/* * 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 . * The Jalview Authors are detailed in the 'AUTHORS' file. */ package jalview.schemes; import jalview.analysis.scoremodels.PairwiseSeqScoreModel; import jalview.math.Matrix; import jalview.math.MatrixI; public class ScoreMatrix extends PairwiseSeqScoreModel { String name; @Override public String getName() { return name; } /** * reference to integer score matrix */ int[][] matrix; /** * 0 for Protein Score matrix. 1 for dna score matrix */ int type; /** * * @param name * Unique, human readable name for the matrix * @param matrix * Pairwise scores indexed according to appropriate symbol alphabet * @param type * 0 for Protein, 1 for NA */ ScoreMatrix(String name, int[][] matrix, int type) { this.matrix = matrix; this.type = type; this.name = name; } @Override public boolean isDNA() { return type == 1; } @Override public boolean isProtein() { return type == 0; } @Override public int[][] getMatrix() { return matrix; } /** * Answers the score for substituting first char in A1 with first char in A2 * * @param A1 * @param A2 * @return */ public int getPairwiseScore(String A1, String A2) { return getPairwiseScore(A1.charAt(0), A2.charAt(0)); } @Override public int getPairwiseScore(char c, char d) { int pog = 0; try { int a = (type == 0) ? ResidueProperties.aaIndex[c] : ResidueProperties.nucleotideIndex[c]; int b = (type == 0) ? ResidueProperties.aaIndex[d] : ResidueProperties.nucleotideIndex[d]; /* * FIXME: 2.10.1 PCA treats gap as [22] or 'X', but Tree * calculation treats as [23]; which is correct? */ /* * hack to convert unassigned / unknown (including gap) * to index of unknown (X for amino acids, N for nucleotide) * TODO: statically assign gap characters to this index? */ // if (type == 0) // { // if (a == ResidueProperties.maxProteinIndex) // { // a = ResidueProperties.aaIndex['X']; // } // if (b == ResidueProperties.maxProteinIndex) // { // b = ResidueProperties.aaIndex['X']; // } // } // if (type != 0) // { // if (a == ResidueProperties.maxNucleotideIndex) // { // a = ResidueProperties.nucleotideIndex['N']; // } // if (b == ResidueProperties.maxNucleotideIndex) // { // b = ResidueProperties.nucleotideIndex['N']; // } // } pog = matrix[a][b]; } catch (Exception e) { // System.out.println("Unknown residue in " + A1 + " " + A2); } return pog; } /** * pretty print the matrix */ @Override public String toString() { return outputMatrix(false); } public String outputMatrix(boolean html) { StringBuffer sb = new StringBuffer(); int[] symbols = (type == 0) ? ResidueProperties.aaIndex : ResidueProperties.nucleotideIndex; int symMax = (type == 0) ? ResidueProperties.maxProteinIndex : ResidueProperties.maxNucleotideIndex; boolean header = true; if (html) { sb.append(""); } for (char sym = 'A'; sym <= 'Z'; sym++) { if (symbols[sym] >= 0 && symbols[sym] < symMax) { if (header) { sb.append(html ? "" : ""); for (char sym2 = 'A'; sym2 <= 'Z'; sym2++) { if (symbols[sym2] >= 0 && symbols[sym2] < symMax) { sb.append((html ? "" : "")); } } header = false; sb.append(html ? "\n" : "\n"); } if (html) { sb.append(""); } sb.append((html ? "" : "")); for (char sym2 = 'A'; sym2 <= 'Z'; sym2++) { if (symbols[sym2] >= 0 && symbols[sym2] < symMax) { sb.append((html ? "" : "")); } } sb.append(html ? "\n" : "\n"); } } if (html) { sb.append("
 " : "\t") + sym2 + (html ? " 
" : "") + sym + (html ? "" : "\t") + matrix[symbols[sym]][symbols[sym2]] + (html ? "
"); } return sb.toString(); } /** * Computes an NxN matrix where N is the number of sequences, and entry [i, j] * is sequence[i] pairwise multiplied with sequence[j], as a sum of scores * computed using the current score matrix. For example * */ public MatrixI computePairwiseScores(String[] seqs) { double[][] values = new double[seqs.length][]; for (int row = 0; row < seqs.length; row++) { values[row] = new double[seqs.length]; for (int col = 0; col < seqs.length; col++) { int total = 0; int width = Math.min(seqs[row].length(), seqs[col].length()); for (int i = 0; i < width; i++) { char c1 = seqs[row].charAt(i); char c2 = seqs[col].charAt(i); int score = getPairwiseScore(c1, c2); total += score; } values[row][col] = total; } } return new Matrix(values); } }