The WPGMA algorithm constructs a rooted tree that reflects the structure present in a pairwise distance matrix. At each step, the nearest two clusters, say and, are combined into a higher-level cluster. Then, its distance to another cluster is simply the arithmetic mean of the average distances between members of and and and : The WPGMA algorithm produces rooted dendrograms and requires a constant-rate assumption: it produces an ultrametric tree in which the distances from the root to every branch tip are equal. This ultrametricity assumption is called the molecular clock when the tips involve DNA, RNA and protein data.
Let us assume that we have five elements and the following matrix of pairwise distances between them :
a
b
c
d
e
a
0
17
21
31
23
b
17
0
30
34
21
c
21
30
0
28
39
d
31
34
28
0
43
e
23
21
39
43
0
In this example, is the smallest value of, so we join elements and.
First branch length estimation
Let denote the node to which and are now connected. Setting ensures that elements and are equidistant from. This corresponds to the expectation of the ultrametricity hypothesis. The branches joining and to then have lengths
First distance matrix update
We then proceed to update the initial distance matrix into a new distance matrix , reduced in size by one row and one column because of the clustering of with. Bold values in correspond to the new distances, calculated by averaging distances between each element of the first cluster and each of the remaining elements: Italicized values in are not affected by the matrix update as they correspond to distances between elements not involved in the first cluster.
Second step
Second clustering
We now reiterate the three previous steps, starting from the new distance matrix :
c
d
e
0
25.5
32.5
22
c
25.5
0
28
39
d
32.5
28
0
43
e
22
39
43
0
Here, is the smallest value of, so we join cluster and element.
Second branch length estimation
Let denote the node to which and are now connected. Because of the ultrametricity constraint, the branches joining or to, and to are equal and have the following length: We deduce the missing branch length:
Second distance matrix update
We then proceed to update the matrix into a new distance matrix , reduced in size by one row and one column because of the clustering of with : Of note, this average calculation of the new distance does not account for the larger size of the cluster with respect to . Similarly: The averaging procedure therefore gives differential weight to the initial distances of matrix. This is the reason why the method is weighted, not with respect to the mathematical procedure but with respect to the initial distances.
Third step
Third clustering
We again reiterate the three previous steps, starting from the updated distance matrix.
c
d
0
32.25
37.75
c
32.25
0
28
d
37.75
28
0
Here, is the smallest value of, so we join elements and.
Third branch length estimation
Let denote the node to which and are now connected. The branches joining and to then have lengths
So we join clusters and. Let denote the node to which and are now connected. The branches joining and to then have lengths: We deduce the two remaining branch lengths:
The dendrogram is now complete. It is ultrametric because all tips are equidistant from : The dendrogram is therefore rooted by, its deepest node.
Comparison with other linkages
Alternative linkage schemes include single linkage clustering, complete linkage clustering, and UPGMA average linkage clustering. Implementing a different linkage is simply a matter of using a different formula to calculate inter-cluster distances during the distance matrix update steps of the above algorithm. Complete linkage clustering avoids a drawback of the alternative single linkage clustering method - the so-called chaining phenomenon, where clusters formed via single linkage clustering may be forced together due to single elements being close to each other, even though many of the elements in each cluster may be very distant to each other. Complete linkage tends to find compact clusters of approximately equal diameters.
