Rethinking Molecular Design: Integrating Latent Variable and Auto-Regressive Models for Enhanced Goal Directed Generation

Arthur-Louis Heath, Amina Mollaysa, Michael Krauthammer

Keywords: generative models.+ molecule design.+conditional generation.+ variational auto encoders

Abstract:

De novo molecule design has become a highly ac-
tive research area, advanced significantly through
the use of state-of-the-art generative models. De-
spite these advances, several fundamental ques-
tions remain unanswered as the field increasingly
focuses on more complex generative models and
sophisticated molecular representations as an an-
swer to the challenges of drug design. In this
paper, we return to the simplest representation
of molecules, and investigate overlooked limita-
tions of classical generative approaches, particu-
larly Variational Autoencoders (VAEs) and auto-
regressive models. We propose a hybrid model
in the form of a novel regularizer that leverages
the strengths of both to improve validity, condi-
tional generation, and style transfer of molecular
sequences. Additionally, we provide an in depth
discussion of overlooked assumptions of these
models’ behaviour.

Submission Number: 53