-/*\r
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5)\r
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle\r
- * \r
- * This file is part of Jalview.\r
- * \r
- * Jalview is free software: you can redistribute it and/or\r
- * modify it under the terms of the GNU General Public License \r
- * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.\r
- * \r
- * Jalview is distributed in the hope that it will be useful, but \r
- * WITHOUT ANY WARRANTY; without even the implied warranty \r
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR \r
- * PURPOSE. See the GNU General Public License for more details.\r
- * \r
- * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.\r
- */\r
-package jalview.datamodel;\r
-\r
-import java.util.Enumeration;\r
-import java.util.Vector;\r
-\r
-import jalview.util.MapList;\r
-\r
-/**\r
- * Stores mapping between the columns of a protein alignment and a DNA alignment\r
- * and a list of individual codon to amino acid mappings between sequences.\r
- */\r
-\r
-public class AlignedCodonFrame\r
-{\r
- /**\r
- * array of nucleotide positions for aligned codons at column of aligned\r
- * proteins.\r
- */\r
- public int[][] codons = null;\r
-\r
- /**\r
- * width of protein sequence alignement implicit assertion that codons.length\r
- * >= aaWidth\r
- */\r
- public int aaWidth = 0;\r
-\r
- /**\r
- * initialise codon frame with a nominal alignment width\r
- * \r
- * @param aWidth\r
- */\r
- public AlignedCodonFrame(int aWidth)\r
- {\r
- if (aWidth <= 0)\r
- {\r
- codons = null;\r
- return;\r
- }\r
- codons = new int[aWidth][];\r
- for (int res = 0; res < aWidth; res++)\r
- codons[res] = null;\r
- }\r
-\r
- /**\r
- * ensure that codons array is at least as wide as aslen residues\r
- * \r
- * @param aslen\r
- * @return (possibly newly expanded) codon array\r
- */\r
- public int[][] checkCodonFrameWidth(int aslen)\r
- {\r
- if (codons.length <= aslen + 1)\r
- {\r
- // probably never have to do this ?\r
- int[][] c = new int[codons.length + 10][];\r
- for (int i = 0; i < codons.length; i++)\r
- {\r
- c[i] = codons[i];\r
- codons[i] = null;\r
- }\r
- codons = c;\r
- }\r
- return codons;\r
- }\r
-\r
- /**\r
- * @return width of aligned translated amino acid residues\r
- */\r
- public int getaaWidth()\r
- {\r
- return aaWidth;\r
- }\r
-\r
- /**\r
- * TODO: not an ideal solution - we reference the aligned amino acid sequences\r
- * in order to make insertions on them Better would be dnaAlignment and\r
- * aaAlignment reference....\r
- */\r
- Vector a_aaSeqs = new Vector();\r
-\r
- /**\r
- * increase aaWidth by one and insert a new aligned codon position space at\r
- * aspos.\r
- * \r
- * @param aspos\r
- */\r
- public void insertAAGap(int aspos, char gapCharacter)\r
- {\r
- // this aa appears before the aligned codons at aspos - so shift them in\r
- // each pair of mapped sequences\r
- aaWidth++;\r
- if (a_aaSeqs != null)\r
- {\r
- // we actually have to modify the aligned sequences here, so use the\r
- // a_aaSeqs vector\r
- Enumeration sq = a_aaSeqs.elements();\r
- while (sq.hasMoreElements())\r
- {\r
- ((SequenceI) sq.nextElement()).insertCharAt(aspos, gapCharacter);\r
- }\r
- }\r
- checkCodonFrameWidth(aspos);\r
- if (aspos < aaWidth)\r
- {\r
- aaWidth++;\r
- System.arraycopy(codons, aspos, codons, aspos + 1, aaWidth - aspos);\r
- codons[aspos] = null; // clear so new codon position can be marked.\r
- }\r
- }\r
-\r
- public void setAaWidth(int aapos)\r
- {\r
- aaWidth = aapos;\r
- }\r
-\r
- /**\r
- * tied array of na Sequence objects.\r
- */\r
- SequenceI[] dnaSeqs = null;\r
-\r
- /**\r
- * tied array of Mappings to protein sequence Objects and SequenceI[]\r
- * aaSeqs=null; MapLists where eac maps from the corresponding dnaSeqs element\r
- * to corresponding aaSeqs element\r
- */\r
- Mapping[] dnaToProt = null;\r
-\r
- /**\r
- * add a mapping between the dataset sequences for the associated dna and\r
- * protein sequence objects\r
- * \r
- * @param dnaseq\r
- * @param aaseq\r
- * @param map\r
- */\r
- public void addMap(SequenceI dnaseq, SequenceI aaseq, MapList map)\r
- {\r
- int nlen = 1;\r
- if (dnaSeqs != null)\r
- {\r
- nlen = dnaSeqs.length + 1;\r
- }\r
- SequenceI[] ndna = new SequenceI[nlen];\r
- Mapping[] ndtp = new Mapping[nlen];\r
- if (dnaSeqs != null)\r
- {\r
- System.arraycopy(dnaSeqs, 0, ndna, 0, dnaSeqs.length);\r
- System.arraycopy(dnaToProt, 0, ndtp, 0, dnaSeqs.length);\r
- }\r
- dnaSeqs = ndna;\r
- dnaToProt = ndtp;\r
- nlen--;\r
- dnaSeqs[nlen] = (dnaseq.getDatasetSequence() == null) ? dnaseq : dnaseq\r
- .getDatasetSequence();\r
- Mapping mp = new Mapping(map);\r
- // JBPNote DEBUG! THIS !\r
- // dnaseq.transferAnnotation(aaseq, mp);\r
- // aaseq.transferAnnotation(dnaseq, new Mapping(map.getInverse()));\r
- mp.to = (aaseq.getDatasetSequence() == null) ? aaseq : aaseq\r
- .getDatasetSequence();\r
- a_aaSeqs.addElement(aaseq);\r
- dnaToProt[nlen] = mp;\r
- }\r
-\r
- public SequenceI[] getdnaSeqs()\r
- {\r
- return dnaSeqs;\r
- }\r
-\r
- public SequenceI[] getAaSeqs()\r
- {\r
- if (dnaToProt == null)\r
- return null;\r
- SequenceI[] sqs = new SequenceI[dnaToProt.length];\r
- for (int sz = 0; sz < dnaToProt.length; sz++)\r
- {\r
- sqs[sz] = dnaToProt[sz].to;\r
- }\r
- return sqs;\r
- }\r
-\r
- public MapList[] getdnaToProt()\r
- {\r
- if (dnaToProt == null)\r
- return null;\r
- MapList[] sqs = new MapList[dnaToProt.length];\r
- for (int sz = 0; sz < dnaToProt.length; sz++)\r
- {\r
- sqs[sz] = dnaToProt[sz].map;\r
- }\r
- return sqs;\r
- }\r
-\r
- public Mapping[] getProtMappings()\r
- {\r
- return dnaToProt;\r
- }\r
-\r
- /**\r
- * \r
- * @param sequenceRef\r
- * @return null or corresponding aaSeq entry for dnaSeq entry\r
- */\r
- public SequenceI getAaForDnaSeq(SequenceI dnaSeqRef)\r
- {\r
- if (dnaSeqs == null)\r
- {\r
- return null;\r
- }\r
- SequenceI dnads = dnaSeqRef.getDatasetSequence();\r
- for (int ds = 0; ds < dnaSeqs.length; ds++)\r
- {\r
- if (dnaSeqs[ds] == dnaSeqRef || dnaSeqs[ds] == dnads)\r
- return dnaToProt[ds].to;\r
- }\r
- return null;\r
- }\r
-\r
- /**\r
- * \r
- * @param sequenceRef\r
- * @return null or corresponding aaSeq entry for dnaSeq entry\r
- */\r
- public SequenceI getDnaForAaSeq(SequenceI aaSeqRef)\r
- {\r
- if (dnaToProt == null)\r
- {\r
- return null;\r
- }\r
- SequenceI aads = aaSeqRef.getDatasetSequence();\r
- for (int as = 0; as < dnaToProt.length; as++)\r
- {\r
- if (dnaToProt[as].to == aaSeqRef || dnaToProt[as].to == aads)\r
- return dnaSeqs[as];\r
- }\r
- return null;\r
- }\r
-\r
- /**\r
- * test to see if codon frame involves seq in any way\r
- * \r
- * @param seq\r
- * a nucleotide or protein sequence\r
- * @return true if a mapping exists to or from this sequence to any translated\r
- * sequence\r
- */\r
- public boolean involvesSequence(SequenceI seq)\r
- {\r
- return getAaForDnaSeq(seq) != null || getDnaForAaSeq(seq) != null;\r
- }\r
-\r
- /**\r
- * Add search results for regions in other sequences that translate or are\r
- * translated from a particular position in seq\r
- * \r
- * @param seq\r
- * @param index\r
- * position in seq\r
- * @param results\r
- * where highlighted regions go\r
- */\r
- public void markMappedRegion(SequenceI seq, int index,\r
- SearchResults results)\r
- {\r
- if (dnaToProt == null)\r
- {\r
- return;\r
- }\r
- int[] codon;\r
- SequenceI ds = seq.getDatasetSequence();\r
- for (int mi = 0; mi < dnaToProt.length; mi++)\r
- {\r
- if (dnaSeqs[mi] == seq || dnaSeqs[mi] == ds)\r
- {\r
- // DEBUG System.err.println("dna pos "+index);\r
- codon = dnaToProt[mi].map.locateInTo(index, index);\r
- if (codon != null)\r
- {\r
- for (int i = 0; i < codon.length; i += 2)\r
- {\r
- results.addResult(dnaToProt[mi].to, codon[i], codon[i + 1]);\r
- }\r
- }\r
- }\r
- else if (dnaToProt[mi].to == seq || dnaToProt[mi].to == ds)\r
- {\r
- // DEBUG System.err.println("aa pos "+index);\r
- {\r
- codon = dnaToProt[mi].map.locateInFrom(index, index);\r
- if (codon != null)\r
- {\r
- for (int i = 0; i < codon.length; i += 2)\r
- {\r
- results.addResult(dnaSeqs[mi], codon[i], codon[i + 1]);\r
- }\r
- }\r
- }\r
- }\r
- }\r
- }\r
-}\r
+/*
+ * 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.
+ *
+ * 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 <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.datamodel;
+
+import jalview.util.MapList;
+import jalview.util.MappingUtils;
+
+import java.util.AbstractList;
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * Stores mapping between the columns of a protein alignment and a DNA alignment
+ * and a list of individual codon to amino acid mappings between sequences.
+ */
+public class AlignedCodonFrame
+{
+
+ private List<SequenceMapping> mappings;
+
+ /**
+ * Constructor
+ */
+ public AlignedCodonFrame()
+ {
+ mappings = new ArrayList<>();
+ }
+
+ /**
+ * Adds a mapping between the dataset sequences for the associated dna and
+ * protein sequence objects
+ *
+ * @param dnaseq
+ * @param aaseq
+ * @param map
+ */
+ public void addMap(SequenceI dnaseq, SequenceI aaseq, MapList map)
+ {
+ addMap(dnaseq, aaseq, map, null);
+ }
+
+ /**
+ * Adds a mapping between the dataset sequences for the associated dna and
+ * protein sequence objects
+ *
+ * @param dnaseq
+ * @param aaseq
+ * @param map
+ * @param mapFromId
+ */
+ public void addMap(SequenceI dnaseq, SequenceI aaseq, MapList map,
+ String mapFromId)
+ {
+ // JBPNote DEBUG! THIS !
+ // dnaseq.transferAnnotation(aaseq, mp);
+ // aaseq.transferAnnotation(dnaseq, new Mapping(map.getInverse()));
+
+ SequenceI fromSeq = (dnaseq.getDatasetSequence() == null) ? dnaseq
+ : dnaseq.getDatasetSequence();
+ SequenceI toSeq = (aaseq.getDatasetSequence() == null) ? aaseq
+ : aaseq.getDatasetSequence();
+
+ /*
+ * if we already hold a mapping between these sequences, just add to it
+ * note that 'adding' a duplicate map does nothing; this protects against
+ * creating duplicate mappings in AlignedCodonFrame
+ */
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == fromSeq && ssm.mapping.to == toSeq)
+ {
+ ssm.mapping.map.addMapList(map);
+ return;
+ }
+ }
+
+ /*
+ * otherwise, add a new sequence mapping
+ */
+ Mapping mp = new Mapping(toSeq, map);
+ mp.setMappedFromId(mapFromId);
+ mappings.add(new SequenceMapping(fromSeq, mp));
+ }
+
+ public SequenceI[] getdnaSeqs()
+ {
+ // TODO return a list instead?
+ // return dnaSeqs;
+ List<SequenceI> seqs = new ArrayList<>();
+ for (SequenceMapping ssm : mappings)
+ {
+ seqs.add(ssm.fromSeq);
+ }
+ return seqs.toArray(new SequenceI[seqs.size()]);
+ }
+
+ public SequenceI[] getAaSeqs()
+ {
+ // TODO not used - remove?
+ List<SequenceI> seqs = new ArrayList<>();
+ for (SequenceMapping ssm : mappings)
+ {
+ seqs.add(ssm.mapping.to);
+ }
+ return seqs.toArray(new SequenceI[seqs.size()]);
+ }
+
+ public MapList[] getdnaToProt()
+ {
+ List<MapList> maps = new ArrayList<>();
+ for (SequenceMapping ssm : mappings)
+ {
+ maps.add(ssm.mapping.map);
+ }
+ return maps.toArray(new MapList[maps.size()]);
+ }
+
+ public Mapping[] getProtMappings()
+ {
+ List<Mapping> maps = new ArrayList<>();
+ for (SequenceMapping ssm : mappings)
+ {
+ maps.add(ssm.mapping);
+ }
+ return maps.toArray(new Mapping[maps.size()]);
+ }
+
+ /**
+ * Returns the first mapping found which is to or from the given sequence, or
+ * null.
+ *
+ * @param seq
+ * @return
+ */
+ public Mapping getMappingForSequence(SequenceI seq, boolean cdsOnly)
+ {
+ SequenceI seqDs = seq.getDatasetSequence();
+ seqDs = seqDs != null ? seqDs : seq;
+
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == seqDs || ssm.mapping.to == seqDs)
+ {
+ if (!cdsOnly || ssm.fromSeq.getName().startsWith("CDS")
+ || ssm.mapping.to.getName().startsWith("CDS"))
+ {
+ return ssm.mapping;
+ }
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Return the corresponding aligned or dataset aa sequence for given dna
+ * sequence, null if not found.
+ *
+ * @param sequenceRef
+ * @return
+ */
+ public SequenceI getAaForDnaSeq(SequenceI dnaSeqRef)
+ {
+ SequenceI dnads = dnaSeqRef.getDatasetSequence();
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == dnaSeqRef || ssm.fromSeq == dnads)
+ {
+ return ssm.mapping.to;
+ }
+ }
+ return null;
+ }
+
+ /**
+ *
+ * @param sequenceRef
+ * @return null or corresponding aaSeq entry for dnaSeq entry
+ */
+ public SequenceI getDnaForAaSeq(SequenceI aaSeqRef)
+ {
+ SequenceI aads = aaSeqRef.getDatasetSequence();
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.mapping.to == aaSeqRef || ssm.mapping.to == aads)
+ {
+ return ssm.fromSeq;
+ }
+ }
+ return null;
+ }
+
+ /**
+ * test to see if codon frame involves seq in any way
+ *
+ * @param seq
+ * a nucleotide or protein sequence
+ * @return true if a mapping exists to or from this sequence to any translated
+ * sequence
+ */
+ public boolean involvesSequence(SequenceI seq)
+ {
+ return getAaForDnaSeq(seq) != null || getDnaForAaSeq(seq) != null;
+ }
+
+ /**
+ * Add search results for regions in other sequences that translate or are
+ * translated from a particular position in seq
+ *
+ * @param seq
+ * @param index
+ * position in seq
+ * @param results
+ * where highlighted regions go
+ */
+ public void markMappedRegion(SequenceI seq, int index,
+ SearchResultsI results)
+ {
+ int[] codon;
+ SequenceI ds = seq.getDatasetSequence();
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == seq || ssm.fromSeq == ds)
+ {
+ codon = ssm.mapping.map.locateInTo(index, index);
+ if (codon != null)
+ {
+ for (int i = 0; i < codon.length; i += 2)
+ {
+ results.addResult(ssm.mapping.to, codon[i], codon[i + 1]);
+ }
+ }
+ }
+ else if (ssm.mapping.to == seq || ssm.mapping.to == ds)
+ {
+ {
+ codon = ssm.mapping.map.locateInFrom(index, index);
+ if (codon != null)
+ {
+ for (int i = 0; i < codon.length; i += 2)
+ {
+ results.addResult(ssm.fromSeq, codon[i], codon[i + 1]);
+ }
+ }
+ }
+ }
+ }
+ }
+
+ /**
+ * Returns the DNA codon positions (base 1) for the given position (base 1) in
+ * a mapped protein sequence, or null if no mapping is found.
+ *
+ * Intended for use in aligning cDNA to match aligned protein. Only the first
+ * mapping found is returned, so not suitable for use if multiple protein
+ * sequences are mapped to the same cDNA (but aligning cDNA as protein is
+ * ill-defined for this case anyway).
+ *
+ * @param seq
+ * the DNA dataset sequence
+ * @param aaPos
+ * residue position (base 1) in a protein sequence
+ * @return
+ */
+ public int[] getDnaPosition(SequenceI seq, int aaPos)
+ {
+ /*
+ * Adapted from markMappedRegion().
+ */
+ MapList ml = null;
+ int i = 0;
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == seq)
+ {
+ ml = getdnaToProt()[i];
+ break;
+ }
+ i++;
+ }
+ return ml == null ? null : ml.locateInFrom(aaPos, aaPos);
+ }
+
+ /**
+ * Convenience method to return the first aligned sequence in the given
+ * alignment whose dataset has a mapping with the given (aligned or dataset)
+ * sequence.
+ *
+ * @param seq
+ *
+ * @param al
+ * @return
+ */
+ public SequenceI findAlignedSequence(SequenceI seq, AlignmentI al)
+ {
+ /*
+ * Search mapped protein ('to') sequences first.
+ */
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.fromSeq == seq || ssm.fromSeq == seq.getDatasetSequence())
+ {
+ for (SequenceI sourceAligned : al.getSequences())
+ {
+ if (ssm.mapping.to == sourceAligned.getDatasetSequence()
+ || ssm.mapping.to == sourceAligned)
+ {
+ return sourceAligned;
+ }
+ }
+ }
+ }
+
+ /*
+ * Then try mapped dna sequences.
+ */
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.mapping.to == seq
+ || ssm.mapping.to == seq.getDatasetSequence())
+ {
+ for (SequenceI sourceAligned : al.getSequences())
+ {
+ if (ssm.fromSeq == sourceAligned.getDatasetSequence())
+ {
+ return sourceAligned;
+ }
+ }
+ }
+ }
+
+ return null;
+ }
+
+ /**
+ * Returns the region in the target sequence's dataset that is mapped to the
+ * given position (base 1) in the query sequence's dataset. The region is a
+ * set of start/end position pairs.
+ *
+ * @param target
+ * @param query
+ * @param queryPos
+ * @return
+ */
+ public int[] getMappedRegion(SequenceI target, SequenceI query,
+ int queryPos)
+ {
+ SequenceI targetDs = target.getDatasetSequence() == null ? target
+ : target.getDatasetSequence();
+ SequenceI queryDs = query.getDatasetSequence() == null ? query
+ : query.getDatasetSequence();
+ if (targetDs == null || queryDs == null /*|| dnaToProt == null*/)
+ {
+ return null;
+ }
+ for (SequenceMapping ssm : mappings)
+ {
+ /*
+ * try mapping from target to query
+ */
+ if (ssm.fromSeq == targetDs && ssm.mapping.to == queryDs)
+ {
+ int[] codon = ssm.mapping.map.locateInFrom(queryPos, queryPos);
+ if (codon != null)
+ {
+ return codon;
+ }
+ }
+ /*
+ * else try mapping from query to target
+ */
+ else if (ssm.fromSeq == queryDs && ssm.mapping.to == targetDs)
+ {
+ int[] codon = ssm.mapping.map.locateInTo(queryPos, queryPos);
+ if (codon != null)
+ {
+ return codon;
+ }
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Returns the mapped DNA codons for the given position in a protein sequence,
+ * or null if no mapping is found. Returns a list of (e.g.) ['g', 'c', 't']
+ * codons. There may be more than one codon mapped to the protein if (for
+ * example), there are mappings to cDNA variants.
+ *
+ * @param protein
+ * the peptide dataset sequence
+ * @param aaPos
+ * residue position (base 1) in the peptide sequence
+ * @return
+ */
+ public List<char[]> getMappedCodons(SequenceI protein, int aaPos)
+ {
+ MapList ml = null;
+ SequenceI dnaSeq = null;
+ List<char[]> result = new ArrayList<>();
+
+ for (SequenceMapping ssm : mappings)
+ {
+ if (ssm.mapping.to == protein
+ && ssm.mapping.getMap().getFromRatio() == 3)
+ {
+ ml = ssm.mapping.map;
+ dnaSeq = ssm.fromSeq;
+
+ int[] codonPos = ml.locateInFrom(aaPos, aaPos);
+ if (codonPos == null)
+ {
+ return null;
+ }
+
+ /*
+ * Read off the mapped nucleotides (converting to position base 0)
+ */
+ codonPos = MappingUtils.flattenRanges(codonPos);
+ int start = dnaSeq.getStart();
+ char c1 = dnaSeq.getCharAt(codonPos[0] - start);
+ char c2 = dnaSeq.getCharAt(codonPos[1] - start);
+ char c3 = dnaSeq.getCharAt(codonPos[2] - start);
+ result.add(new char[] { c1, c2, c3 });
+ }
+ }
+ return result.isEmpty() ? null : result;
+ }
+
+ /**
+ * Returns any mappings found which are from the given sequence, and to
+ * distinct sequences.
+ *
+ * @param seq
+ * @return
+ */
+ public List<Mapping> getMappingsFromSequence(SequenceI seq)
+ {
+ List<Mapping> result = new ArrayList<>();
+ List<SequenceI> related = new ArrayList<>();
+ SequenceI seqDs = seq.getDatasetSequence();
+ seqDs = seqDs != null ? seqDs : seq;
+
+ for (SequenceMapping ssm : mappings)
+ {
+ final Mapping mapping = ssm.mapping;
+ if (ssm.fromSeq == seqDs)
+ {
+ if (!related.contains(mapping.to))
+ {
+ result.add(mapping);
+ related.add(mapping.to);
+ }
+ }
+ }
+ return result;
+ }
+
+ /**
+ * Test whether the given sequence is substitutable for one or more dummy
+ * sequences in this mapping
+ *
+ * @param map
+ * @param seq
+ * @return
+ */
+ public boolean isRealisableWith(SequenceI seq)
+ {
+ return realiseWith(seq, false) > 0;
+ }
+
+ /**
+ * Replace any matchable mapped dummy sequences with the given real one.
+ * Returns the count of sequence mappings instantiated.
+ *
+ * @param seq
+ * @return
+ */
+ public int realiseWith(SequenceI seq)
+ {
+ return realiseWith(seq, true);
+ }
+
+ /**
+ * Returns the number of mapped dummy sequences that could be replaced with
+ * the given real sequence.
+ *
+ * @param seq
+ * a dataset sequence
+ * @param doUpdate
+ * if true, performs replacements, else only counts
+ * @return
+ */
+ protected int realiseWith(SequenceI seq, boolean doUpdate)
+ {
+ SequenceI ds = seq.getDatasetSequence() != null
+ ? seq.getDatasetSequence()
+ : seq;
+ int count = 0;
+
+ /*
+ * check for replaceable DNA ('map from') sequences
+ */
+ for (SequenceMapping ssm : mappings)
+ {
+ SequenceI dna = ssm.fromSeq;
+ if (dna instanceof SequenceDummy
+ && dna.getName().equals(ds.getName()))
+ {
+ Mapping mapping = ssm.mapping;
+ int mapStart = mapping.getMap().getFromLowest();
+ int mapEnd = mapping.getMap().getFromHighest();
+ boolean mappable = couldRealiseSequence(dna, ds, mapStart, mapEnd);
+ if (mappable)
+ {
+ count++;
+ if (doUpdate)
+ {
+ // TODO: new method ? ds.realise(dna);
+ // might want to copy database refs as well
+ ds.setSequenceFeatures(dna.getSequenceFeatures());
+ // dnaSeqs[i] = ds;
+ ssm.fromSeq = ds;
+ System.out.println("Realised mapped sequence " + ds.getName());
+ }
+ }
+ }
+
+ /*
+ * check for replaceable protein ('map to') sequences
+ */
+ Mapping mapping = ssm.mapping;
+ SequenceI prot = mapping.getTo();
+ int mapStart = mapping.getMap().getToLowest();
+ int mapEnd = mapping.getMap().getToHighest();
+ boolean mappable = couldRealiseSequence(prot, ds, mapStart, mapEnd);
+ if (mappable)
+ {
+ count++;
+ if (doUpdate)
+ {
+ // TODO: new method ? ds.realise(dna);
+ // might want to copy database refs as well
+ ds.setSequenceFeatures(dna.getSequenceFeatures());
+ ssm.mapping.setTo(ds);
+ }
+ }
+ }
+ return count;
+ }
+
+ /**
+ * Helper method to test whether a 'real' sequence could replace a 'dummy'
+ * sequence in the map. The criteria are that they have the same name, and
+ * that the mapped region overlaps the candidate sequence.
+ *
+ * @param existing
+ * @param replacement
+ * @param mapStart
+ * @param mapEnd
+ * @return
+ */
+ protected static boolean couldRealiseSequence(SequenceI existing,
+ SequenceI replacement, int mapStart, int mapEnd)
+ {
+ if (existing instanceof SequenceDummy
+ && !(replacement instanceof SequenceDummy)
+ && existing.getName().equals(replacement.getName()))
+ {
+ int start = replacement.getStart();
+ int end = replacement.getEnd();
+ boolean mappingOverlapsSequence = (mapStart >= start
+ && mapStart <= end) || (mapEnd >= start && mapEnd <= end);
+ if (mappingOverlapsSequence)
+ {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ /**
+ * Change any mapping to the given sequence to be to its dataset sequence
+ * instead. For use when mappings are created before their referenced
+ * sequences are instantiated, for example when parsing GFF data.
+ *
+ * @param seq
+ */
+ public void updateToDataset(SequenceI seq)
+ {
+ if (seq == null || seq.getDatasetSequence() == null)
+ {
+ return;
+ }
+ SequenceI ds = seq.getDatasetSequence();
+
+ for (SequenceMapping ssm : mappings)
+ /*
+ * 'from' sequences
+ */
+ {
+ if (ssm.fromSeq == seq)
+ {
+ ssm.fromSeq = ds;
+ }
+
+ /*
+ * 'to' sequences
+ */
+ if (ssm.mapping.to == seq)
+ {
+ ssm.mapping.to = ds;
+ }
+ }
+ }
+
+ /**
+ * Answers true if this object contains no mappings
+ *
+ * @return
+ */
+ public boolean isEmpty()
+ {
+ return mappings.isEmpty();
+ }
+
+ /**
+ * Method for debug / inspection purposes only, may change in future
+ */
+ @Override
+ public String toString()
+ {
+ return mappings == null ? "null" : mappings.toString();
+ }
+
+ /**
+ * Returns the first mapping found that is between 'fromSeq' and 'toSeq', or
+ * null if none found
+ *
+ * @param fromSeq
+ * aligned or dataset sequence
+ * @param toSeq
+ * aligned or dataset sequence
+ * @return
+ */
+ public Mapping getMappingBetween(SequenceI fromSeq, SequenceI toSeq)
+ {
+ SequenceI dssFrom = fromSeq.getDatasetSequence() == null ? fromSeq
+ : fromSeq.getDatasetSequence();
+ SequenceI dssTo = toSeq.getDatasetSequence() == null ? toSeq
+ : toSeq.getDatasetSequence();
+
+ for (SequenceMapping mapping : mappings)
+ {
+ SequenceI from = mapping.fromSeq;
+ SequenceI to = mapping.mapping.to;
+ if ((from == dssFrom && to == dssTo)
+ || (from == dssTo && to == dssFrom))
+ {
+ return mapping.mapping;
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Returns a hashcode derived from the list of sequence mappings
+ *
+ * @see SequenceMapping#hashCode()
+ * @see AbstractList#hashCode()
+ */
+ @Override
+ public int hashCode()
+ {
+ return this.mappings.hashCode();
+ }
+
+ /**
+ * Two AlignedCodonFrame objects are equal if they hold the same ordered list
+ * of mappings
+ *
+ * @see SequenceToSequenceMapping#
+ */
+ @Override
+ public boolean equals(Object obj)
+ {
+ if (!(obj instanceof AlignedCodonFrame))
+ {
+ return false;
+ }
+ return this.mappings.equals(((AlignedCodonFrame) obj).mappings);
+ }
+
+ public List<SequenceMapping> getMappings()
+ {
+ return mappings;
+ }
+}
git://source.jalview.org / jalview.git / blobdiff