Molecule Design by Latent Prompt Transformer

TL;DR

This paper introduces the Latent Prompt Transformer (LPT), a novel generative model for molecule design that conditions on desired properties, enabling efficient discovery of molecules with targeted characteristics.

Contribution

The paper presents LPT, combining a learnable latent vector, a causal Transformer for molecule generation, and a property predictor, with an online learning algorithm for property-guided molecule design.

Findings

Effectively discovers molecules for various optimization tasks

Exhibits strong sample efficiency in molecule generation

Supports multi-objective and structure-constrained optimization

Abstract

This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task, where target biological properties or desired chemical constraints serve as conditioning variables. We propose the Latent Prompt Transformer (LPT), a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution modeled by a neural transformation of Gaussian white noise; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt. LPT can be learned by maximum likelihood estimation on molecule-property pairs. During property optimization, the latent prompt is inferred from target properties and constraints through posterior sampling and then used to guide the autoregressive molecule generation. After initial training on existing molecules and their properties, we adopt an online learning algorithm to progressively shift the model distribution towards regions that support desired target properties. Experiments demonstrate that LPT not only effectively discovers useful molecules across single-objective, multi-objective, and structure-constrained optimization tasks, but also exhibits strong sample efficiency.