string + * + * @see #getComplement(char) + * @param s + * @return + */ + public static String reverseComplement(String s) + { + StringBuilder sb = new StringBuilder(s.length()); + for (int i = s.length() - 1; i >= 0; i--) + { + sb.append(Dna.getComplement(s.charAt(i))); + } + return sb.toString(); + } + + /** * Returns dna complement (preserving case) for aAcCgGtTuU. Ambiguity codes * are treated as on http://reverse-complement.com/. Anything else is left * unchanged.