Goal directed molecule generation using Monte Carlo Tree Search
This addresses a challenging task in biochemistry for generating molecules with specific properties, though it appears incremental as it builds on existing optimization methods.
The authors tackled the problem of generating novel molecules with desired properties by proposing unitMCTS, a method using Monte Carlo Tree Search to make unit changes at each step, which outperforms recent techniques on benchmark tasks like QED and penalized logP, achieving faster results without learning.
One challenging and essential task in biochemistry is the generation of novel molecules with desired properties. Novel molecule generation remains a challenge since the molecule space is difficult to navigate through, and the generated molecules should obey the rules of chemical valency. Through this work, we propose a novel method, which we call unitMCTS, to perform molecule generation by making a unit change to the molecule at every step using Monte Carlo Tree Search. We show that this method outperforms the recently published techniques on benchmark molecular optimization tasks such as QED and penalized logP. We also demonstrate the usefulness of this method in improving molecule properties while being similar to the starting molecule. Given that there is no learning involved, our method finds desired molecules within a shorter amount of time.