X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fschemes%2FResidueProperties.java;h=092971d762ae5f7097cd599d6135115b5d1d09f9;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hp=1780a4acf50bcdbac7b3e09768eeb69aed95a065;hpb=47168f025aefdaa044802bd5f8f510ffe43a4808;p=jalview.git diff --git a/src/jalview/schemes/ResidueProperties.java b/src/jalview/schemes/ResidueProperties.java index 1780a4a..092971d 100755 --- a/src/jalview/schemes/ResidueProperties.java +++ b/src/jalview/schemes/ResidueProperties.java @@ -1,6 +1,6 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2) - * Copyright (C) 2014 The Jalview Authors + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9) + * Copyright (C) 2015 The Jalview Authors * * This file is part of Jalview. * @@ -20,16 +20,22 @@ */ package jalview.schemes; +import jalview.analysis.scoremodels.FeatureScoreModel; import jalview.analysis.scoremodels.PIDScoreModel; import jalview.api.analysis.ScoreModelI; -import java.util.*; +import java.awt.Color; +import java.util.ArrayList; +import java.util.Enumeration; +import java.util.HashMap; +import java.util.Hashtable; import java.util.List; -import java.awt.*; +import java.util.Map; +import java.util.Vector; public class ResidueProperties { - public static Hashtable scoreMatrices = new Hashtable(); + public static Hashtable scoreMatrices = new Hashtable(); // Stores residue codes/names and colours and other things public static final int[] aaIndex; // aaHash version 2.1.1 and below @@ -38,11 +44,14 @@ public class ResidueProperties public static final int[] purinepyrimidineIndex; - public static final Hashtable aa3Hash = new Hashtable(); + public static final Map aa3Hash = new HashMap(); - public static final Hashtable aa2Triplet = new Hashtable(); + public static final Map aa2Triplet = new HashMap(); - public static final Hashtable nucleotideName = new Hashtable(); + 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(); static { @@ -289,9 +298,9 @@ public class ResidueProperties aa2Triplet.put("v", "VAL"); } - public static final String[] aa = - { "A", "R", "N", "D", "C", "Q", "E", "G", "H", "I", "L", "K", "M", "F", - "P", "S", "T", "W", "Y", "V", "B", "Z", "X", "_", "*", ".", " " }; + public static final String[] aa = { "A", "R", "N", "D", "C", "Q", "E", + "G", "H", "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V", "B", + "Z", "X", "_", "*", ".", " " }; public static final Color midBlue = new Color(100, 100, 255); @@ -311,8 +320,8 @@ public class ResidueProperties scaleColours.addElement(Color.white); } - public static final Color[] taylor = - { new Color(204, 255, 0), // A Greenish-yellowy-yellow + public static final Color[] taylor = { new Color(204, 255, 0), // A + // Greenish-yellowy-yellow new Color(0, 0, 255), // R Blueish-bluey-blue new Color(204, 0, 255), // N Blueish-reddy-blue new Color(255, 0, 0), // D Reddish-reddy-red @@ -340,8 +349,7 @@ public class ResidueProperties Color.white // . }; - public static final Color[] nucleotide = - { new Color(100, 247, 63), // A + public static final Color[] nucleotide = { new Color(100, 247, 63), // A new Color(255, 179, 64), // C new Color(235, 65, 60), // G new Color(60, 136, 238), // T @@ -355,16 +363,15 @@ 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 }; // Zappo - public static final Color[] zappo = - { Color.pink, // A + public static final Color[] zappo = { Color.pink, // A midBlue, // R Color.green, // N Color.red, // D @@ -394,8 +401,7 @@ public class ResidueProperties }; // Dunno where I got these numbers from - public static final double[] hyd2 = - { 0.62, // A + public static final double[] hyd2 = { 0.62, // A 0.29, // R -0.90, // N -0.74, // D @@ -420,34 +426,33 @@ 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; public static final double helixmax = 1.51; - public static final double[] strand = - { 0.83, 0.93, 0.89, 0.54, 1.19, 1.10, 0.37, 0.75, 0.87, 1.60, 1.30, 0.74, - 1.05, 1.38, 0.55, 0.75, 1.19, 1.37, 1.47, 1.70, 0.72, 0.74, 1.0, 0.0 }; + public static final double[] strand = { 0.83, 0.93, 0.89, 0.54, 1.19, + 1.10, 0.37, 0.75, 0.87, 1.60, 1.30, 0.74, 1.05, 1.38, 0.55, 0.75, + 1.19, 1.37, 1.47, 1.70, 0.72, 0.74, 1.0, 0.0 }; public static final double strandmin = 0.37; public static final double strandmax = 1.7; - public static final double[] turn = - { 0.66, 0.95, 1.56, 1.46, 1.19, 0.98, 0.74, 1.56, 0.95, 0.47, 0.59, 1.01, - 0.60, 0.60, 1.52, 1.43, 0.96, 0.96, 1.14, 0.50, 1.51, 0.86, 1.00, 0, - 0 }; + public static final double[] turn = { 0.66, 0.95, 1.56, 1.46, 1.19, 0.98, + 0.74, 1.56, 0.95, 0.47, 0.59, 1.01, 0.60, 0.60, 1.52, 1.43, 0.96, + 0.96, 1.14, 0.50, 1.51, 0.86, 1.00, 0, 0 }; public static final double turnmin = 0.47; 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; @@ -456,9 +461,9 @@ public class ResidueProperties // This is hydropathy index // Kyte, J., and Doolittle, R.F., J. Mol. Biol. // 1157, 105-132, 1982 - public static final double[] hyd = - { 1.8, -4.5, -3.5, -3.5, 2.5, -3.5, -3.5, -0.4, -3.2, 4.5, 3.8, -3.9, - 1.9, 2.8, -1.6, -0.8, -0.7, -0.9, -1.3, 4.2, -3.5, -3.5, -0.49, 0.0 }; + public static final double[] hyd = { 1.8, -4.5, -3.5, -3.5, 2.5, -3.5, + -3.5, -0.4, -3.2, 4.5, 3.8, -3.9, 1.9, 2.8, -1.6, -0.8, -0.7, -0.9, + -1.3, 4.2, -3.5, -3.5, -0.49, 0.0 }; public static final double hydmax = 4.5; @@ -466,8 +471,7 @@ public class ResidueProperties // public static final double hydmax = 1.38; // public static final double hydmin = -2.53; - private static final int[][] BLOSUM62 = - { + private static final int[][] BLOSUM62 = { { 4, -1, -2, -2, 0, -1, -1, 0, -2, -1, -1, -1, -1, -2, -1, 1, 0, -3, -2, 0, -2, -1, 0, -4 }, { -1, 5, 0, -2, -3, 1, 0, -2, 0, -3, -2, 2, -1, -3, -2, -1, -1, -3, @@ -517,8 +521,7 @@ public class ResidueProperties { -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, -4, 1 }, }; - static final int[][] PAM250 = - { + static final int[][] PAM250 = { { 2, -2, 0, 0, -2, 0, 0, 1, -1, -1, -2, -1, -1, -3, 1, 1, 1, -6, -3, 0, 0, 0, 0, -8 }, { -2, 6, 0, -1, -4, 1, -1, -3, 2, -2, -3, 3, 0, -4, 0, 0, -1, 2, -4, @@ -594,9 +597,7 @@ public class ResidueProperties // treats T and U identically. R and Y weak equivalence with AG and CTU. // N matches any other base weakly // - static final int[][] DNA = - { - { 10, -8, -8, -8, -8, 1, 1, 1, -8, 1, 1 }, // A + static final int[][] DNA = { { 10, -8, -8, -8, -8, 1, 1, 1, -8, 1, 1 }, // A { -8, 10, -8, -8, -8, 1, 1, -8, 1, 1, 1 }, // C { -8, -8, 10, -8, -8, 1, 1, 1, -8, 1, 1 }, // G { -8, -8, -8, 10, 10, 1, 1, -8, 1, 1, 1 }, // T @@ -619,57 +620,58 @@ public class ResidueProperties } - public static final Color[] pidColours = - { midBlue, new Color(153, 153, 255), + public static final Color[] pidColours = { midBlue, + new Color(153, 153, 255), // Color.lightGray, new Color(204, 204, 255), }; - public static final float[] pidThresholds = - { 80, 60, 40, }; + public static final float[] pidThresholds = { 80, 60, 40, }; + + public static Map> codonHash = new HashMap>(); - public static Hashtable codonHash = new Hashtable(); + private static List Lys = new ArrayList(); - public static Vector Lys = new Vector(); + private static List Asn = new ArrayList(); - public static Vector Asn = new Vector(); + private static List Gln = new ArrayList(); - public static Vector Gln = new Vector(); + private static List His = new ArrayList(); - public static Vector His = new Vector(); + private static List Glu = new ArrayList(); - public static Vector Glu = new Vector(); + private static List Asp = new ArrayList(); - public static Vector Asp = new Vector(); + private static List Tyr = new ArrayList(); - public static Vector Tyr = new Vector(); + private static List Thr = new ArrayList(); - public static Vector Thr = new Vector(); + private static List Pro = new ArrayList(); - public static Vector Pro = new Vector(); + private static List Ala = new ArrayList(); - public static Vector Ala = new Vector(); + private static List Ser = new ArrayList(); - public static Vector Ser = new Vector(); + private static List Arg = new ArrayList(); - public static Vector Arg = new Vector(); + private static List Gly = new ArrayList(); - public static Vector Gly = new Vector(); + private static List Trp = new ArrayList(); - public static Vector Trp = new Vector(); + private static List Cys = new ArrayList(); - public static Vector Cys = new Vector(); + private static List Ile = new ArrayList(); - public static Vector Ile = new Vector(); + private static List Met = new ArrayList(); - public static Vector Met = new Vector(); + private static List Leu = new ArrayList(); - public static Vector Leu = new Vector(); + private static List Val = new ArrayList(); - public static Vector Val = new Vector(); + private static List Phe = new ArrayList(); - public static Vector Phe = new Vector(); + public static List STOP = new ArrayList(); - public static Vector STOP = new Vector(); + public static String START = "ATG"; static { @@ -697,121 +699,38 @@ public class ResidueProperties } /** - * Nucleotide Ambiguity Codes + * Nucleotide Ambiguity Codes */ - public static final Hashtable ambiguityCodes=new Hashtable(); + public static final Map ambiguityCodes = new Hashtable(); + /** - * Codon triplets with additional symbols for unambiguous codons that include ambiguity codes + * Codon triplets with additional symbols for unambiguous codons that include + * ambiguity codes */ - public static final Hashtable codonHash2 = new Hashtable(); - + public static final Hashtable codonHash2 = new Hashtable(); + /** * all ambiguity codes for a given base */ - public final static Hashtable> _ambiguityCodes = new Hashtable>(); - + public final static Hashtable> _ambiguityCodes = new Hashtable>(); static { - /** - * 3.2. Purine (adenine or guanine): R - * - * R is the symbol previously recommended [1]. + /* + * Ambiguity codes as per http://www.chem.qmul.ac.uk/iubmb/misc/naseq.html */ - ambiguityCodes.put("R", new String[] - { "A", "G" }); + 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" }); - /** - * 3.3. Pyrimidine (thymine or cytosine): Y - * - * Y is the symbol previously recommended [1]. - */ - ambiguityCodes.put("Y", new String[] - { "T", "C" }); - /** - * 3.4. Adenine or thymine: W - * - * Although several diverse symbols have been used for this pair, (and for - * the reciprocal pair G+C), only two symbols have a rational basis, L and - * W: L derives from DNA density (light; G+C - heavy - would thus be H); W - * derives from the strength of the hydrogen bonding interaction between the - * base pairs (weak for A+T: G +C - strong - would thus be S). However, the - * system recommended for the three-base series (not-A = B, etc., see below, - * section 3.8) rules out H as this would be not-G. W is thus recommended. - */ - ambiguityCodes.put("W", new String[] - { "A", "T" }); - /** - * 3.5. Guanine or cytosine: S - * - * The choice of this symbol is discussed above in section 3.4. - */ - ambiguityCodes.put("S", new String[] - { "G", "C" }); - /** - * 3.6. Adenine or cytosine: M - * - * There are few common features between A and C. The presence of an NH2 - * group in similar positions on both bases (Fig. 1) makes possible a - * logically derived symbol. A and N being ruled out, M (from aMino) is - * recommended. - * - * - * Fig. 1. Origin of the symbols M and K The four bases are drawn so as to - * show the relationship between adenine and cytosine on the one hand, which - * both have aMino groups at the ring position most distant from the point - * of attachment to the sugar, and between guanine and thymine on the other, - * which both have Keto groups at the corresponding position. The ring atoms - * are numbered as recommended [24-26], although for the present purpose - * this has the disadvantage of giving discordant numbers to the - * corresponding positions. - */ - ambiguityCodes.put("M", new String[] - { "A", "C" }); - /** - * 3.7. Guanine or thymine: K By analogy with A and C (section 3.6), both G - * and T have Keto groups in similar positions (Fig. 1). - */ - ambiguityCodes.put("K", new String[] - { "G", "T" }); - /** - * 3.8. Adenine or thymine or cytosine: H - * - * Not-G is the most simple means of memorising this combination and symbols - * logically related to G were examined. F and H would both be suitable, as - * the letters before and after G in the alphabet, but A would have no - * equivalent to F. The use of H has historical precedence [2]. - */ - ambiguityCodes.put("H", new String[] - { "A", "T", "C" }); - /** - * 3.9. Guanine or cytosine or thymine: B - * - * Not-A as above (section 3.8). - */ - ambiguityCodes.put("B", new String[] - { "G", "T", "C" }); - /** - * 3.10. Guanine or adenine or cytosine: V - * - * Not-T by analogy with not-G (section 3.8) would be U but this is ruled - * out to eliminate confusion with uracil. V is the next logical choice. - * Note that T and U may in some cases be considered to be synonyms. - */ - ambiguityCodes.put("V", new String[] - { "G", "A", "C" }); - /** - * 3.11. Guanine or adenine or thymine: D - * - * Not-C as above (section 3.8). - */ - ambiguityCodes.put("D", new String[] - { "G", "A", "T" }); - /** - * 3.12. Guanine or adenine or thymine or cytosine: N - */ - ambiguityCodes.put("R", new String[] - { "G", "A", "T", "C" }); // Now build codon translation table codonHash2.put("AAA", "K"); codonHash2.put("AAG", "K"); @@ -894,10 +813,10 @@ public class ResidueProperties codonHash2.put("TTC", "F"); codonHash2.put("TTT", "F"); - + buildAmbiguityCodonSet(); } - + /** * programmatic generation of codons including ambiguity codes */ @@ -933,7 +852,8 @@ public class ResidueProperties } // and programmatically add in the ambiguity codes that yield the same amino // acid - String[] unambcodons = codonHash2.keySet().toArray(new String[codonHash2.size()]); + String[] unambcodons = codonHash2.keySet().toArray( + new String[codonHash2.size()]); for (String codon : unambcodons) { String residue = codonHash2.get(codon); @@ -948,8 +868,7 @@ public class ResidueProperties } else { - acodon[i] = new String[] - {}; + acodon[i] = new String[] {}; } } // enumerate all combinations and test for veracity of translation @@ -968,11 +887,10 @@ public class ResidueProperties char _anuc; for (ipos = 0; ipos < tpos.length; ipos++) { - if (acodon[ipos].length==0 || tpos[ipos] < 0) + if (acodon[ipos].length == 0 || tpos[ipos] < 0) { _acodon += codon.charAt(ipos); - allres[ipos] = new char[] - { codon.charAt(ipos) }; + allres[ipos] = new char[] { codon.charAt(ipos) }; } else { @@ -1000,7 +918,7 @@ public class ResidueProperties _codon += allres[j][cpos[j]]; } String tr = codonHash2.get(_codon); - if (valid = (tr!=null && tr.equals(residue))) + if (valid = (tr != null && tr.equals(residue))) { // advance to next combination ipos = acodon.length - 1; @@ -1014,14 +932,14 @@ public class ResidueProperties if (valid) { // Add this to the set of codons we will translate -// System.out.println("Adding ambiguity codon: " + _acodon + " for " -// + residue); + // System.out.println("Adding ambiguity codon: " + _acodon + " for " + // + residue); codonHash2.put(_acodon, residue); } else { -// System.err.println("Rejecting ambiguity codon: " + _acodon -// + " for " + residue); + // System.err.println("Rejecting ambiguity codon: " + _acodon + // + " for " + residue); } // next combination ipos = acodon.length - 1; @@ -1037,87 +955,87 @@ public class ResidueProperties static { - Lys.addElement("AAA"); - Lys.addElement("AAG"); - Asn.addElement("AAC"); - Asn.addElement("AAT"); - - Gln.addElement("CAA"); - Gln.addElement("CAG"); - His.addElement("CAC"); - His.addElement("CAT"); - - Glu.addElement("GAA"); - Glu.addElement("GAG"); - Asp.addElement("GAC"); - Asp.addElement("GAT"); - - Tyr.addElement("TAC"); - Tyr.addElement("TAT"); - - Thr.addElement("ACA"); - Thr.addElement("ACG"); - Thr.addElement("ACC"); - Thr.addElement("ACT"); - - Pro.addElement("CCA"); - Pro.addElement("CCG"); - Pro.addElement("CCC"); - Pro.addElement("CCT"); - - Ala.addElement("GCA"); - Ala.addElement("GCG"); - Ala.addElement("GCC"); - Ala.addElement("GCT"); - - Ser.addElement("TCA"); - Ser.addElement("TCG"); - Ser.addElement("TCC"); - Ser.addElement("TCT"); - Ser.addElement("AGC"); - Ser.addElement("AGT"); - - Arg.addElement("AGA"); - Arg.addElement("AGG"); - Arg.addElement("CGA"); - Arg.addElement("CGG"); - Arg.addElement("CGC"); - Arg.addElement("CGT"); - - Gly.addElement("GGA"); - Gly.addElement("GGG"); - Gly.addElement("GGC"); - Gly.addElement("GGT"); - - STOP.addElement("TGA"); - STOP.addElement("TAA"); - STOP.addElement("TAG"); - - Trp.addElement("TGG"); - - Cys.addElement("TGC"); - Cys.addElement("TGT"); - - Ile.addElement("ATA"); - Ile.addElement("ATC"); - Ile.addElement("ATT"); - - Met.addElement("ATG"); - - Leu.addElement("CTA"); - Leu.addElement("CTG"); - Leu.addElement("CTC"); - Leu.addElement("CTT"); - Leu.addElement("TTA"); - Leu.addElement("TTG"); - - Val.addElement("GTA"); - Val.addElement("GTG"); - Val.addElement("GTC"); - Val.addElement("GTT"); - - Phe.addElement("TTC"); - Phe.addElement("TTT"); + Lys.add("AAA"); + Lys.add("AAG"); + Asn.add("AAC"); + Asn.add("AAT"); + + Gln.add("CAA"); + Gln.add("CAG"); + His.add("CAC"); + His.add("CAT"); + + Glu.add("GAA"); + Glu.add("GAG"); + Asp.add("GAC"); + Asp.add("GAT"); + + Tyr.add("TAC"); + Tyr.add("TAT"); + + Thr.add("ACA"); + Thr.add("ACG"); + Thr.add("ACC"); + Thr.add("ACT"); + + Pro.add("CCA"); + Pro.add("CCG"); + Pro.add("CCC"); + Pro.add("CCT"); + + Ala.add("GCA"); + Ala.add("GCG"); + Ala.add("GCC"); + Ala.add("GCT"); + + Ser.add("TCA"); + Ser.add("TCG"); + Ser.add("TCC"); + Ser.add("TCT"); + Ser.add("AGC"); + Ser.add("AGT"); + + Arg.add("AGA"); + Arg.add("AGG"); + Arg.add("CGA"); + Arg.add("CGG"); + Arg.add("CGC"); + Arg.add("CGT"); + + Gly.add("GGA"); + Gly.add("GGG"); + Gly.add("GGC"); + Gly.add("GGT"); + + STOP.add("TGA"); + STOP.add("TAA"); + STOP.add("TAG"); + + Trp.add("TGG"); + + Cys.add("TGC"); + Cys.add("TGT"); + + Ile.add("ATA"); + Ile.add("ATC"); + Ile.add("ATT"); + + Met.add("ATG"); + + Leu.add("CTA"); + Leu.add("CTG"); + Leu.add("CTC"); + Leu.add("CTT"); + Leu.add("TTA"); + Leu.add("TTG"); + + Val.add("GTA"); + Val.add("GTG"); + Val.add("GTC"); + Val.add("GTT"); + + Phe.add("TTC"); + Phe.add("TTT"); } // Stores residue codes/names and colours and other things @@ -1422,63 +1340,76 @@ public class ResidueProperties } static { - int[][] propMatrixF = new int[maxProteinIndex][maxProteinIndex], - propMatrixPos = new int[maxProteinIndex][maxProteinIndex], - propMatrixEpos = new int[maxProteinIndex][maxProteinIndex]; - for (int i=0;ii) { - ic+=aa[i]; + int maxF = 0, maxP = 0, maxEP = 0; + String ic = ""; + if (aa.length > i) + { + ic += aa[i]; } - else {ic = "-";} - for (int j=i+1;jj) { - jc+=aa[j]; + String jc = ""; + if (aa.length > j) + { + jc += aa[j]; + } + else + { + jc = "-"; } - else {jc = "-";} - propMatrixF[i][j]=0; - propMatrixPos[i][j]=0; - propMatrixEpos[i][j]=0; - for (Enumeration en= (Enumeration)propHash.keys(); en.hasMoreElements(); ) + propMatrixF[i][j] = 0; + propMatrixPos[i][j] = 0; + propMatrixEpos[i][j] = 0; + for (Enumeration en = propHash.keys(); en.hasMoreElements();) { String ph = en.nextElement(); - Map pph=(Map)propHash.get(ph); - if (pph.get(ic)!=null && pph.get(jc)!=null) { - int icp=pph.get(ic).intValue(),jcp=pph.get(jc).intValue(); + Map pph = (Map) propHash + .get(ph); + if (pph.get(ic) != null && pph.get(jc) != null) + { + int icp = pph.get(ic).intValue(), jcp = pph.get(jc).intValue(); // Still working on these definitions. - propMatrixPos[i][j] += icp == jcp && icp>0 ? 2 : 0; - propMatrixPos[j][i] += icp == jcp && icp>0 ? 2 : 0; + propMatrixPos[i][j] += icp == jcp && icp > 0 ? 2 : 0; + propMatrixPos[j][i] += icp == jcp && icp > 0 ? 2 : 0; propMatrixF[i][j] += icp == jcp ? 2 : 0; propMatrixF[j][i] += icp == jcp ? 2 : 0; - propMatrixEpos[i][j] += icp == jcp ? (1+icp * 2) : 0; - propMatrixEpos[j][i] += icp == jcp ? (1+icp * 2) : 0; - }} - if (maxF getAA3Hash() { return aa3Hash; } @@ -1555,12 +1486,13 @@ public class ResidueProperties return _codonTranslate(lccodon); } String cdn = codonHash2.get(lccodon.toUpperCase()); - if (cdn!=null && cdn.equals("*")) + if ("*".equals(cdn)) { return "STOP"; } return cdn; } + public static String _codonTranslate(String lccodon) { String codon = lccodon.toUpperCase(); @@ -1569,14 +1501,9 @@ public class ResidueProperties { return "X"; } - Enumeration e = codonHash.keys(); - - while (e.hasMoreElements()) + for (String key : codonHash.keySet()) { - String key = (String) e.nextElement(); - Vector tmp = (Vector) codonHash.get(key); - - if (tmp.contains(codon)) + if (codonHash.get(key).contains(codon)) { return key; } @@ -1610,6 +1537,7 @@ public class ResidueProperties } return null; } + /** * get a ScoreModel based on its string name * @@ -1678,10 +1606,12 @@ public class ResidueProperties * Used by getRNASecStrucState * */ - public static Hashtable toRNAssState; + public static Hashtable toRNAssState; + + public static boolean RNAcloseParen[] = new boolean[255]; static { - toRNAssState = new Hashtable(); + toRNAssState = new Hashtable(); toRNAssState.put(")", "("); toRNAssState.put("(", "("); toRNAssState.put("]", "["); @@ -1742,7 +1672,35 @@ public class ResidueProperties toRNAssState.put("y", "Y"); toRNAssState.put("Z", "Z"); toRNAssState.put("z", "Z"); - + for (int p = 0; p < RNAcloseParen.length; p++) + { + RNAcloseParen[p] = false; + } + for (String k : toRNAssState.keySet()) + { + RNAcloseParen[k.charAt(0)] = k.charAt(0) != toRNAssState.get(k) + .charAt(0); + } + } + + static + { + modifications.put("MSE", "MET"); // Selenomethionine + // the rest tbc; from + // http://sourceforge.net/p/jmol/mailman/message/12833570/ + // modifications.put("CSE", "CYS"); // Selenocysteine + // modifications.put("PTR", "TYR"); // Phosphotyrosine + // modifications.put("SEP", "SER"); // Phosphoserine + // modifications.put("HYP", "PRO"); // 4-hydroxyproline + // modifications.put("5HP", "GLU"); // Pyroglutamic acid; 5-hydroxyproline + // modifications.put("PCA", "GLU"); // Pyroglutamic acid + // modifications.put("LYZ", "LYS"); // 5-hydroxylysine + } + + public static String getCanonicalAminoAcid(String aa) + { + String canonical = modifications.get(aa); + return canonical == null ? aa : canonical; } /** @@ -1763,7 +1721,8 @@ public class ResidueProperties String ssc = ssstring.substring(i, i + 1); if (toRNAssState.containsKey(ssc)) { - ss.append((String) toRNAssState.get(ssc)); + // valid ss character - so return it + ss.append(ssc); // (String) toRNAssState.get(ssc)); } else { @@ -1773,6 +1732,11 @@ public class ResidueProperties return ss.toString(); } + public static boolean isCloseParenRNA(char dc) + { + return RNAcloseParen[dc]; + } + // main method generates perl representation of residue property hash // / cut here public static void main(String[] args) @@ -1821,5 +1785,74 @@ public class ResidueProperties } System.out.println("};"); } + // to here + + /** + * Returns a list of residue characters for the specified inputs + * + * @param nucleotide + * @param includeAmbiguous + * @return + */ + public static List getResidues(boolean nucleotide, + boolean includeAmbiguous) + { + List result = new ArrayList(); + if (nucleotide) + { + for (String nuc : nucleotideName.keySet()) + { + int val = nucleotideIndex[nuc.charAt(0)]; + if ((!includeAmbiguous && val > 4) || (val >= maxNucleotideIndex)) + { + continue; + } + nuc = nuc.toUpperCase(); + if (!result.contains(nuc)) + { + result.add(nuc); + } + } + } + else + { + /* + * Peptide + */ + for (String res : aa3Hash.keySet()) + { + int index = aa3Hash.get(res).intValue(); + if ((!includeAmbiguous && index >= 20) || index >= maxProteinIndex) + { + continue; + } + res = res.toUpperCase(); + if (!result.contains(res)) + { + result.add(res); + } + } + } + + return result; + } + + /** + * Returns the single letter code for a three letter code, or '0' if not known + * + * @param threeLetterCode + * not case sensitive + * @return + */ + public static char getSingleCharacterCode(String threeLetterCode) + { + if (threeLetterCode == null) + { + return '0'; + } + Integer index = ResidueProperties.aa3Hash.get(threeLetterCode + .toUpperCase()); + return index == null ? '0' : aa[index].charAt(0); + } }