Prediction of Synergism From Chemical-Genetic Interactions by Machine Learning

Cell Syst. 2015 Dec 23;1(6):383-95. doi: 10.1016/j.cels.2015.12.003. Epub 2015 Dec 23.

Abstract

The structure of genetic interaction networks predicts that, analogous to synthetic lethal interactions between non-essential genes, combinations of compounds with latent activities may exhibit potent synergism. To test this hypothesis, we generated a chemical-genetic matrix of 195 diverse yeast deletion strains treated with 4,915 compounds. This approach uncovered 1,221 genotype-specific inhibitors, which we termed cryptagens. Synergism between 8,128 structurally disparate cryptagen pairs was assessed experimentally and used to benchmark predictive algorithms. A model based on the chemical-genetic matrix and the genetic interaction network failed to accurately predict synergism. However, a combined random forest and Naive Bayesian learner that associated chemical structural features with genotype-specific growth inhibition had strong predictive power. This approach identified previously unknown compound combinations that exhibited species-selective toxicity toward human fungal pathogens. This work demonstrates that machine learning methods trained on unbiased chemical-genetic interaction data may be widely applicable for the discovery of synergistic combinations in different species.

Keywords: Bayesian analysis; antifungal; bipartite graph; chemical-genetic interaction; combination; genetic network; machine learning; random forest; synergism.