X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fschemes%2FResidueProperties.java;h=7ad35c3200b2d6d9ef4aa21c90004e2797107de1;hb=53fe06e7ae7a8c00ec902413391cea15362bdbf2;hp=751175d8025f607e7a433933ebb36134bdf0e44c;hpb=136c0793b90b72b928c4d77dc109dd5c644e00d3;p=jalview.git diff --git a/src/jalview/schemes/ResidueProperties.java b/src/jalview/schemes/ResidueProperties.java index 751175d..7ad35c3 100755 --- a/src/jalview/schemes/ResidueProperties.java +++ b/src/jalview/schemes/ResidueProperties.java @@ -20,6 +20,10 @@ */ package jalview.schemes; +import java.util.Locale; + +import jalview.analysis.GeneticCodes; + import java.awt.Color; import java.util.ArrayList; import java.util.Arrays; @@ -39,14 +43,14 @@ public class ResidueProperties public static final int[] purinepyrimidineIndex; - public static final Map aa3Hash = new HashMap(); + public static final Map aa3Hash = new HashMap<>(); - public static final Map aa2Triplet = new HashMap(); + public static final Map aa2Triplet = new HashMap<>(); - public static final Map nucleotideName = new HashMap(); + public static final Map nucleotideName = new HashMap<>(); // lookup from modified amino acid (e.g. MSE) to canonical form (e.g. MET) - public static final Map modifications = new HashMap(); + public static final Map modifications = new HashMap<>(); static { @@ -363,8 +367,11 @@ public class ResidueProperties }; // Added for PurinePyrimidineColourScheme - public static final Color[] purinepyrimidine = { - new Color(255, 131, 250), // A, G, R purines purplish/orchid + public static final Color[] purinepyrimidine = { new Color(255, 131, 250), // A, + // G, + // R + // purines + // purplish/orchid new Color(64, 224, 208), // C,U, T, Y pyrimidines turquoise Color.white, // all other nucleotides Color.white // Gap @@ -379,7 +386,7 @@ public class ResidueProperties Color.green, // Q Color.red, // E Color.magenta, // G - midBlue,// Color.red, // H + midBlue, // Color.red, // H Color.pink, // I Color.pink, // L midBlue, // K @@ -400,6 +407,125 @@ public class ResidueProperties Color.white // ' ' }; + /* + * flower, blossom, sunset, ocean colour schemes from geocos. + * See https://gecos.biotite-python.org/ + * https://raw.githubusercontent.com/biotite-dev/biotite/master/src/biotite/sequence/graphics/color_schemes/flower.json + * and https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-3526-6 + * (https://doi.org/10.1186/s12859-020-3526-6) + */ + public static final Color[] flower = { new Color(177, 138, 81), // A + new Color(131, 191, 241), // R + new Color(11, 206, 198), // N + new Color(1, 165, 120), // D + new Color(255, 87, 1), // C + new Color(114, 149, 174), // Q + new Color(45, 160, 161), // E + new Color(177, 194, 60), // G + new Color(1, 148, 249), // H + new Color(242, 118, 99), // I + new Color(223, 110, 117), // L + new Color(127, 195, 215), // K + new Color(254, 157, 175), // M + new Color(250, 85, 157), // F + new Color(79, 163, 42), // P + new Color(180, 189, 155), // S + new Color(210, 181, 118), // T + new Color(255, 45, 237), // W + new Color(201, 110, 207), // Y + new Color(253, 153, 123), // V + Color.white, // B + Color.white, // Z + Color.white, // X + Color.white, // - + Color.white, // * + Color.white // . + }; + + public static final Color[] blossom = { new Color(139, 196, 180), // A + new Color(252, 149, 2), // R + new Color(181, 194, 6), // N + new Color(95, 165, 5), // D + new Color(8, 147, 254), // C + new Color(191, 133, 39), // Q + new Color(219, 181, 1), // E + new Color(0, 211, 130), // G + new Color(255, 87, 1), // H + new Color(154, 186, 243), // I + new Color(205, 165, 220), // L + new Color(254, 165, 39), // K + new Color(245, 161, 184), // M + new Color(247, 79, 168), // F + new Color(16, 214, 49), // P + new Color(126, 157, 89), // S + new Color(0, 162, 156), // T + new Color(254, 8, 251), // W + new Color(255, 78, 122), // Y + new Color(135, 192, 228), // V + Color.white, // B + Color.white, // Z + Color.white, // X + Color.white, // - + Color.white, // * + Color.white // . + }; + + public static final Color[] sunset = { new Color(254, 160, 253), // A + new Color(133, 116, 106), // R + new Color(171, 200, 245), // N + new Color(46, 123, 190), // D + new Color(252, 12, 254), // C + new Color(140, 110, 129), // Q + new Color(103, 120, 146), // E + new Color(39, 153, 255), // G + new Color(219, 197, 142), // H + new Color(250, 33, 161), // I + new Color(224, 30, 130), // L + new Color(222, 190, 204), // K + new Color(209, 62, 123), // M + new Color(255, 56, 93), // F + new Color(87, 102, 249), // P + new Color(231, 180, 253), // S + new Color(166, 88, 183), // T + new Color(255, 55, 1), // W + new Color(203, 83, 57), // Y + new Color(254, 81, 184), // V + Color.white, // B + Color.white, // Z + Color.white, // X + Color.white, // - + Color.white, // * + Color.white // . + }; + + public static final Color[] ocean = { new Color(198, 202, 155), // A + new Color(12, 160, 168), // R + new Color(10, 223, 195), // N + new Color(76, 223, 161), // D + new Color(198, 129, 54), // C + new Color(139, 211, 209), // Q + new Color(96, 218, 201), // E + new Color(51, 165, 81), // G + new Color(0, 207, 254), // H + new Color(242, 186, 170), // I + new Color(187, 138, 131), // L + new Color(64, 160, 144), // K + new Color(164, 139, 136), // M + new Color(171, 136, 174), // F + new Color(175, 211, 101), // P + new Color(109, 155, 116), // S + new Color(141, 149, 102), // T + new Color(117, 138, 238), // W + new Color(186, 195, 252), // Y + new Color(233, 190, 164), // V + Color.white, // B + Color.white, // Z + Color.white, // X + Color.white, // - + Color.white, // * + Color.white // . + }; + // Dunno where I got these numbers from public static final double[] hyd2 = { 0.62, // A 0.29, // R @@ -426,9 +552,9 @@ public class ResidueProperties 0.0 // X }; - public static final double[] helix = { 1.42, 0.98, 0.67, 1.01, 0.70, - 1.11, 1.51, 0.57, 1.00, 1.08, 1.21, 1.16, 1.45, 1.13, 0.57, 0.77, - 0.83, 1.08, 0.69, 1.06, 0.84, 1.31, 1.00, 0.0 }; + public static final double[] helix = { 1.42, 0.98, 0.67, 1.01, 0.70, 1.11, + 1.51, 0.57, 1.00, 1.08, 1.21, 1.16, 1.45, 1.13, 0.57, 0.77, 0.83, + 1.08, 0.69, 1.06, 0.84, 1.31, 1.00, 0.0 }; public static final double helixmin = 0.57; @@ -450,9 +576,9 @@ public class ResidueProperties public static final double turnmax = 1.56; - public static final double[] buried = { 1.7, 0.1, 0.4, 0.4, 4.6, 0.3, - 0.3, 1.8, 0.8, 3.1, 2.4, 0.05, 1.9, 2.2, 0.6, 0.8, 0.7, 1.6, 0.5, - 2.9, 0.4, 0.3, 1.358, 0.00 }; + public static final double[] buried = { 1.7, 0.1, 0.4, 0.4, 4.6, 0.3, 0.3, + 1.8, 0.8, 3.1, 2.4, 0.05, 1.9, 2.2, 0.6, 0.8, 0.7, 1.6, 0.5, 2.9, 0.4, + 0.3, 1.358, 0.00 }; public static final double buriedmin = 0.05; @@ -493,285 +619,35 @@ public class ResidueProperties * Color.white, // R Color.white, // Y Color.white, // N Color.white, // Gap */ - public static List STOP = Arrays.asList("TGA", "TAA", "TAG"); - - public static String START = "ATG"; - - /** - * Nucleotide Ambiguity Codes - */ - public static final Map ambiguityCodes = new Hashtable(); - - /** - * Codon triplets with additional symbols for unambiguous codons that include - * ambiguity codes - */ - public static final Hashtable codonHash2 = new Hashtable(); + public static String STOP = "STOP"; - /** - * all ambiguity codes for a given base - */ - public final static Hashtable> _ambiguityCodes = new Hashtable>(); + public static List STOP_CODONS = Arrays.asList("TGA", "TAA", + "TAG"); - static - { - /* - * Ambiguity codes as per http://www.chem.qmul.ac.uk/iubmb/misc/naseq.html - */ - ambiguityCodes.put("R", new String[] { "A", "G" }); - ambiguityCodes.put("Y", new String[] { "T", "C" }); - ambiguityCodes.put("W", new String[] { "A", "T" }); - ambiguityCodes.put("S", new String[] { "G", "C" }); - ambiguityCodes.put("M", new String[] { "A", "C" }); - ambiguityCodes.put("K", new String[] { "G", "T" }); - ambiguityCodes.put("H", new String[] { "A", "T", "C" }); - ambiguityCodes.put("B", new String[] { "G", "T", "C" }); - ambiguityCodes.put("V", new String[] { "G", "A", "C" }); - ambiguityCodes.put("D", new String[] { "G", "A", "T" }); - ambiguityCodes.put("N", new String[] { "G", "A", "T", "C" }); - - // Now build codon translation table - codonHash2.put("AAA", "K"); - codonHash2.put("AAG", "K"); - codonHash2.put("AAC", "N"); - codonHash2.put("AAT", "N"); - - codonHash2.put("CAA", "Q"); - codonHash2.put("CAG", "Q"); - codonHash2.put("CAC", "H"); - codonHash2.put("CAT", "H"); - - codonHash2.put("GAA", "E"); - codonHash2.put("GAG", "E"); - codonHash2.put("GAC", "D"); - codonHash2.put("GAT", "D"); - - codonHash2.put("TAC", "Y"); - codonHash2.put("TAT", "Y"); - - codonHash2.put("ACA", "T"); - codonHash2.put("ACC", "T"); - codonHash2.put("ACT", "T"); - codonHash2.put("ACG", "T"); - - codonHash2.put("CCA", "P"); - codonHash2.put("CCG", "P"); - codonHash2.put("CCC", "P"); - codonHash2.put("CCT", "P"); - - codonHash2.put("GCA", "A"); - codonHash2.put("GCG", "A"); - codonHash2.put("GCC", "A"); - codonHash2.put("GCT", "A"); - - codonHash2.put("TCA", "S"); - codonHash2.put("TCG", "S"); - codonHash2.put("TCC", "S"); - codonHash2.put("TCT", "S"); - codonHash2.put("AGC", "S"); - codonHash2.put("AGT", "S"); - - codonHash2.put("AGA", "R"); - codonHash2.put("AGG", "R"); - codonHash2.put("CGA", "R"); - codonHash2.put("CGG", "R"); - codonHash2.put("CGC", "R"); - codonHash2.put("CGT", "R"); - - codonHash2.put("GGA", "G"); - codonHash2.put("GGG", "G"); - codonHash2.put("GGC", "G"); - codonHash2.put("GGT", "G"); - - codonHash2.put("TGA", "*"); - codonHash2.put("TAA", "*"); - codonHash2.put("TAG", "*"); - - codonHash2.put("TGG", "W"); - - codonHash2.put("TGC", "C"); - codonHash2.put("TGT", "C"); - - codonHash2.put("ATA", "I"); - codonHash2.put("ATC", "I"); - codonHash2.put("ATT", "I"); - - codonHash2.put("ATG", "M"); - - codonHash2.put("CTA", "L"); - codonHash2.put("CTG", "L"); - codonHash2.put("CTC", "L"); - codonHash2.put("CTT", "L"); - codonHash2.put("TTA", "L"); - codonHash2.put("TTG", "L"); - - codonHash2.put("GTA", "V"); - codonHash2.put("GTG", "V"); - codonHash2.put("GTC", "V"); - codonHash2.put("GTT", "V"); - - codonHash2.put("TTC", "F"); - codonHash2.put("TTT", "F"); - - buildAmbiguityCodonSet(); - } - - /** - * programmatic generation of codons including ambiguity codes - */ - public static void buildAmbiguityCodonSet() - { - if (_ambiguityCodes.size() > 0) - { - System.err - .println("Ignoring multiple calls to buildAmbiguityCodonSet"); - return; - } - // Invert the ambiguity code set - for (Map.Entry acode : ambiguityCodes.entrySet()) - { - for (String r : acode.getValue()) - { - List codesfor = _ambiguityCodes.get(r); - if (codesfor == null) - { - _ambiguityCodes.put(r, codesfor = new ArrayList()); - } - if (!codesfor.contains(acode.getKey())) - { - codesfor.add(acode.getKey()); - } - else - { - System.err - .println("Inconsistency in the IUBMB ambiguity code nomenclature table: collision for " - + acode.getKey() + " in residue " + r); - } - } - } - // and programmatically add in the ambiguity codes that yield the same amino - // acid - String[] unambcodons = codonHash2.keySet().toArray( - new String[codonHash2.size()]); - for (String codon : unambcodons) - { - String residue = codonHash2.get(codon); - String acodon[][] = new String[codon.length()][]; - for (int i = 0, iSize = codon.length(); i < iSize; i++) - { - String _ac = "" + codon.charAt(i); - List acodes = _ambiguityCodes.get(_ac); - if (acodes != null) - { - acodon[i] = acodes.toArray(new String[acodes.size()]); - } - else - { - acodon[i] = new String[] {}; - } - } - // enumerate all combinations and test for veracity of translation - int tpos[] = new int[codon.length()], cpos[] = new int[codon.length()]; - for (int i = 0; i < tpos.length; i++) - { - tpos[i] = -1; - } - tpos[acodon.length - 1] = 0; - int ipos, j; - while (tpos[0] < acodon[0].length) - { - // make all codons for this combination - char allres[][] = new char[tpos.length][]; - String _acodon = ""; - for (ipos = 0; ipos < tpos.length; ipos++) - { - if (acodon[ipos].length == 0 || tpos[ipos] < 0) - { - _acodon += codon.charAt(ipos); - allres[ipos] = new char[] { codon.charAt(ipos) }; - } - else - { - _acodon += acodon[ipos][tpos[ipos]]; - String[] altbase = ambiguityCodes.get(acodon[ipos][tpos[ipos]]); - allres[ipos] = new char[altbase.length]; - j = 0; - for (String ab : altbase) - { - allres[ipos][j++] = ab.charAt(0); - } - } - } - // test all codons for this combination - for (ipos = 0; ipos < cpos.length; ipos++) - { - cpos[ipos] = 0; - } - boolean valid = true; - do - { - String _codon = ""; - for (j = 0; j < cpos.length; j++) - { - _codon += allres[j][cpos[j]]; - } - String tr = codonHash2.get(_codon); - if (valid = (tr != null && tr.equals(residue))) - { - // advance to next combination - ipos = acodon.length - 1; - while (++cpos[ipos] >= allres[ipos].length && ipos > 0) - { - cpos[ipos] = 0; - ipos--; - } - } - } while (valid && cpos[0] < allres[0].length); - if (valid) - { - // Add this to the set of codons we will translate - // System.out.println("Adding ambiguity codon: " + _acodon + " for " - // + residue); - codonHash2.put(_acodon, residue); - } - else - { - // System.err.println("Rejecting ambiguity codon: " + _acodon - // + " for " + residue); - } - // next combination - ipos = acodon.length - 1; - while (++tpos[ipos] >= acodon[ipos].length && ipos > 0) - { - tpos[ipos] = -1; - ipos--; - } - } - } - } + public static String START = "ATG"; // Stores residue codes/names and colours and other things - public static Map> propHash = new Hashtable>(); + public static Map> propHash = new Hashtable<>(); - public static Map hydrophobic = new Hashtable(); + public static Map hydrophobic = new Hashtable<>(); - public static Map polar = new Hashtable(); + public static Map polar = new Hashtable<>(); - public static Map small = new Hashtable(); + public static Map small = new Hashtable<>(); - public static Map positive = new Hashtable(); + public static Map positive = new Hashtable<>(); - public static Map negative = new Hashtable(); + public static Map negative = new Hashtable<>(); - public static Map charged = new Hashtable(); + public static Map charged = new Hashtable<>(); - public static Map aromatic = new Hashtable(); + public static Map aromatic = new Hashtable<>(); - public static Map aliphatic = new Hashtable(); + public static Map aliphatic = new Hashtable<>(); - public static Map tiny = new Hashtable(); + public static Map tiny = new Hashtable<>(); - public static Map proline = new Hashtable(); + public static Map proline = new Hashtable<>(); static { @@ -924,7 +800,7 @@ public class ResidueProperties charged.put("Q", ZERO); charged.put("D", ONE); charged.put("N", ZERO); // Asparagine is polar but not - // charged. + // charged. // Alternative would be charged and // negative (in basic form)? charged.put("S", ZERO); @@ -1053,7 +929,9 @@ public class ResidueProperties } static { - int[][] propMatrixF = new int[maxProteinIndex][maxProteinIndex], propMatrixPos = new int[maxProteinIndex][maxProteinIndex], propMatrixEpos = new int[maxProteinIndex][maxProteinIndex]; + int[][] propMatrixF = new int[maxProteinIndex][maxProteinIndex], + propMatrixPos = new int[maxProteinIndex][maxProteinIndex], + propMatrixEpos = new int[maxProteinIndex][maxProteinIndex]; for (int i = 0; i < maxProteinIndex; i++) { int maxF = 0, maxP = 0, maxEP = 0; @@ -1140,55 +1018,60 @@ public class ResidueProperties public static String codonTranslate(String lccodon) { - String cdn = codonHash2.get(lccodon.toUpperCase()); - if ("*".equals(cdn)) + String peptide = GeneticCodes.getInstance().getStandardCodeTable() + .translate(lccodon); + if ("*".equals(peptide)) { return "STOP"; } - return cdn; + return peptide; } - public static Hashtable toDssp3State; + /* + * lookup of (A-Z) alternative secondary structure symbols' + * equivalents in DSSP3 notation + */ + private static char[] toDssp3State; static { - toDssp3State = new Hashtable(); - toDssp3State.put("H", "H"); - toDssp3State.put("E", "E"); - toDssp3State.put("C", " "); - toDssp3State.put(" ", " "); - toDssp3State.put("T", " "); - toDssp3State.put("B", "E"); - toDssp3State.put("G", "H"); - toDssp3State.put("I", "H"); - toDssp3State.put("X", " "); + toDssp3State = new char[9]; // for 'A'-'I'; extend if needed + Arrays.fill(toDssp3State, ' '); + toDssp3State['B' - 'A'] = 'E'; + toDssp3State['E' - 'A'] = 'E'; + toDssp3State['G' - 'A'] = 'H'; + toDssp3State['H' - 'A'] = 'H'; + toDssp3State['I' - 'A'] = 'H'; } /** * translate from other dssp secondary structure alphabets to 3-state * - * @param ssstring - * @return ssstring as a three-state secondary structure assignment. + * @param ssString + * @return ssstring */ - public static String getDssp3state(String ssstring) + public static String getDssp3state(String ssString) { - if (ssstring == null) + if (ssString == null) { return null; } - StringBuffer ss = new StringBuffer(); - for (int i = 0; i < ssstring.length(); i++) + int lookupSize = toDssp3State.length; + int len = ssString.length(); + char[] trans = new char[len]; + for (int i = 0; i < len; i++) { - String ssc = ssstring.substring(i, i + 1); - if (toDssp3State.containsKey(ssc)) + char c = ssString.charAt(i); + int index = c - 'A'; + if (index < 0 || index >= lookupSize) { - ss.append(toDssp3State.get(ssc)); + trans[i] = ' '; } else { - ss.append(" "); + trans[i] = toDssp3State[index]; } } - return ss.toString(); + return new String(trans); } static @@ -2517,9 +2400,13 @@ public class ResidueProperties // main method generates perl representation of residue property hash // / cut here + /** + * @j2sIgnore + * @param args + */ public static void main(String[] args) { - Hashtable> aaProps = new Hashtable>(); + Hashtable> aaProps = new Hashtable<>(); System.out.println("my %aa = {"); // invert property hashes for (String pname : propHash.keySet()) @@ -2530,7 +2417,7 @@ public class ResidueProperties Vector aprops = aaProps.get(rname); if (aprops == null) { - aprops = new Vector(); + aprops = new Vector<>(); aaProps.put(rname, aprops); } Integer hasprop = phash.get(rname); @@ -2572,7 +2459,7 @@ public class ResidueProperties public static List getResidues(boolean forNucleotide, boolean includeAmbiguous) { - List result = new ArrayList(); + List result = new ArrayList<>(); if (forNucleotide) { for (String nuc : nucleotideName.keySet()) @@ -2582,7 +2469,7 @@ public class ResidueProperties { continue; } - nuc = nuc.toUpperCase(); + nuc = nuc.toUpperCase(Locale.ROOT); if (!result.contains(nuc)) { result.add(nuc); @@ -2601,7 +2488,7 @@ public class ResidueProperties { continue; } - res = res.toUpperCase(); + res = res.toUpperCase(Locale.ROOT); if (!result.contains(res)) { result.add(res); @@ -2625,8 +2512,8 @@ public class ResidueProperties { return '0'; } - Integer index = ResidueProperties.aa3Hash.get(threeLetterCode - .toUpperCase()); + Integer index = ResidueProperties.aa3Hash + .get(threeLetterCode.toUpperCase(Locale.ROOT)); return index == null ? '0' : aa[index].charAt(0); } }