The genome-wide expression profiles of each individual (variables), both AF and control subjects, were clustered by a divisive clustering algorithm based on Oblique Principal Component Analysis (OPCA, [19]).
Variable clustering was performed using a linear combination of the first principal component and following a hierarchical divisive structure.
Existing hierarchical clustering algorithms involve a flat clustering component and an additional agglomerative or divisive procedure.
The second such example is Principal Direction Divisive Partitioning (PDDP), which is based on repeated divisions of instances according to the sign of their projection on the first principal component [14].
Various multivariate methods (unsupervised) such as K-means Cluster Analysis (KMCA), Agglomerative Hierarchical Cluster Analysis (AHCA), Principal Component Analysis (PCA), Fuzzy C Means Cluster Analysis (FCMCA), Vertex Component Analysis (VCA), and Divisive Correlation Cluster Analysis (DCCA) are being widely used for cluster analysis of Raman and IR images [45, 81, 82].
ORBACLAN (available from the authors on request) is a divisive cluster analysis that follows the general principle of TWINSPAN [ 28], but uses Principal Components instead of correspondence analysis.
Unsupervised methods widely reported in the literature include agglomerative clustering (Eisen et al. 1998), divisive clustering (Alon et al. 1999), K-means clustering (Everitt 1974), self-organizing maps (Kohonen 1995), and principal component analysis (Joliffe 1986).
The effect can be identified by the steady-state solution of Eq. 3, namely ν(3)inf = (ν(2)−E Σφν(2))/(A+Σφν(2)).We observe that the constant E weights the component of linear subtractive inhibition in the numerator, while the self-inhibition by ν(3) leads to a net divisive effect (denominator).
And strikes are divisive.
