The Open Polymers 2026 (OPoly26) Dataset and Evaluations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Levine, Daniel S., Liesen, Nicholas, Chua, Lauren, Diffenderfer, James, Ingolfsson, Helgi, Kroonblawd, Matthew P., Kumar, Nitesh, Maiti, Amitesh, Mohottalalage, Supun S., Shuaibi, Muhammed, Van Essen, Brian, Wood, Brandon M., Zitnick, C. Lawrence, Blau, Samuel M., Antoniuk, Evan R.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914368453607424
author Levine, Daniel S.
Liesen, Nicholas
Chua, Lauren
Diffenderfer, James
Ingolfsson, Helgi
Kroonblawd, Matthew P.
Kumar, Nitesh
Maiti, Amitesh
Mohottalalage, Supun S.
Shuaibi, Muhammed
Van Essen, Brian
Wood, Brandon M.
Zitnick, C. Lawrence
Blau, Samuel M.
Antoniuk, Evan R.
author_facet Levine, Daniel S.
Liesen, Nicholas
Chua, Lauren
Diffenderfer, James
Ingolfsson, Helgi
Kroonblawd, Matthew P.
Kumar, Nitesh
Maiti, Amitesh
Mohottalalage, Supun S.
Shuaibi, Muhammed
Van Essen, Brian
Wood, Brandon M.
Zitnick, C. Lawrence
Blau, Samuel M.
Antoniuk, Evan R.
contents Polymers-macromolecular systems composed of repeating chemical units-constitute the molecular foundation of living organisms, while their synthetic counterparts drive transformative advances across medicine, consumer products, and energy technologies. While machine learning (ML) models have been trained on millions of quantum chemical atomistic simulations for materials and/or small molecular structures to enable efficient, accurate, and transferable predictions of chemical properties, polymers have largely not been included in prior datasets due to the computational expense of high quality electronic structure calculations on representative polymeric structures. Here, we address this shortcoming with the creation of the Open Polymers 2026 (OPoly26) dataset, which contains more than 6.57 million density functional theory (DFT) calculations on up to 360 atom clusters derived from polymeric systems, comprising over 1.2 billion total atoms. OPoly26 captures the chemical diversity that makes polymers intrinsically tunable and versatile materials, encompassing variations in monomer composition, degree of polymerization, chain architectures, and solvation environments. We show that augmenting ML model training with the OPoly26 dataset improves model performance for polymer prediction tasks. We also publicly release the OPoly26 dataset to help further the development of ML models for polymers, and more broadly, strive towards universal atomistic models.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Open Polymers 2026 (OPoly26) Dataset and Evaluations
Levine, Daniel S.
Liesen, Nicholas
Chua, Lauren
Diffenderfer, James
Ingolfsson, Helgi
Kroonblawd, Matthew P.
Kumar, Nitesh
Maiti, Amitesh
Mohottalalage, Supun S.
Shuaibi, Muhammed
Van Essen, Brian
Wood, Brandon M.
Zitnick, C. Lawrence
Blau, Samuel M.
Antoniuk, Evan R.
Chemical Physics
Computational Physics
Polymers-macromolecular systems composed of repeating chemical units-constitute the molecular foundation of living organisms, while their synthetic counterparts drive transformative advances across medicine, consumer products, and energy technologies. While machine learning (ML) models have been trained on millions of quantum chemical atomistic simulations for materials and/or small molecular structures to enable efficient, accurate, and transferable predictions of chemical properties, polymers have largely not been included in prior datasets due to the computational expense of high quality electronic structure calculations on representative polymeric structures. Here, we address this shortcoming with the creation of the Open Polymers 2026 (OPoly26) dataset, which contains more than 6.57 million density functional theory (DFT) calculations on up to 360 atom clusters derived from polymeric systems, comprising over 1.2 billion total atoms. OPoly26 captures the chemical diversity that makes polymers intrinsically tunable and versatile materials, encompassing variations in monomer composition, degree of polymerization, chain architectures, and solvation environments. We show that augmenting ML model training with the OPoly26 dataset improves model performance for polymer prediction tasks. We also publicly release the OPoly26 dataset to help further the development of ML models for polymers, and more broadly, strive towards universal atomistic models.
title The Open Polymers 2026 (OPoly26) Dataset and Evaluations
topic Chemical Physics
Computational Physics
url https://arxiv.org/abs/2512.23117