•The
Jarvis-Patrick algorithm appears to be an ideal method for clustering
chemical structures:
–The
same results are produced regardless of input order (almost!!)
–It's
a non-parametric method
–Cluster
resolution can be adjusted (J,K) to match a particular need
–Autoscaling
is built into the method
–It
will find tight clusters embedded in loose ones
–It
is not biased towards globular clusters
–The
clustering step is very fast
–Overhead
requirements are relatively low
–