PageRenderTime 42ms CodeModel.GetById 38ms app.highlight 1ms RepoModel.GetById 1ms app.codeStats 1ms

/fingerprint/man/bitimp.Rd

http://github.com/rajarshi/cdkr
Unknown | 33 lines | 33 code | 0 blank | 0 comment | 0 complexity | d76542452b5b085238f6708e4c24593c MD5 | raw file
 1\name{bit.importance}
 2\alias{bit.importance}
 3\title{
 4Evaluate the Discriminatory Power of Individual Bits in a Binary Fingerprint
 5}
 6\description{
 7This method evaluates the Kullback-Leibler (KL) divergence to rank the 
 8individual bits in a binary fingerprint in their ability to discriminate 
 9between database and active compounds. This method is implemented based on
10Nisius and Bajorath and includes an m-estimate correction.
11}
12\usage{
13bit.importance(actives, background)
14}
15\arguments{
16\item{actives}{A list of fingerprints for the actives}
17\item{background}{A list of fingerprints representing the background collection}
18}
19\value{
20A numeric vector of length equal to the size of the fingerprints. Each element
21of the vector is the KL divergence for the corresponding bit. If a bit position
22is never set to 1 in any of the compounds from the actives and the background, then
23the KL divergence for that position is undefined and \code{NA} is returned.
24}
25\seealso{
26\code{\link{bit.spectrum}}
27}
28\references{
29Nisius, B.; Bajorath, J.; \emph{ChemMedChem}, \bold{2010},
30\emph{5}, 859-868.
31}
32\keyword{programming}
33\author{Rajarshi Guha \email{rajarshi.guha@gmail.com}}