X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fschemes%2FResidueProperties.java;h=0b62bb6d69e62c712a2b6f405339df9f34f6ee26;hb=c794c5033adeee182b03a5ea92c0a7495a29661f;hp=a4e648071e152d4462152cc79002300867b53e3b;hpb=6a99631de459c9ba52894900d08be0a2d6500488;p=jalview.git diff --git a/src/jalview/schemes/ResidueProperties.java b/src/jalview/schemes/ResidueProperties.java index a4e6480..0b62bb6 100755 --- a/src/jalview/schemes/ResidueProperties.java +++ b/src/jalview/schemes/ResidueProperties.java @@ -20,6 +20,8 @@ */ package jalview.schemes; +import jalview.analysis.GeneticCodes; + import java.awt.Color; import java.util.ArrayList; import java.util.Arrays; @@ -32,6 +34,13 @@ import java.util.Vector; public class ResidueProperties { + // alphabet names used in Hidden Markov Model files + public static final String ALPHABET_RNA = "RNA"; + + public static final String ALPHABET_DNA = "DNA"; + + public static final String ALPHABET_AMINO = "amino"; + // Stores residue codes/names and colours and other things public static final int[] aaIndex; // aaHash version 2.1.1 and below @@ -48,6 +57,9 @@ public class ResidueProperties // lookup from modified amino acid (e.g. MSE) to canonical form (e.g. MET) public static final Map modifications = new HashMap<>(); + // residue background frequencies across different alphabets + public static final Map> backgroundFrequencies = new HashMap<>(); + static { aaIndex = new int[255]; @@ -502,260 +514,6 @@ public class ResidueProperties 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<>(); - - /** - * all ambiguity codes for a given base - */ - public final static Hashtable> _ambiguityCodes = new Hashtable<>(); - - 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--; - } - } - } - } - // Stores residue codes/names and colours and other things public static Map> propHash = new Hashtable<>(); @@ -1148,55 +906,60 @@ 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 "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 @@ -2517,6 +2280,58 @@ public class ResidueProperties } + static + { + Map amino = new HashMap<>(); + amino.put('A', 0.0826f); + amino.put('Q', 0.0393f); + amino.put('L', 0.0965f); + amino.put('S', 0.0661f); + amino.put('R', 0.0553f); + amino.put('E', 0.0674f); + amino.put('K', 0.0582f); + amino.put('T', 0.0535f); + amino.put('N', 0.0406f); + amino.put('G', 0.0708f); + amino.put('M', 0.0241f); + amino.put('W', 0.0109f); + amino.put('D', 0.0546f); + amino.put('H', 0.0227f); + amino.put('F', 0.0386f); + amino.put('Y', 0.0292f); + amino.put('C', 0.0137f); + amino.put('I', 0.0593f); + amino.put('P', 0.0472f); + amino.put('V', 0.0686f); + backgroundFrequencies.put(ALPHABET_AMINO, amino); + // todo: these don't match https://www.ebi.ac.uk/uniprot/TrEMBLstats - what + // are they? + } + + // TODO get correct frequencies + + static + { + Map dna = new HashMap<>(); + dna.put('A', 0.25f); + dna.put('C', 0.25f); + dna.put('T', 0.25f); + dna.put('G', 0.25f); + backgroundFrequencies.put(ALPHABET_DNA, dna); + + } + + static + { + Map rna = new HashMap<>(); + rna.put('A', 0.25f); + rna.put('C', 0.25f); + rna.put('T', 0.25f); + rna.put('G', 0.25f); + backgroundFrequencies.put(ALPHABET_RNA, rna); + + } + public static String getCanonicalAminoAcid(String aA) { String canonical = modifications.get(aA); @@ -2525,6 +2340,10 @@ 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<>();