Generative Design of Polymer Formulations via Conditional Graph Diffusion with Feasibility Filters
Computer Science Bulletin · 2025-12-28 · 8 (01) · 503-513
DOI: 10.71465/csb180 ↗At a glance
Journal article in Computer Science Bulletin, published online on 2025-12-28. Written by Elizabeth Moore.
Abstract (original language)
The inverse design of polymer formulations—identifying molecular structures and mixture ratios that satisfy specific property constraints—remains a grand challenge in materials informatics. Traditional combinatorial chemistry and high-throughput screening are often constrained by the vastness of the chemical space and the non-linear structure-property relationships inherent in macromolecular systems. In this work, we propose a novel generative framework based on Conditional Graph Diffusion with Feasibility Filters (CGD-FF). Unlike conventional variational autoencoders or generative adversarial networks, which often suffer from mode collapse or generate thermodynamically unstable structures, our approach models the generation process as a reverse diffusion process on molecular graphs. We introduce a conditional guidance mechanism that directs the denoising trajectory towards regions of the latent space associated with desired target properties, such as glass transition temperature and tensile strength. Furthermore, we integrate a physics-based feasibility filter that evaluates synthetic accessibility and thermodynamic miscibility in real-time during the generation phase. Our experimental results demonstrate that CGD-FF outperforms state-of-the-art baselines in generating valid, unique, and novel polymer structures while adhering to strict property targets. The integration of domain knowledge via feasibility filters significantly reduces the generation of chemically invalid candidates, bridging the gap between computational design and experimental realizability.
Cite
APA
Moore, E. (2025). Generative Design of Polymer Formulations via Conditional Graph Diffusion with Feasibility Filters. Computer Science Bulletin, 8(01), 503-513. https://doi.org/10.71465/csb180
Vancouver
Moore E. Generative Design of Polymer Formulations via Conditional Graph Diffusion with Feasibility Filters. Computer Science Bulletin. 2025;8(01):503-513. doi:10.71465/csb180
BibTeX
@article{Moore2025,
author = {Moore, Elizabeth},
title = {Generative Design of Polymer Formulations via Conditional Graph Diffusion with Feasibility Filters},
journal = {Computer Science Bulletin},
year = {2025},
volume = {8},
number = {01},
pages = {503--513},
doi = {10.71465/csb180}
}
EUVIMED