trainChemPC: trainChemPC

In SimuChemPC: Simulation process of 4 selection methods in predicting chemical potent compounds

Description

Apply Gaussian Process Regression to learn the model.

Usage

trainChemPC(xTrain, yTrain)

Arguments

xTrain	m * n martrix of train data.
yTrain	m * 1 matrix of target values consist of potencies, pIC50 or other measurements of compound affinities that are desired to be maximized.

Details

This function performs training step of GP or EI by finding loghyper parameters.

Value

It returns a vector that holds calculated loghyper parameters.

Author(s)

Mohsen Ahmadi

References

1.Predicting Potent Compounds via Model-Based Global Optimization, Journal of Chemical Information and Modeling, 2013, 53 (3), pp 553-559, M Ahmadi, M Vogt, P Iyer, J Bajorath, H Froehlich. 2.Software MOE is used to calculate the numerical descriptors in data sets. Ref: http://www.chemcomp.com/MOE-Molecular_Operating_Environment.htm 3.ChEMBL was the source of the compound data and potency annotations in data sets. Ref: https://www.ebi.ac.uk/chembl/

Examples

x = as.data.frame(array(1:100, dim=c(20,5)))
y = as.matrix(as.numeric(array(1:20, dim=c(20,1))))
loghyper = trainChemPC(x, y)

SimuChemPC documentation built on May 2, 2019, 3:30 p.m.