-/*\r
-* Jalview - A Sequence Alignment Editor and Viewer\r
-* Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
-*\r
-* This program is free software; you can redistribute it and/or\r
-* modify it under the terms of the GNU General Public License\r
-* as published by the Free Software Foundation; either version 2\r
-* of the License, or (at your option) any later version.\r
-*\r
-* This program is distributed in the hope that it will be useful,\r
-* but WITHOUT ANY WARRANTY; without even the implied warranty of\r
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
-* GNU General Public License for more details.\r
-*\r
-* You should have received a copy of the GNU General Public License\r
-* along with this program; if not, write to the Free Software\r
-* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
-*/\r
-package jalview.datamodel;\r
-\r
-import jalview.schemes.*;\r
-\r
-\r
-\r
-/**\r
- * DOCUMENT ME!\r
- *\r
- * @author $author$\r
- * @version $Revision$\r
- */\r
-public class BinarySequence extends Sequence\r
-{\r
- int[] binary;\r
- double[] dbinary;\r
-\r
- /**\r
- * Creates a new BinarySequence object.\r
- *\r
- * @param s DOCUMENT ME!\r
- */\r
- public BinarySequence(String s)\r
- {\r
- super("", s, 0, s.length());\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- */\r
- public void encode()\r
- {\r
- // Set all matrix to 0\r
- dbinary = new double[getSequence().length() * 21];\r
-\r
- int nores = 21;\r
-\r
- for (int i = 0; i < dbinary.length; i++)\r
- {\r
- dbinary[i] = 0.0;\r
- }\r
-\r
- for (int i = 0; i < getSequence().length(); i++)\r
- {\r
- int aanum = 20;\r
-\r
- try\r
- {\r
- aanum = ResidueProperties.aaIndex[getSequence().charAt(i)];\r
- }\r
- catch (NullPointerException e)\r
- {\r
- aanum = 20;\r
- }\r
-\r
- if (aanum > 20)\r
- {\r
- aanum = 20;\r
- }\r
-\r
- dbinary[(i * nores) + aanum] = 1.0;\r
- }\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- */\r
- public void blosumEncode()\r
- {\r
- // Set all matrix to 0\r
- dbinary = new double[getSequence().length() * 21];\r
-\r
- int nores = 21;\r
-\r
- //for (int i = 0; i < dbinary.length; i++) {\r
- // dbinary[i] = 0.0;\r
- //}\r
- for (int i = 0; i < getSequence().length(); i++)\r
- {\r
- int aanum = 20;\r
-\r
- try\r
- {\r
- aanum = ResidueProperties.aaIndex[getSequence().charAt(i)];\r
- }\r
- catch (NullPointerException e)\r
- {\r
- aanum = 20;\r
- }\r
-\r
- if (aanum > 20)\r
- {\r
- aanum = 20;\r
- }\r
-\r
- // Do the blosum thing\r
- for (int j = 0; j < 20; j++)\r
- {\r
- dbinary[(i * nores) + j] = ResidueProperties.getBLOSUM62()[aanum][j];\r
- }\r
- }\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public String toBinaryString()\r
- {\r
- String out = "";\r
-\r
- for (int i = 0; i < binary.length; i++)\r
- {\r
- out += (new Integer(binary[i])).toString();\r
-\r
- if (i < (binary.length - 1))\r
- {\r
- out += " ";\r
- }\r
- }\r
-\r
- return out;\r
- }\r
-\r
- /**\r
- * DOCUMENT ME!\r
- *\r
- * @return DOCUMENT ME!\r
- */\r
- public double[] getDBinary()\r
- {\r
- return dbinary;\r
- }\r
-\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.datamodel;
+
+import jalview.schemes.ResidueProperties;
+import jalview.schemes.ScoreMatrix;
+
+/**
+ * Encode a sequence as a numeric vector using either classic residue binary
+ * encoding or convolved with residue substitution matrix.
+ *
+ * @author $author$
+ * @version $Revision$
+ */
+public class BinarySequence extends Sequence
+{
+ public class InvalidSequenceTypeException extends Exception
+ {
+
+ public InvalidSequenceTypeException(String string)
+ {
+ super(string);
+ }
+
+ }
+
+ int[] binary;
+
+ double[] dbinary;
+
+ boolean isNa = false;
+
+ /**
+ * Creates a new BinarySequence object.
+ *
+ * @param s
+ * DOCUMENT ME!
+ */
+ public BinarySequence(String s, boolean isNa)
+ {
+ super("", s, 0, s.length());
+ this.isNa = isNa;
+ }
+
+ /**
+ * clear the dbinary matrix
+ *
+ * @return nores - dimension of sequence symbol encoding for this sequence
+ */
+ private int initMatrixGetNoRes()
+ {
+ int nores = (isNa) ? ResidueProperties.maxNucleotideIndex
+ : ResidueProperties.maxProteinIndex;
+ // Set all matrix to 0
+ dbinary = new double[getSequence().length * nores];
+
+ for (int i = 0; i < dbinary.length; i++)
+ {
+ dbinary[i] = 0.0;
+ }
+ return nores;
+ }
+
+ private int[] getSymbolmatrix()
+ {
+ return (isNa) ? ResidueProperties.nucleotideIndex
+ : ResidueProperties.aaIndex;
+ }
+
+ /**
+ * DOCUMENT ME!
+ */
+ public void encode()
+ {
+ int nores = initMatrixGetNoRes();
+ final int[] sindex = getSymbolmatrix();
+ for (int i = 0; i < getSequence().length; i++)
+ {
+ int aanum = nores - 1;
+
+ try
+ {
+ aanum = sindex[getCharAt(i)];
+ } catch (NullPointerException e)
+ {
+ aanum = nores - 1;
+ }
+
+ if (aanum >= nores)
+ {
+ aanum = nores - 1;
+ }
+
+ dbinary[(i * nores) + aanum] = 1.0;
+ }
+ }
+
+ /**
+ * ancode using substitution matrix given in matrix
+ *
+ * @param matrix
+ */
+ public void matrixEncode(final ScoreMatrix matrix)
+ throws InvalidSequenceTypeException
+ {
+ if (isNa != matrix.isDNA())
+ {
+ throw new InvalidSequenceTypeException("matrix "
+ + matrix.getClass().getCanonicalName()
+ + " is not a valid matrix for "
+ + (isNa ? "nucleotide" : "protein") + "sequences");
+ }
+ matrixEncode(matrix.isDNA() ? ResidueProperties.nucleotideIndex
+ : ResidueProperties.aaIndex, matrix.getMatrix());
+ }
+
+ private void matrixEncode(final int[] aaIndex, final int[][] matrix)
+ {
+ // Set all matrix to 0
+ // dbinary = new double[getSequence().length * 21];
+
+ int nores = initMatrixGetNoRes();
+
+ // for (int i = 0; i < dbinary.length; i++) {
+ // dbinary[i] = 0.0;
+ // }
+ for (int i = 0, iSize = getSequence().length; i < iSize; i++)
+ {
+ int aanum = nores - 1;
+
+ try
+ {
+ aanum = aaIndex[getCharAt(i)];
+ } catch (NullPointerException e)
+ {
+ aanum = nores - 1;
+ }
+
+ if (aanum >= nores)
+ {
+ aanum = nores - 1;
+ }
+
+ // Do the blosum^H^H^H^H^H score matrix summation thing
+
+ for (int j = 0; j < nores; j++)
+ {
+ dbinary[(i * nores) + j] = matrix[aanum][j];
+ }
+ }
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public String toBinaryString()
+ {
+ String out = "";
+
+ for (int i = 0; i < binary.length; i++)
+ {
+ out += (new Integer(binary[i])).toString();
+
+ if (i < (binary.length - 1))
+ {
+ out += " ";
+ }
+ }
+
+ return out;
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public double[] getDBinary()
+ {
+ return dbinary;
+ }
+
+}
git://source.jalview.org / jalview.git / blobdiff