kchem: Kernel matrices for chemicals

In jpvert/kmr4toxicogenetics: Kernel multitask regression for toxicogenetics

Description

A list of example kernel matrices of chemical features.

Usage

kchem

Format

A list of 32 kernel matrices for chemicals of five categories of cell line features:

KcdkRbf

10 kernel matrices of chemical descriptors calculated using the Chemistry Development Kit (CDK) provided by the challenge, corresponding to Gaussian RBF kernel with various bandwidth.

Kchemcpp

1 kernel matrix of a marginalized graph kernel, as implemented in the ChemCPP package, in the 2D structure of the chemicals.

KpredtargetRbf

10 kernel matrices based on the chemical descriptors by their predicted targets, corresponding to Gaussian RBF kernel with various bandwidth.

KsirmsRbf

10 kernel matrices of chemical descriptors generated by the Simplex representation of molecular structure (SIRMS) provided by the challenge, corresponding to Gaussian RBF kernel with various bandwidth.

Ksubstructure

1 kernel matrix (linear kernel) of the presence or absence of a list of predefined substructures from the PubChem fingerprint in the 2D structure of the chemicals.

Source

https://doi.org/10.7303/syn1761567

References

Bernard, E., Jiao, Y., Scornet, E., Stoven, V., Walter, T., and Vert, J.-P. (2017). "Kernel multitask regression for toxicogenetics." bioRxiv-171298.

jpvert/kmr4toxicogenetics documentation built on May 24, 2019, 2:04 a.m.