Disentangling multispecific antibody function with graph neural networks

2026-01-30

AI Summary

This work addresses the challenge that the function of multispecific antibodies is highly dependent on their intricate molecular topologies, which are difficult to predict using conventional methods due to the scarcity of experimental data and the sensitivity of function to subtle structural variations. To overcome these limitations, we propose a graph neural network architecture that integrates generative synthetic data with transfer learning, explicitly modeling the topological connectivity of antibody domains for the first time. Our approach achieves high-accuracy functional prediction, successfully recapitulating the complex behavior of trispecific T-cell engagers, effectively balancing efficacy and toxicity, and enabling efficient identification of optimal common light chains. This framework establishes a new paradigm for the rational design of multispecific antibodies.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Multispecific antibodies offer transformative therapeutic potential by engaging multiple epitopes simultaneously, yet their efficacy is an emergent property governed by complex molecular architectures. Rational design is often bottlenecked by the inability to predict how subtle changes in domain topology influence functional outcomes, a challenge exacerbated by the scarcity of comprehensive experimental data. Here, we introduce a computational framework to address part of this gap. First, we present a generative method for creating large-scale, realistic synthetic functional landscapes that capture non-linear interactions where biological activity depends on domain connectivity. Second, we propose a graph neural network architecture that explicitly encodes these topological constraints, distinguishing between format configurations that appear identical to sequence-only models. We demonstrate that this model, trained on synthetic landscapes, recapitulates complex functional properties and, via transfer learning, has the potential to achieve high predictive accuracy on limited biological datasets. We showcase the model's utility by optimizing trade-offs between efficacy and toxicity in trispecific T-cell engagers and retrieving optimal common light chains. This work provides a robust benchmarking environment for disentangling the combinatorial complexity of multispecifics, accelerating the design of next-generation therapeutics.

Problem

• multispecific antibodies
• domain topology
• functional prediction
• molecular architecture
• rational design

Innovation

• graph neural networks
• multispecific antibodies
• synthetic functional landscapes
• topological encoding
• transfer learning