Title: AI-driven prediction of mRNA vaccine degradation rates with dropout-enhanced hyperparameter optimisation

Authors: Hwai Ing Soon; Azian Azamimi Abdullah; Hiromitsu Nishizaki; Mohd Yusoff Mashor; Latifah Munirah Kamarudin; Zeti-Azura Mohamed-Hussein; Zeehaida Mohamed; Wei Chern Ang

Addresses: Faculty of Electronic Engineering and Technology, Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia; Integrated Graduate School of Medicine, Engineering, and Agricultural Science, University of Yamanashi, Kofu, Yamanashi, Japan ' Faculty of Electronic Engineering and Technology, Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia; Medical Devices and Life Sciences Cluster, Sport Engineering Research Centre, Centre of Excellence (SERC), UniMAP, Arau, Perlis, Malaysia; Advanced Sensor Technology, Centre of Excellence (CEASTech), Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia ' Integrated Graduate School of Medicine, Engineering, and Agricultural Science, University of Yamanashi, Kofu, Yamanashi, Japan ' Faculty of Electronic Engineering and Technology, Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia ' Faculty of Electronic Engineering and Technology, Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia; Advanced Sensor Technology, Centre of Excellence (CEASTech), Universiti Malaysia Perlis (UniMAP), Arau, Perlis, Malaysia ' UKM Medical Molecular Biology Institute, Universiti Kebangsaan Malaysia (UKM), Jalan Yaacob Latif, 56000 Cheras, Kuala Lumpur, Malaysia; Department of Applied Physics, Faculty of Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia ' Department of Medical Microbiology Parasitology, School of Medical Sciences, Universiti Sains Malaysia (USM), 16150 Kubang Kerian Kelantan, Malaysia ' Clinical Research Centre (CRC), Hospital Tuanku Fauziah (HTF), Ministry of Health Malaysia, Kangar, 01000, Perlis, Malaysia

Abstract: Rapid mRNA vaccine degradation necessitates accurate prediction to ensure efficacy and mitigate risks. Despite challenges, mRNA vaccines' affordability, high efficacy, and minimal side effects justify intensive research efforts. Multifaceted data analysis enhances prediction efficiency. This study leverages bioinformatics with label-encoding of tetra-nitrogenous bases (4-ntb-lbA) and advanced models, refined through extensive review. Hyperparameter optimisation is improved with the dropout-enhanced technique (DEet), addressing traditional shortcomings - frequently suggesting suboptimal configurations. Results demonstrate that 4-ntb-lbA and DEet offer practical solutions. Specifically, 4-ntb-lbA upholds interdisciplinarity and minimises overfitting, while DEet mitigates suboptimality and accelerates convergence. These improvements are notable in the three-layered-wrapped-stacked BiLSTM (3lw-BiLSTM) model with 0.125-DEet to Bayesian optimisation with Gaussian process (BOGP) on a medium-sized subset (MSbT) at epoch 150, where training and validation losses reached 0.0015 and 0.0018, respectively, significantly reducing computational costs. This interdisciplinary approach is valuable for biotechnology and biomedicine, underscoring its contribution to efficient data analysis.

Keywords: mRNA vaccines; degradation rates; nitrogenous bases; hyperparameter optimisation; HPO; dropout; deep neural networks.

DOI: 10.1504/IJBET.2025.147078

International Journal of Biomedical Engineering and Technology, 2025 Vol.48 No.2, pp.172 - 210

Received: 17 Sep 2024
Accepted: 16 Dec 2024
Published online: 10 Jul 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article