Molecule Design by Latent Prompt Transformer

TL;DR

This paper introduces a latent prompt Transformer model that combines generative and predictive components to optimize molecule design, achieving state-of-the-art results on benchmark tasks.

Contribution

The paper presents a novel latent prompt Transformer architecture that integrates molecule generation and property prediction for optimized molecule design.

Findings

Achieves state-of-the-art performance on molecule design benchmarks.

Effectively shifts model distribution towards desired property regions.

Combines generative and predictive modeling in a unified framework.

Abstract

This paper proposes a latent prompt Transformer model for solving challenging optimization problems such as molecule design, where the goal is to find molecules with optimal values of a target chemical or biological property that can be computed by an existing software. Our proposed model consists of three components. (1) A latent vector whose prior distribution is modeled by a Unet transformation of a Gaussian white noise vector. (2) A molecule generation model that generates the string-based representation of molecule conditional on the latent vector in (1). We adopt the causal Transformer model that takes the latent vector in (1) as prompt. (3) A property prediction model that predicts the value of the target property of a molecule based on a non-linear regression on the latent vector in (1). We call the proposed model the latent prompt Transformer model. After initial training of the model on existing molecules and their property values, we then gradually shift the model distribution towards the region that supports desired values of the target property for the purpose of molecule design. Our experiments show that our proposed model achieves state of the art performances on several benchmark molecule design tasks.