Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRS

2026-06-26

AI Summary

This study addresses the high computational cost of accurate molecular docking, which hinders large-scale screening of epitopes for porcine reproductive and respiratory syndrome (PRRS) vaccines. The authors propose an efficient approach combining a compact Transformer architecture with pool-based active learning to identify high-affinity 9-mer epitopes capable of binding conserved swine leukocyte antigen (SLA) molecules under extremely limited sample conditions. Through iterative active learning rounds, joint hyperparameter optimization, and an ensemble decision strategy, the method outperforms baseline models trained on twice as many samples—achieving superior performance with only 30 labeled examples. At 60 samples, it attains an accuracy of 86.8%, approaching the theoretical upper bound of 85% imposed by conformational noise, and significantly surpasses both random sampling and alternative model architectures.

Abstract

High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be screened for vaccine design. In this work, we evaluate machine learning (ML) approaches where variants of active learning are used to classify instances of high binding affinity between 9-mer epitopes and a well-conserved swine leukocyte antigen (SLA) receptor in the context of Porcine Reproductive and Respiratory Syndrome (PRRS). We use an internally generated dataset of 80 epitope-SLA docking affinities, each requiring more than 48 hours of high-performance computing (HPC). Multiple model families (linear, MLP, CNN, and a small transformer) are trained under strict low-data conditions within a pool-based active learning loop. In each case, optimal model configurations are identified by conducting large-scale hyperparameter optimization over the combined space of model architecture, training configuration, acquisition policy, and ensemble decision rules. To mitigate the effects of data subsample selection, each candidate configuration is evaluated by averaging performance over many randomized and balanced training and validation data subsets. Across experiments, transformer-based sequence models consistently emerged as the best-performing architecture, with active incremental learning yielding significant improvement over a baseline random sample acquisition strategy. Under moderate training data availability (N=30), the optimized ML-model configuration outperforms a standard baseline trained on twice the amount of data. Under higher training data availability (N=60), the same configuration achieves a peak accuracy of 86.8%, consistent with an upper bound of 85% classification accuracy based on two independent estimates of conformational noise.

Problem

• epitope selection
• active learning
• vaccine design
• binding affinity
• data efficiency

Innovation

• Transformer
• Active Learning
• Epitope Selection
• Data-Efficient Learning
• Molecular Docking