Language models can learn complex molecular distributions.

ABSTRACT: Deep generative models of molecules have grown immensely in popularity, trained on relevant datasets, these models are used to search through chemical space. The downstream utility of generative models for the inverse design of novel functional compounds, depends on their ability to learn a training distribution of molecules. The most simple example is a language model that takes the form of a recurrent neural network and generates molecules using a string representation. Since their initial use, subsequent work has shown that language models are very capable, in particular, recent research has demonstrated their utility in the low data regime. In this work, we investigate the capacity of simple language models to learn more  complex distributions of molecules. For this purpose, we introdu

SUBMITTER: Flam-Shepherd D 

PROVIDER: S-EPMC9174447 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature