Reducing Data Requirements for Sequence–Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning
Journal of Chemical Information and Modeling · 09.11.2026 · 66 (21) · 13753-13767
DOI: 10.1021/acs.jcim.6c00178 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 19.10.2026. Verfasst von Nishat Nayla Labiba und 3 weiteren Autor:innen. Beteiligte Einrichtung: Bellini College of Artificial Intelligence, Cybersecurity & Computing, University of South Florida, Tampa, Florida33620, United States. Hauptthemen laut MEDLINE: Polymers, Neural Networks, Computer, Deep Learning. Die Arbeit nennt 58 Literaturangaben. Gefördert von: University of South Florida.
Abstract (Originalsprache)
Synthetic sequence-controlled polymers promise to transform polymer science by combining the chemical versatility of synthetic polymers with the precise sequence-mediated functionality of biological proteins. However, design of these materials has proven extraordinarily challenging, because they lack the massive data sets of closely related evolved molecules that accelerate design of proteins. Here, we report on an Artificial Intelligence strategy to reduce the amount of data necessary to accelerate the design of these materials. We focus on data connecting the repeat-unit-sequence of a model compatibilizer molecule to its ability to reduce the interfacial tension between distinct polymer domains. The optimal sequence of these molecules, which are essential for applications such as mixed-waste polymer recycling, depends strongly on variables such as concentration and chemical details of the polymer. We show that a deep neural network trained on low-fidelity data for sequence/interfacial tension relations at one set of conditions can be rapidly tuned to make higher-fidelity predictions at a distinct set of conditions, requiring far less data than would ordinarily be needed within the data sets we have tested. This priming using a pretrained model and then tuning it on unseen data from a different data set approach could allow a single low-fidelity parent data set to accelerate prediction and design in a larger set of related systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Bellini College of Artificial Intelligence, Cybersecurity & Computing, University of South Florida, Tampa, Florida33620, United States.
- Bellini College of Artificial Intelligence, Cybersecurity & Computing, Institute of AI + X, University of South Florida, Tampa, Florida33620, United States.
- Department of Chemical, Biological, and Materials Engineering, University of South Florida, Tampa, Florida33620, United States.
ORCID-Profile: Nishat Nayla Labiba, David S Simmons
Förderung
- University of South Florida
Zitieren
APA
Labiba, N. N., Islam, M. M., Hall, L. O., & Simmons, D. S. (2026). Reducing Data Requirements for Sequence–Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning. Journal of Chemical Information and Modeling, 66(21), 13753-13767. https://doi.org/10.1021/acs.jcim.6c00178
Vancouver
Labiba NN, Islam MM, Hall LO, Simmons DS. Reducing Data Requirements for Sequence–Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning. Journal of Chemical Information and Modeling. 2026;66(21):13753-13767. doi:10.1021/acs.jcim.6c00178
BibTeX
@article{Labiba2026,
author = {Labiba, Nishat Nayla and Islam, Md Mushfiqul and Hall, Lawrence O and Simmons, David S},
title = {Reducing Data Requirements for Sequence–Property Prediction in Copolymer Compatibilizers via Deep Neural Network Tuning},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
volume = {66},
number = {21},
pages = {13753--13767},
doi = {10.1021/acs.jcim.6c00178}
}
EUVIMED