Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model

TL;DR

This paper introduces TSMMG, a large language model that generates molecules meeting complex property constraints described in natural language, demonstrating high validity and success rates across multiple constraint tasks.

Contribution

The paper presents a novel multi-constraint molecular generation model that leverages knowledge distillation from small models and addresses data scarcity through innovative dataset construction.

Findings

Over 99% molecular validity achieved

Success ratios of 82.58%, 68.03%, and 67.48% on multi-constraint tasks

Effective zero-shot property satisfaction demonstrated

Abstract

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science.