ADEPT-PolyGraphMT: Automated Molecular Simulation and Multi-Task Multi-Fidelity Machine Learning for Polymer Property Generation and Prediction

TL;DR

This paper introduces ADEPT-PolyGraphMT, a comprehensive framework combining simulations, experimental data, and multi-task machine learning to predict polymer properties efficiently across diverse chemical spaces.

Contribution

It presents an integrated approach that automates polymer simulations and employs multi-fidelity, multi-task learning for accurate property prediction with limited data.

Findings

Multi-task models perform comparably to single-task models in data-rich settings.

Fidelity-aware training enhances prediction accuracy across data sources.

Large-scale property predictions align with physical expectations across broad chemical spaces.

Abstract

The discovery of polymers with targeted properties is challenged by the vast chemical design space and the limited availability of consistent, high-quality data across multiple properties. In this work, an integrated polymer informatics framework is presented that combines the Automated molecular Dynamics Engine for Polymer simulaTions (ADEPT) workflow with multi-task and multi-fidelity machine learning (PolyGraphMT). Polymer repeat units are represented as molecular graphs and processed using a graph neural network to learn structure-property relationships. Starting from SMILES representations for monomers, ADEPT automates the construction of atomistic models and the evaluation of their properties using molecular dynamics simulations and density functional theory calculations. The simulation data are combined with curated experimental data and group contribution theory estimates to construct a unified dataset of approximately 62,000 polymer property values spanning 28 properties. Using this dataset, inter-property correlations are analyzed, and multi-task learning strategies are evaluated for joint property prediction. The results show that multi-task models achieve performance comparable to single-task models in data-rich regimes and exhibit superior accuracy as training data become limited. In addition, fidelity-aware training improves predictive accuracy when combining experimental and computational data sources. The trained models are further applied to large-scale property prediction for polymers in the PolyInfo database and the PI1M virtual polymer library, producing physically consistent property distributions across a broad chemical space. Overall, the proposed framework provides a structured approach for scalable prediction and screening of polymer properties across multiple property types and data fidelity levels.