*/
package jalview.analysis;
-import jalview.datamodel.BinarySequence;
-import jalview.datamodel.BinarySequence.InvalidSequenceTypeException;
-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.math.SparseMatrix;
-import jalview.schemes.ResidueProperties;
-import jalview.schemes.ScoreMatrix;
import java.io.PrintStream;
{
boolean jvCalcMode = true;
- MatrixI m;
-
MatrixI symm;
- MatrixI m2;
-
double[] eigenvalue;
MatrixI eigenvector;
StringBuilder details = new StringBuilder(1024);
- /**
- * 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);
- }
+ private AlignmentView seqs;
- /**
- * 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);
- }
+ private ScoreModelI scoreModel;
- 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 smtrx = null;
- String sm = s_m;
- if (sm != null)
- {
- smtrx = ResidueProperties.getScoreMatrix(sm);
- }
- if (smtrx == null)
- {
- // either we were given a non-existent score matrix or a scoremodel that
- // isn't based on a pairwise symbol score matrix
- smtrx = 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 (smtrx != null)
- {
- try
- {
- bs2[ii].matrixEncode(smtrx);
- } 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);
-
- }
-
- /**
- * Returns the matrix used in PCA calculation
- *
- * @return java.math.Matrix object
- */
-
- public MatrixI getM()
- {
- return m;
}
/**
*/
public float[][] getComponents(int l, int n, int mm, float factor)
{
- float[][] out = new float[m.height()][3];
+ float[][] out = new float[getHeight()][3];
- for (int i = 0; i < m.height(); i++)
+ for (int i = 0; i < getHeight(); i++)
{
out[i][0] = (float) component(i, l) * factor;
out[i][1] = (float) component(i, n) * factor;
public double[] component(int n)
{
// n = index of eigenvector
- double[] out = new double[m.height()];
+ double[] out = new double[getHeight()];
- for (int i = 0; i < m.height(); i++)
+ for (int i = 0; i < out.length; i++)
{
out[i] = component(i, n);
}
details.append("PCA Calculation Mode is "
+ (jvCalcMode ? "Jalview variant" : "Original SeqSpace")
+ "\n");
- MatrixI mt = m.transpose();
-
- details.append(" --- OrigT * Orig ---- \n");
- eigenvector = mt.preMultiply(jvCalcMode ? m2 : m);
+ eigenvector = computeSimilarity(seqs);
+ details.append(" --- OrigT * Orig ---- \n");
eigenvector.print(ps, "%8.2f");
symm = eigenvector.copy();
// + (System.currentTimeMillis() - now) + "ms"));
}
+ /**
+ * 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 computeSimilarity(AlignmentView av)
+ {
+ MatrixI result = null;
+ if (scoreModel instanceof SimilarityScoreModelI)
+ {
+ result = ((SimilarityScoreModelI) scoreModel).findSimilarities(av);
+ }
+ else if (scoreModel instanceof DistanceScoreModelI)
+ {
+ result = ((DistanceScoreModelI) scoreModel).findDistances(av);
+ double maxDistance = result.getMaxValue();
+ result.subtractAllFrom(maxDistance);
+ }
+ else
+ {
+ System.err
+ .println("Unexpected type of score model, cannot calculate similarity");
+ }
+
+ return result;
+ }
+
public void setJvCalcMode(boolean calcMode)
{
this.jvCalcMode = calcMode;
}
+
+ /**
+ * Answers the N dimensions of the NxN PCA matrix. This is the number of
+ * sequences involved in the pairwise score calculation.
+ *
+ * @return
+ */
+ public int getHeight()
+ {
+ // TODO can any of seqs[] be null?
+ return seqs.getSequences().length;
+ }
}
git://source.jalview.org / jalview.git / blobdiff