LAPSE:2025.0215
Published Article
LAPSE:2025.0215
Comparative Analysis of PharmHGT, GCN, and GAT Models for Predicting LogCMC in Surfactants
June 27, 2025
Abstract
Predicting the critical micelle concentration (CMC) of surfactants is essential for optimizing their applications in various industries, including pharmaceuticals, detergents, and emulsions. In this study, we investigate the performance of graph-based machine learning models, specifically Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and a graph-transformer model, PharmHGT, for predicting CMC values. We aim to determine the most effective model for capturing the structural and physicochemical properties of surfactants. Our results provide insights into the relative strengths of each approach, highlighting the potential advantages of transformer-based architectures like PharmHGT in handling molecular graph representations compared to traditional graph neural networks. This comparative study serves as a step towards enhancing the accuracy of CMC predictions, contributing to the efficient design of surfactants for targeted applications.
Predicting the critical micelle concentration (CMC) of surfactants is essential for optimizing their applications in various industries, including pharmaceuticals, detergents, and emulsions. In this study, we investigate the performance of graph-based machine learning models, specifically Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and a graph-transformer model, PharmHGT, for predicting CMC values. We aim to determine the most effective model for capturing the structural and physicochemical properties of surfactants. Our results provide insights into the relative strengths of each approach, highlighting the potential advantages of transformer-based architectures like PharmHGT in handling molecular graph representations compared to traditional graph neural networks. This comparative study serves as a step towards enhancing the accuracy of CMC predictions, contributing to the efficient design of surfactants for targeted applications.
Record ID
Keywords
Critical Micelle Concentration, Graph Neural Networks, Machine Learning, Molecular Property Prediction, Surfactants
Suggested Citation
Marchan GCT, Olayiwola T, Romagnoli J. Comparative Analysis of PharmHGT, GCN, and GAT Models for Predicting LogCMC in Surfactants. Systems and Control Transactions 4:399-405 (2025) https://doi.org/10.69997/sct.107030
Author Affiliations
Marchan GCT: Louisiana State University, Department of Chemical Engineering, Baton Rouge, Louisiana 70803, United States
Olayiwola T: Louisiana State University, Department of Chemical Engineering, Baton Rouge, Louisiana 70803, United States
Romagnoli J: Louisiana State University, Department of Chemical Engineering, Baton Rouge, Louisiana 70803, United States
Olayiwola T: Louisiana State University, Department of Chemical Engineering, Baton Rouge, Louisiana 70803, United States
Romagnoli J: Louisiana State University, Department of Chemical Engineering, Baton Rouge, Louisiana 70803, United States
Journal Name
Systems and Control Transactions
Volume
4
First Page
399
Last Page
405
Year
2025
Publication Date
2025-07-01
Version Comments
Original Submission
Other Meta
PII: 0399-0405-1747-SCT-4-2025, Publication Type: Journal Article
Record Map
Published Article
LAPSE:2025.0215
This Record
External Link
https://doi.org/10.69997/sct.107030
Article DOI
Data
LAPSE:2025.0036
DIGITAL SUPPLEMENTARY MATERIAL: Com...
Download
Meta
Record Statistics
Record Views
964
Version History
[v1] (Original Submission)
Jun 27, 2025
Verified by curator on
Jun 27, 2025
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2025.0215
Record Owner
PSE Press
Links to Related Works
Directly Related to This Work
Article DOI
Supplementary Material
References Cited
- B. Bhattacharya, T. K. Ghosh, N. Das, Application of bio-surfactants in cosmetics and pharmaceutical industry. Sch. Acad. J. Pharm 6, 320-329 (2017)
- C. Ceresa, L. Fracchia, E. Fedeli, C. Porta, I. M. Banat, Recent advances in biomedical, therapeutic and pharmaceutical applications of microbial surfactants. Pharmaceutics 13, 466 (2021) https://doi.org/10.3390/pharmaceutics13040466
- C. Negin, S. Ali, Q. Xie, Most common surfactants employed in chemical enhanced oil recovery. Petroleum 3, 197-211 (2017) https://doi.org/10.1016/j.petlm.2016.11.007
- M. J. Rosen, J. T. Kunjappu, Surfactants and interfacial phenomena. (John Wiley & Sons, 2012) https://doi.org/10.1002/9781118228920
- M. Bielawska, A. Chodzinska, B. Janczuk, A. Zdziennicka, Determination of CTAB CMC in mixed water+ short-chain alcohol solvent by surface tension, conductivity, density and viscosity measurements. Colloids and Surfaces A: Physicochemical and Engineering Aspects 424, 81-88 (2013) https://doi.org/10.1016/j.colsurfa.2013.02.017
- S. F. Burlatsky et al., Surface tension model for surfactant solutions at the critical micelle concentration. Journal of colloid and interface science 393, 151-160 (2013) https://doi.org/10.1016/j.jcis.2012.10.020
- M. M. Mabrouk, N. A. Hamed, F. R. Mansour, Spectroscopic methods for determination of critical micelle concentrations of surfactants; a comprehensive review. Applied Spectroscopy Reviews 58, 206-234 (2023) https://doi.org/10.1080/05704928.2021.1955702
- A. R. Katritzky, L. Pacureanu, D. Dobchev, M. Karelson, QSPR study of critical micelle concentration of anionic surfactants using computational molecular descriptors. Journal of chemical information and modeling 47, 782-793 (2007) https://doi.org/10.1021/ci600462d
- A. P. Santos, A. Z. Panagiotopoulos, Determination of the critical micelle concentration in simulations of surfactant systems. The Journal of chemical physics 144, (2016) https://doi.org/10.1063/1.4940687
- Y. Jiang, S. Jin, X. Jin, Pharmacophoric-constrained heterogeneous graph transformer model for molecular property prediction. Communications. Chemistry 6, (2023) https://doi.org/10.1038/s42004-023-00857-x
- P. Naghshnejad, G. Theis Marchan, T. Olayiwola, R. Kumar, J. Romagnoli, Graph-Based Modeling and Molecular Dynamics for Ion Activity Coefficient Prediction in Polymeric Ion-Exchange Membranes. Industrial & Engineering Chemistry Research, (2024) https://doi.org/10.26434/chemrxiv-2024-jcjg3
- D. Deng et al., XGraphBoost: extracting graph neural network-based features for a better prediction of molecular properties. Journal of chemical information and modeling 61, 2697-2705 (2021) https://doi.org/10.1021/acs.jcim.0c01489
- P. Velickovic et al., Graph attention networks. stat 1050, 10-48550 (2017)
- M. Nnadili et al., Surfactant-Specific AI-Driven Molecular Design: Integrating Generative Models, Predictive Modeling, and Reinforcement Learning for Tailored Surfactant Synthesis. Industrial & Engineering Chemistry Research 63, 6313-6324 (2024) https://doi.org/10.1021/acs.iecr.4c00401
- S. Qin, T. Jin, R. C. Van Lehn, V. M. Zavala, Predicting critical micelle concentrations for surfactants using graph convolutional neural networks. The Journal of Physical Chemistry B 125, 10610-10620 (2021) https://doi.org/10.1021/acs.jpcb.1c05264
- R. A. Saunders, J. A. Platts, Correlation and prediction of critical micelle concentration using polar surface area and LFER methods. Journal of physical organic chemistry 17, 431-438 (2004) https://doi.org/10.1002/poc.749
- S. Lee, J. Lee, H. Yu, J. Lim, Synthesis of environment friendly nonionic surfactants from sugar base and characterization of interfacial properties for detergent application. Journal of Industrial and Engineering Chemistry 38, 157-166 (2016) https://doi.org/10.1016/j.jiec.2016.04.019
- L. Chaveriat, I. Gosselin, C. Machut, P. Martin, Synthesis, surface tension properties and antibacterial activities of amphiphilic D-galactopyranose derivatives. European Journal of Medicinal Chemistry 62, 177-186 (2013) https://doi.org/10.1016/j.ejmech.2012.12.032
- C. Yan, G. Li, The rise of machine learning in polymer discovery. Advanced Intelligent Systems 5, 2200243 (2023) https://doi.org/10.1002/aisy.202200243
- G. Landrum, RDKit: Open-source cheminformatics. 2006. Google Scholar, (2006)
- J. L. Durant, B. A. Leland, D. R. Henry, J. G. Nourse, Reoptimization of MDL keys for use in drug discovery. Journal of chemical information and computer sciences 42, 1273-1280 (2002) https://doi.org/10.1021/ci010132r
- A. Paszke et al., Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32, (2019)
- M. Wang et al., Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315, (2019)
(0.09 seconds)
[0.09 s]