maximallyDissimilar: Maximally Dissimilar

View source: R/sim.R

maximallyDissimilarR Documentation

Maximally Dissimilar

Description

Find a set of compounds that are far away from each other.

Usage

maximallyDissimilar(compounds, n, similarity = cmp.similarity)

Arguments

compounds

The set of items from which to pick n dissimlar items. This can be a list of anything that the similarity function will accept. By default this will be an APset.

n

The number of dissimilar items to return.

similarity

The similarity function to use. By default Tanimoto will be used on APset objects. Internally, this will be converted to a distance function using 1-similarity(a,b), so whatever similarity function you use should return a value between 0 and 1.

Details

This will run in O(length(compounds)n) time. Based on the algorithm described in (Higgs,1997).

Value

A vector of indexes of the dissimilar items.

Author(s)

Kevin Horan

References

Higgs, R.E., Bemis, K.G., Watson, I.A., and Wikel, J.H. 1997. Experimental designs for selecting molecules from large chemical databases. J. Chem. Inf. Comput. Sci. 37, 861-870

Examples

	data(apset)
	maximallyDissimilar(apset,10)

girke-lab/ChemmineR documentation built on July 28, 2023, 10:36 a.m.