*/
package jalview.schemes;
-import jalview.analysis.GeneticCodes;
-
import java.awt.Color;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Hashtable;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import java.util.Vector;
+import jalview.analysis.GeneticCodes;
+
public class ResidueProperties
{
// Stores residue codes/names and colours and other things
public static final Map<String, String> nucleotideName = new HashMap<>();
+ public static final Map<String, String> nucleotideAmbiguityName = new HashMap<>();
+
// lookup from modified amino acid (e.g. MSE) to canonical form (e.g. MET)
public static final Map<String, String> modifications = new HashMap<>();
/**
* maximum (gap) index for matrices involving nucleotide alphabet
*/
- public final static int maxNucleotideIndex = 10;
+ // public final static int maxNucleotideIndex = 10;
+ public final static int maxNucleotideIndex;
static
{
+ String[][] namesArray = { { "a", "Adenine" }, { "c", "Cytosine" },
+ { "g", "Guanine" },
+ { "t", "Thymine" },
+ { "u", "Uracil" },
+ { "i", "Inosine" },
+ { "x", "Xanthine" },
+ { "r", "Unknown Purine" },
+ { "y", "Unknown Pyrimidine" },
+ { "w", "Weak nucleotide (A or T)" },
+ { "s", "Strong nucleotide (G or C)" },
+ { "m", "Amino (A or C)" },
+ { "k", "Keto (G or T)" },
+ { "b", "Not A (G or C or T)" },
+ { "h", "Not G (A or C or T)" },
+ { "d", "Not C (A or G or T)" },
+ { "v", "Not T (A or G or C)" },
+ { "n", "Unknown" } };
+ // "gap" index
+ maxNucleotideIndex = namesArray.length;
+
nucleotideIndex = new int[255];
for (int i = 0; i < 255; i++)
{
- nucleotideIndex[i] = 10; // non-nucleotide symbols are all non-gap gaps.
+ nucleotideIndex[i] = maxNucleotideIndex; // non-nucleotide symbols are all
+ // non-gap gaps.
}
- nucleotideIndex['A'] = 0;
- nucleotideIndex['a'] = 0;
- nucleotideIndex['C'] = 1;
- nucleotideIndex['c'] = 1;
- nucleotideIndex['G'] = 2;
- nucleotideIndex['g'] = 2;
- nucleotideIndex['T'] = 3;
- nucleotideIndex['t'] = 3;
- nucleotideIndex['U'] = 4;
- nucleotideIndex['u'] = 4;
- nucleotideIndex['I'] = 5;
- nucleotideIndex['i'] = 5;
- nucleotideIndex['X'] = 6;
- nucleotideIndex['x'] = 6;
- nucleotideIndex['R'] = 7;
- nucleotideIndex['r'] = 7;
- nucleotideIndex['Y'] = 8;
- nucleotideIndex['y'] = 8;
- nucleotideIndex['N'] = 9;
- nucleotideIndex['n'] = 9;
-
- nucleotideName.put("A", "Adenine");
- nucleotideName.put("a", "Adenine");
- nucleotideName.put("G", "Guanine");
- nucleotideName.put("g", "Guanine");
- nucleotideName.put("C", "Cytosine");
- nucleotideName.put("c", "Cytosine");
- nucleotideName.put("T", "Thymine");
- nucleotideName.put("t", "Thymine");
- nucleotideName.put("U", "Uracil");
- nucleotideName.put("u", "Uracil");
- nucleotideName.put("I", "Inosine");
- nucleotideName.put("i", "Inosine");
- nucleotideName.put("X", "Xanthine");
- nucleotideName.put("x", "Xanthine");
- nucleotideName.put("R", "Unknown Purine");
- nucleotideName.put("r", "Unknown Purine");
- nucleotideName.put("Y", "Unknown Pyrimidine");
- nucleotideName.put("y", "Unknown Pyrimidine");
- nucleotideName.put("N", "Unknown");
- nucleotideName.put("n", "Unknown");
- nucleotideName.put("W", "Weak nucleotide (A or T)");
- nucleotideName.put("w", "Weak nucleotide (A or T)");
- nucleotideName.put("S", "Strong nucleotide (G or C)");
- nucleotideName.put("s", "Strong nucleotide (G or C)");
- nucleotideName.put("M", "Amino (A or C)");
- nucleotideName.put("m", "Amino (A or C)");
- nucleotideName.put("K", "Keto (G or T)");
- nucleotideName.put("k", "Keto (G or T)");
- nucleotideName.put("B", "Not A (G or C or T)");
- nucleotideName.put("b", "Not A (G or C or T)");
- nucleotideName.put("H", "Not G (A or C or T)");
- nucleotideName.put("h", "Not G (A or C or T)");
- nucleotideName.put("D", "Not C (A or G or T)");
- nucleotideName.put("d", "Not C (A or G or T)");
- nucleotideName.put("V", "Not T (A or G or C");
- nucleotideName.put("v", "Not T (A or G or C");
+ for (int i = 0; i < namesArray.length; i++)
+ {
+ char c = namesArray[i][0].charAt(0);
+ nucleotideIndex[c] = i;
+ // Character.toUpperCase is Locale insensitive
+ nucleotideIndex[Character.toUpperCase(c)] = i;
+ nucleotideName.put(namesArray[i][0], namesArray[i][1]);
+ nucleotideName.put(namesArray[i][0].toUpperCase(Locale.ROOT),
+ namesArray[i][1]);
+ }
}
Color.white, // R
Color.white, // Y
Color.white, // N
+ Color.white, // w
+ Color.white, // s
+ Color.white, // m
+ Color.white, // k
+ Color.white, // b
+ Color.white, // h
+ Color.white, // d
+ Color.white, // v
+ Color.white, // Gap
+ };
+
+ // this colour scheme devised by sduce
+ public static final Color[] nucleotideAmbiguity = {
+ Color.decode("#f0fff0"), // a
+ Color.decode("#f0fff0"), // c
+ Color.decode("#f0fff0"), // g
+ Color.decode("#f0fff0"), // t
+ Color.decode("#f0fff0"), // u
+ Color.decode("#ffffff"), // i
+ Color.decode("#4f6f6f"), // x
+ Color.decode("#CD5C5C"), // r
+ Color.decode("#008000"), // y
+ Color.decode("#4682B4"), // w
+ Color.decode("#FF8C00"), // s
+ Color.decode("#9ACD32"), // m
+ Color.decode("#9932CC"), // k
+ Color.decode("#8b4513"), // b
+ Color.decode("#808080"), // h
+ Color.decode("#483D8B"), // d
+ Color.decode("#b8860b"), // v
+ Color.decode("#2f4f4f"), // n
Color.white, // Gap
};
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
public static String STOP = "STOP";
- public static List<String> STOP_CODONS = Arrays.asList("TGA", "TAA", "TAG");
+ public static List<String> STOP_CODONS = Arrays.asList("TGA", "TAA",
+ "TAG");
public static String START = "ATG";
return peptide;
}
- public static Hashtable<String, String> 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
// main method generates perl representation of residue property hash
// / cut here
+ /**
+ * @j2sIgnore
+ * @param args
+ */
public static void main(String[] args)
{
Hashtable<String, Vector<String>> aaProps = new Hashtable<>();
{
continue;
}
- nuc = nuc.toUpperCase();
+ nuc = nuc.toUpperCase(Locale.ROOT);
if (!result.contains(nuc))
{
result.add(nuc);
{
continue;
}
- res = res.toUpperCase();
+ res = res.toUpperCase(Locale.ROOT);
if (!result.contains(res))
{
result.add(res);
return '0';
}
Integer index = ResidueProperties.aa3Hash
- .get(threeLetterCode.toUpperCase());
+ .get(threeLetterCode.toUpperCase(Locale.ROOT));
return index == null ? '0' : aa[index].charAt(0);
}
}
git://source.jalview.org / jalview.git / blobdiff