Efficient combinatorial drug optimization through stochastic search

Multi-target therapeutics has been shown to be effective for treating complex diseases. In this paper, we propose a novel stochastic search algorithm that can be effectively used for combinatorial drug optimization. The proposed algorithm aims to enhance existing drug optimization, including the Gur Game algorithm, where the key of the proposed approach lies in utilizing a reference concentration to decide how to update a given drug combination to improve the drug response. We demonstrate that the proposed algorithm outperforms the existing algorithms, in terms of both efficiency and success rate.