The linkage criterion determines the distance between sets of samples (variables) as a function of the pairwise distances between samples (variables). If the objects or clusters just merged are indexed by i and j, and if k is any other object or cluster, and if s(i) denotes the number of elements in cluster i, then the linkage critera available in Qlucore Omics Explorer for computing the distance d between i+j and k can be defined as follows.
Average linkage d(i+j,k) = (s(i)*d(i,k) + s(j)*d(j,k)) / (s(i) + s(j))
Weighted average linkage d(i+j,k) = (d(i,k) + d(j,k)) / 2
Minimum linkage (single linkage) d(i+j,k) = min{d(i,k), d(j,k)}
Maximum linkage (complete linkage) d(i+j,k) = max{d(i,k), d(j,k)}
The linkage can be set by the user in the Options tab. |
