*/
package jalview.analysis;
-import jalview.math.Matrix;
+import jalview.api.analysis.DistanceScoreModelI;
+import jalview.api.analysis.ScoreModelI;
+import jalview.api.analysis.SimilarityScoreModelI;
+import jalview.datamodel.AlignmentView;
import jalview.math.MatrixI;
-import jalview.schemes.ResidueProperties;
-import jalview.schemes.ScoreMatrix;
import java.io.PrintStream;
StringBuilder details = new StringBuilder(1024);
- private String[] seqs;
+ private AlignmentView seqs;
- private ScoreMatrix scoreMatrix;
+ private ScoreModelI scoreModel;
- /**
- * Creates a new PCA object. By default, uses blosum62 matrix to generate
- * sequence similarity matrices
- *
- * @param s
- * Set of amino acid sequences to perform PCA on
- */
- public PCA(String[] s)
- {
- this(s, false);
- }
-
- /**
- * Creates a new PCA object. By default, uses blosum62 matrix to generate
- * sequence similarity matrices
- *
- * @param s
- * Set of sequences to perform PCA on
- * @param nucleotides
- * if true, uses standard DNA/RNA matrix for sequence similarity
- * calculation.
- */
- public PCA(String[] s, boolean nucleotides)
- {
- this(s, nucleotides, null);
- }
-
- public PCA(String[] s, boolean nucleotides, String s_m)
+ public PCA(AlignmentView s, ScoreModelI sm)
{
this.seqs = s;
- // BinarySequence[] bs = new BinarySequence[s.length];
- // int ii = 0;
- //
- // while ((ii < s.length) && (s[ii] != null))
- // {
- // bs[ii] = new BinarySequence(s[ii], nucleotides);
- // bs[ii].encode();
- // ii++;
- // }
- //
- // BinarySequence[] bs2 = new BinarySequence[s.length];
- scoreMatrix = null;
- String sm = s_m;
- if (sm != null)
- {
- scoreMatrix = ResidueProperties.getScoreMatrix(sm);
- }
- if (scoreMatrix == null)
- {
- // either we were given a non-existent score matrix or a scoremodel that
- // isn't based on a pairwise symbol score matrix
- scoreMatrix = ResidueProperties
- .getScoreMatrix(sm = (nucleotides ? "DNA" : "BLOSUM62"));
- }
- details.append("PCA calculation using " + sm
+ scoreModel = sm;
+ details.append("PCA calculation using " + sm.getName()
+ " sequence similarity matrix\n========\n\n");
- // ii = 0;
- // while ((ii < s.length) && (s[ii] != null))
- // {
- // bs2[ii] = new BinarySequence(s[ii], nucleotides);
- // if (scoreMatrix != null)
- // {
- // try
- // {
- // bs2[ii].matrixEncode(scoreMatrix);
- // } catch (InvalidSequenceTypeException x)
- // {
- // details.append("Unexpected mismatch of sequence type and score matrix. Calculation will not be valid!\n\n");
- // }
- // }
- // ii++;
- // }
- //
- // int count = 0;
- // while ((count < bs.length) && (bs[count] != null))
- // {
- // count++;
- // }
- //
- // double[][] seqmat = new double[count][];
- // double[][] seqmat2 = new double[count][];
- //
- // int i = 0;
- // while (i < count)
- // {
- // seqmat[i] = bs[i].getDBinary();
- // seqmat2[i] = bs2[i].getDBinary();
- // i++;
- // }
- //
- // /*
- // * using a SparseMatrix to hold the encoded sequences matrix
- // * greatly speeds up matrix multiplication as these are mostly zero
- // */
- // m = new SparseMatrix(seqmat);
- // m2 = new Matrix(seqmat2);
-
}
/**
+ (jvCalcMode ? "Jalview variant" : "Original SeqSpace")
+ "\n");
- // MatrixI mt = m.transpose();
- // eigenvector = mt.preMultiply(jvCalcMode ? m2 : m);
- eigenvector = computePairwiseScores();
+ eigenvector = computeSimilarity(seqs);
details.append(" --- OrigT * Orig ---- \n");
eigenvector.print(ps, "%8.2f");
}
/**
- * Computes an NxN matrix where N is the number of sequences, and entry [i, j]
- * is sequence[i] pairwise multiplied with sequence[j], as a sum of scores
- * computed using the current score matrix. For example
- * <ul>
- * <li>Sequences:</li>
- * <li>FKL</li>
- * <li>RSD</li>
- * <li>QIA</li>
- * <li>GWC</li>
- * <li>Score matrix is BLOSUM62</li>
- * <li>product [0, 0] = F.F + K.K + L.L = 6 + 5 + 4 = 15</li>
- * <li>product [2, 1] = R.R + S.S + D.D = 5 + 4 + 6 = 15</li>
- * <li>product [2, 2] = Q.Q + I.I + A.A = 5 + 4 + 4 = 13</li>
- * <li>product [3, 3] = G.G + W.W + C.C = 6 + 11 + 9 = 26</li>
- * <li>product[0, 1] = F.R + K.S + L.D = -3 + 0 + -3 = -7
- * <li>and so on</li>
- * </ul>
+ * Computes a pairwise similarity matrix for the given sequence regions using
+ * the configured score model. If the score model is a similarity model, then
+ * it computes the result directly. If it is a distance model, then use it to
+ * compute pairwise distances, and convert these to similarity scores by
+ * substracting from the maximum value.
+ *
+ * @param av
+ * @return
*/
- MatrixI computePairwiseScores()
+ MatrixI computeSimilarity(AlignmentView av)
{
- double[][] values = new double[seqs.length][];
- for (int row = 0; row < seqs.length; row++)
+ MatrixI result = null;
+ if (scoreModel instanceof SimilarityScoreModelI)
{
- values[row] = new double[seqs.length];
- for (int col = 0; col < seqs.length; col++)
- {
- int total = 0;
- int width = Math.min(seqs[row].length(), seqs[col].length());
- for (int i = 0; i < width; i++)
- {
- char c1 = seqs[row].charAt(i);
- char c2 = seqs[col].charAt(i);
- int score = scoreMatrix.getPairwiseScore(c1, c2);
- total += score;
- }
- values[row][col] = total;
- }
+ result = ((SimilarityScoreModelI) scoreModel).findSimilarities(av);
+ }
+ else if (scoreModel instanceof DistanceScoreModelI)
+ {
+ result = ((DistanceScoreModelI) scoreModel).findDistances(av);
+ double maxDistance = result.getMaxValue();
+ result.subtractAllFrom(maxDistance);
}
- return new Matrix(values);
+ else
+ {
+ System.err
+ .println("Unexpected type of score model, cannot calculate similarity");
+ }
+
+ return result;
}
public void setJvCalcMode(boolean calcMode)
public int getHeight()
{
// TODO can any of seqs[] be null?
- return seqs.length;
+ return seqs.getSequences().length;
}
}
git://source.jalview.org / jalview.git / blobdiff