phangorn (version 0.0-5)

splitsNetwork: Phylogenetic Network

Description

splitsNetwork estimates a splits graph from a distance matrix.

Usage

splitsNetwork(dm, gamma=.1, lambda=0.001)

Arguments

dm

A distance matrix.

gamma

penalty value for the L1 constraint.

lambda

penalty value for the L2 constraint.

Value

• splitsNetwork returns a matrix. The first column contains the indices of the splits, the second column an unconstraint fit without penalty terms and the third column the constraint fit.

Details

splitsNetwork fits phylogenetic networks using L1, L2 and non-negativity constraints. The function minimises the peanlised least squares $$\beta = min \sum(dm - X\beta)^2 + \lambda \|\beta \|^2_2$$ with respect to $$\|\beta \|_1 <= \gamma,="" \beta="">= 0$$ where X is a design matrix constructed with designSplits. External edges are fitted without constraints.

See Also

distanceHadamard, designTree

Examples

data(yeast)
dm = dist.ml(yeast)
fit = splitsNetwork(dm)
write.nexus.splits(fit)