2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.datamodel;
23 import java.util.HashSet;
24 import java.util.List;
27 import jalview.io.gff.Gff3Helper;
28 import jalview.schemes.ResidueProperties;
29 import jalview.util.MapList;
30 import jalview.util.MappingUtils;
31 import jalview.util.StringUtils;
34 * A data bean to hold a list of mapped sequence features (e.g. CDS features
35 * mapped from protein), and the mapping between the sequences. It also provides
36 * a method to derive peptide variants from codon variants.
40 public class MappedFeatures
43 * VEP CSQ:HGVSp (if present) is a short-cut to the protein variant consequence
45 private static final String HGV_SP = "HGVSp";
47 private static final String CSQ = "CSQ";
50 * the sequence the mapped features are on
52 private final SequenceI featureSequence;
55 * the mapping between sequences;
56 * NB this could be in either sense (from or to featureSequence)
58 private final Mapping mapping;
61 * features on featureSequence that overlap the mapped positions
63 public final List<SequenceFeature> features;
66 * the residue position in the sequence mapped to
68 private final int toPosition;
71 * the residue at toPosition
73 private final char toResidue;
76 * if the mapping is 3:1 or 1:3 (peptide to CDS), this holds the
77 * mapped positions i.e. codon base positions in CDS; to
78 * support calculation of peptide variants from alleles
80 private final int[] codonPos;
82 private final char[] baseCodon;
88 * sequence mapping (which may be either to, or from, the sequence
89 * holding the linked features)
91 * the sequence hosting the virtual features
93 * the residue position in the sequence mapped to
95 * the residue character at position pos
97 * list of mapped features found in the 'featureSeq' sequence at the
100 public MappedFeatures(Mapping theMapping, SequenceI featureSeq, int pos,
101 char res, List<SequenceFeature> theFeatures)
103 mapping = theMapping;
104 featureSequence = featureSeq;
107 features = theFeatures;
110 * determine codon positions and canonical codon
111 * for a peptide-to-CDS mapping
113 int[] codonIntervals = mapping.getMap().locateInFrom(toPosition, toPosition);
114 int[] codonPositions = codonIntervals == null ? null
115 : MappingUtils.flattenRanges(codonIntervals);
116 if (codonPositions != null && codonPositions.length == 3)
118 codonPos = codonPositions;
119 baseCodon = new char[3];
120 int cdsStart = featureSequence.getStart();
121 baseCodon[0] = Character
122 .toUpperCase(featureSequence.getCharAt(codonPos[0] - cdsStart));
123 baseCodon[1] = Character
124 .toUpperCase(featureSequence.getCharAt(codonPos[1] - cdsStart));
125 baseCodon[2] = Character
126 .toUpperCase(featureSequence.getCharAt(codonPos[2] - cdsStart));
136 * Computes and returns comma-delimited HGVS notation peptide variants derived
137 * from codon allele variants. If no variants are found, answers an empty
138 * string. The peptide variant is either simply read from the "CSQ:HGVSp"
139 * attribute if present, else computed based on the "alleles" attribute if
140 * present. If neither attribute is found, no variant (empty string) is
144 * a sequence feature (which must be one of those held in this
148 public String findProteinVariants(SequenceFeature sf)
150 if (!features.contains(sf) || baseCodon == null)
156 * VCF data may already contain the protein consequence
158 String hgvsp = sf.getValueAsString(CSQ, HGV_SP);
161 int colonPos = hgvsp.lastIndexOf(':');
164 String var = hgvsp.substring(colonPos + 1);
165 if (var.contains("p.")) // sanity check
173 * otherwise, compute codon and peptide variant
175 int cdsPos = sf.getBegin();
176 if (cdsPos != sf.getEnd())
178 // not handling multi-locus variant features
181 if (cdsPos != codonPos[0] && cdsPos != codonPos[1]
182 && cdsPos != codonPos[2])
184 // e.g. feature on intron within spliced codon!
188 String alls = (String) sf.getValue(Gff3Helper.ALLELES);
194 String from3 = StringUtils.toSentenceCase(
195 ResidueProperties.aa2Triplet.get(String.valueOf(toResidue)));
198 * make a peptide variant for each SNP allele
199 * e.g. C,G,T gives variants G and T for base C
201 Set<String> variantPeptides = new HashSet<>();
202 String[] alleles = alls.toUpperCase().split(",");
203 StringBuilder vars = new StringBuilder();
205 for (String allele : alleles)
207 allele = allele.trim().toUpperCase();
208 if (allele.length() > 1 || "-".equals(allele))
210 continue; // multi-locus variant
212 char[] variantCodon = new char[3];
213 variantCodon[0] = baseCodon[0];
214 variantCodon[1] = baseCodon[1];
215 variantCodon[2] = baseCodon[2];
218 * poke variant base into canonical codon;
219 * ignore first 'allele' (canonical base)
221 final int i = cdsPos == codonPos[0] ? 0
222 : (cdsPos == codonPos[1] ? 1 : 2);
223 variantCodon[i] = allele.toUpperCase().charAt(0);
224 if (variantCodon[i] == baseCodon[i])
228 String codon = new String(variantCodon);
229 String peptide = ResidueProperties.codonTranslate(codon);
230 boolean synonymous = toResidue == peptide.charAt(0);
231 StringBuilder var = new StringBuilder();
235 * synonymous variant notation e.g. c.1062C>A(p.=)
237 var.append("c.").append(String.valueOf(cdsPos))
238 .append(String.valueOf(baseCodon[i])).append(">")
239 .append(String.valueOf(variantCodon[i]))
245 * missense variant notation e.g. p.Arg355Met
247 String to3 = ResidueProperties.STOP.equals(peptide) ? "Ter"
248 : StringUtils.toSentenceCase(
249 ResidueProperties.aa2Triplet.get(peptide));
250 var.append("p.").append(from3).append(String.valueOf(toPosition))
253 if (!variantPeptides.contains(peptide)) // duplicate consequence
255 variantPeptides.add(peptide);
256 if (vars.length() > 0)
264 return vars.toString();
268 * Answers the name of the linked sequence holding any mapped features
272 public String getLinkedSequenceName()
274 return featureSequence == null ? null : featureSequence.getName();
278 * Answers the mapped ranges (as one or more [start, end] positions) which
279 * correspond to the given [begin, end] range of the linked sequence.
282 * Example: MappedFeatures with CDS features mapped to peptide
283 * CDS/200-220 gtc aac TGa acGt att AAC tta
284 * mapped to PEP/6-7 WN by mapping [206, 207, 210, 210, 215, 217] to [6, 7]
285 * getMappedPositions(206, 206) should return [6, 6]
286 * getMappedPositions(200, 214) should return [6, 6]
287 * getMappedPositions(210, 215) should return [6, 7]
294 public int[] getMappedPositions(int begin, int end)
296 MapList map = mapping.getMap();
297 return mapping.to == featureSequence ? map.locateInFrom(begin, end)
298 : map.locateInTo(begin, end);
302 * Answers true if the linked features are on coding sequence, false if on
307 public boolean isFromCds()
309 if (mapping.getMap().getFromRatio() == 3)
311 return mapping.to != featureSequence;
313 return mapping.to == featureSequence;