Inverse design allows the generation of molecules with desirable physical quantities using property optimization. Deep generative models have recently been applied to tackle inverse design, as they possess the ability to optimize molecular properties directly through structure modification using gradients. While the ability to carry out direct property optimizations is promising, the use of generative deep learning models<br/>to solve practical problems requires large amounts of data and is very time-consuming. In this talk, we introduce STONED [1] – a simple and efficient algorithm to perform interpolation and exploration in the chemical space, comparable to deep generative models. STONED bypasses the need for large amounts of data and training times by using string modifications in the SELFIES molecular representation. In this talk, we<br/>discuss the current state of the art in generative modelling for molecular design, and draw performance comparisons to STONED. The talk will be accompanied by a tutorial on how to use STONED. Overall, we anticipate our results to be a stepping stone for developing more sophisticated inverse design models and benchmarking tools, ultimately helping generative models achieve wider adoption.

Efficient interpolation and exploration of the chemical space with stoned selfies

ACS Fall 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.