/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
*/
package jalview.schemes;
+import jalview.analysis.scoremodels.FeatureScoreModel;
import jalview.analysis.scoremodels.PIDScoreModel;
import jalview.api.analysis.ScoreModelI;
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.util.Map;
public static final int[] purinepyrimidineIndex;
- public static final Hashtable aa3Hash = new Hashtable();
+ public static final Map<String, Integer> aa3Hash = new HashMap<String, Integer>();
- public static final Hashtable aa2Triplet = new Hashtable();
+ public static final Map<String, String> aa2Triplet = new HashMap<String, String>();
- public static final Hashtable nucleotideName = new Hashtable();
+ public static final Map<String, String> nucleotideName = new HashMap<String, String>();
+
+ // lookup from modified amino acid (e.g. MSE) to canonical form (e.g. MET)
+ public static final Map<String, String> modifications = new HashMap<String, String>();
static
{
public static final float[] pidThresholds =
{ 80, 60, 40, };
- public static Hashtable codonHash = new Hashtable();
+ public static Map<String, List<String>> codonHash = new HashMap<String, List<String>>();
+
+ private static List<String> Lys = new ArrayList<String>();
- public static Vector Lys = new Vector();
+ private static List<String> Asn = new ArrayList<String>();
- public static Vector Asn = new Vector();
+ private static List<String> Gln = new ArrayList<String>();
- public static Vector Gln = new Vector();
+ private static List<String> His = new ArrayList<String>();
- public static Vector His = new Vector();
+ private static List<String> Glu = new ArrayList<String>();
- public static Vector Glu = new Vector();
+ private static List<String> Asp = new ArrayList<String>();
- public static Vector Asp = new Vector();
+ private static List<String> Tyr = new ArrayList<String>();
- public static Vector Tyr = new Vector();
+ private static List<String> Thr = new ArrayList<String>();
- public static Vector Thr = new Vector();
+ private static List<String> Pro = new ArrayList<String>();
- public static Vector Pro = new Vector();
+ private static List<String> Ala = new ArrayList<String>();
- public static Vector Ala = new Vector();
+ private static List<String> Ser = new ArrayList<String>();
- public static Vector Ser = new Vector();
+ private static List<String> Arg = new ArrayList<String>();
- public static Vector Arg = new Vector();
+ private static List<String> Gly = new ArrayList<String>();
- public static Vector Gly = new Vector();
+ private static List<String> Trp = new ArrayList<String>();
- public static Vector Trp = new Vector();
+ private static List<String> Cys = new ArrayList<String>();
- public static Vector Cys = new Vector();
+ private static List<String> Ile = new ArrayList<String>();
- public static Vector Ile = new Vector();
+ private static List<String> Met = new ArrayList<String>();
- public static Vector Met = new Vector();
+ private static List<String> Leu = new ArrayList<String>();
- public static Vector Leu = new Vector();
+ private static List<String> Val = new ArrayList<String>();
- public static Vector Val = new Vector();
+ private static List<String> Phe = new ArrayList<String>();
- public static Vector Phe = new Vector();
+ public static List<String> STOP = new ArrayList<String>();
- public static Vector STOP = new Vector();
+ public static String START = "ATG";
static
{
/**
* Nucleotide Ambiguity Codes
*/
- public static final Hashtable<String, String[]> ambiguityCodes = new Hashtable<String, String[]>();
+ public static final Map<String, String[]> ambiguityCodes = new Hashtable<String, String[]>();
/**
* Codon triplets with additional symbols for unambiguous codons that include
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" });
-
- /**
- * 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[]
+ ambiguityCodes.put("N", new String[]
{ "G", "A", "T", "C" });
+
// Now build codon translation table
codonHash2.put("AAA", "K");
codonHash2.put("AAG", "K");
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
// scoreMatrices.put("Conservation EnhPos", new
// ScoreMatrix("Conservation EnhPos",propMatrixEpos,0));
scoreMatrices.put("PID", new PIDScoreModel());
+ scoreMatrices.put("Displayed Features", new FeatureScoreModel());
}
private ResidueProperties()
return hyd;
}
- public static Hashtable getAA3Hash()
+ public static Map<String, Integer> getAA3Hash()
{
return aa3Hash;
}
{
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;
}
}
}
+ 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;
+ }
+
/**
* translate to RNA secondary structure representation
*
}
// to here
+ /**
+ * Returns a list of residue characters for the specified inputs
+ *
+ * @param nucleotide
+ * @param includeAmbiguous
+ * @return
+ */
+ public static List<String> getResidues(boolean nucleotide,
+ boolean includeAmbiguous)
+ {
+ List<String> result = new ArrayList<String>();
+ 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);
+ }
}