PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design

2026-08-02

AI Summary

Traditional polymer generation methods struggle to jointly optimize multiple physical properties, limiting precise control over material behavior. This work proposes PolymerGPT—a decoder-based autoregressive generative model that integrates up to 37 performance metrics into the generation process via learnable conditional prefixes and supports molecular scaffold constraints. For the first time, this approach enables direct, simultaneous optimization of a large number of polymer properties, overcoming the limitations of single-property-focused generation. Experimental results demonstrate that the generated structures exhibit high validity, uniqueness, and novelty under both unconditional and conditional settings, with predicted values for five key properties closely matching their target specifications.

Abstract

Polymer property prediction and inverse generative design targeting desired properties are two crucial tasks in machine learning-assisted polymer design. While the former has received considerable attention, there have been limited methods developed for the latter. Existing methods focus on single-property optimization in the generative process, whereas accurate prediction of macroscopic material behavior requires simultaneous control of multiple physical properties. In this paper, we provide a transformative framework for direct optimization of a large collection of polymer properties. We propose PolymerGPT, a decoder-based GPT model that incorporates up to 37 commonly used polymer properties into the generative process via learned conditioning prefixes. It also supports a scaffold condition that specifies a desired scaffold for predicted structures. Our experimental results demonstrate that PolymerGPT achieves exceptional performance for unconditional and conditional generation while maintaining high validity, uniqueness, and novelty. Conditioning on five key properties yields generated structures whose predicted values closely match all target properties simultaneously.

Problem

• multi-property optimization
• inverse design
• polymer generation
• property control
• generative modeling

Innovation

• multi-property optimization
• decoder-based GPT
• inverse generative design
• conditioning prefixes
• polymer property prediction