Leveraging Large Language Models to Predict Antibody Biological Activity Against Influenza A Hemagglutinin

2025-02-02

AI Summary

Experimental screening of therapeutic antibodies against influenza A virus hemagglutinin (H1N1 HA) is costly and time-consuming. Method: We propose a sequence-level prediction framework leveraging large language models (LLMs), adapting the MAMMAL biologics discovery architecture for HA-targeting antibody functional prediction—requiring only antibody and HA antigen amino acid sequences to end-to-end predict binding affinity and receptor-blocking activity, without structural modeling. Contribution/Results: The method achieves strong generalization across HA subtypes and enables activity inference for novel antibodies. Under multiple data-splitting strategies, it attains AUROC ≥ 0.91 on known HA antibodies, 0.90 on unseen HA subtypes, and 0.73 on entirely novel antibodies. This significantly improves screening throughput and reduces experimental validation costs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Monoclonal antibodies (mAbs) represent one of the most prevalent FDA-approved modalities for treating autoimmune diseases, infectious diseases, and cancers. However, discovery and development of therapeutic antibodies remains a time-consuming and expensive process. Recent advancements in machine learning (ML) and artificial intelligence (AI) have shown significant promise in revolutionizing antibody discovery and optimization. In particular, models that predict antibody biological activity enable in-silico evaluation of binding and functional properties; such models can prioritize antibodies with the highest likelihoods of success in costly and time-intensive laboratory testing procedures. We here explore an AI model for predicting the binding and receptor blocking activity of antibodies against influenza A hemagglutinin (HA) antigens. Our present model is developed with the MAMMAL framework for biologics discovery to predict antibody-antigen interactions using only sequence information. To evaluate the model's performance, we tested it under various data split conditions to mimic real-world scenarios. Our models achieved an AUROC $geq$ 0.91 for predicting the activity of existing antibodies against seen HAs and an AUROC of 0.9 for unseen HAs. For novel antibody activity prediction, the AUROC was 0.73, which further declined to 0.63-0.66 under stringent constraints on similarity to existing antibodies. These results demonstrate the potential of AI foundation models to transform antibody design by reducing dependence on extensive laboratory testing and enabling more efficient prioritization of antibody candidates. Moreover, our findings emphasize the critical importance of diverse and comprehensive antibody datasets to improve the generalization of prediction models, particularly for novel antibody development.

Problem

• Artificial Intelligence
• Machine Learning
• Antibody Prediction

Innovation

• Advanced Language Models
• Antibody Efficacy Prediction
• Influenza A Virus