This work designs a biological prior-guided feature fusion framework that integrates pseudo-structural epitope knowledge and CDR-specific attention mechanisms via a mixture-of-experts architecture to effectively capture complex binding landscapes in antibody screening and drug residence time analysis.
Abstract
MOTIVATION
The rapid advancement of generative artificial intelligence has enabled the high-throughput design of therapeutic antibody candidates. However, the precise evaluation of these candidates remains a significant challenge due to the scarcity of high-quality activity data and the structural flexibility of antibody complementarity-determining regions (CDRs).
RESULTS
To address these challenges, we propose AbAgKer, an antibody screening model leveraging pre-trained representations and biological prior guidance for antigen-antibody affinity and kinetics prediction. Specifically, we design a biological prior-guided feature fusion framework that integrates pseudo-structural epitope knowledge and CDR-specific attention mechanisms via a mixture-of-experts architecture to effectively capture complex binding landscapes. To mitigate data scarcity, we employ a semi-supervised learning strategy for data self-distillation, which significantly enhances affinity prediction performance. Additionally, we demonstrate that the interaction representations learned by AbAgKer can be effectively transferred to the data-scarce task of predicting dissociation rates via few-shot learning. Extensive experiments demonstrate that AbAgKer outperforms baseline models and exhibits strong generalization capabilities in antibody screening and drug residence time analysis.
AVAILABILITY AND IMPLEMENTATION
The source code and dataset are available at https://github.com/CSUBioGroup/AbAgKer and https://doi.org/10.5281/zenodo.19691211.
Summary Predicting antigen-antibody binding is essential to drug discovery and protein engineering. For de novo antibody design, generalizable binding prediction models are crucial for efficient in silico screening. However, existing affinity predictors lack generalization, with performance deteriorating for antibodies targeting antigens absent from training data or datasets lacking non-binders. To address this, we establish a benchmarking framework for evaluating universal antibody-antigen binding affinity prediction. Our framework compares sequence- and structure-based methods across diverse antigens, introducing standardized evaluation protocols based on pairwise accuracy and retrieval metrics. We propose MochiBind, a sequence-only pairwise binding affinity predictor, and benchmark it against structure-derived baselines such as Boltz-2, GeoDock, and Graphinity. The results show that MochiBind achieves comparable or superior performance in pairwise accuracy and retrieval, suggesting that sequence-based approaches can match or surpass structure-based models in generalization. The proposed benchmark provides a foundation for fair comparison and future development, enabling scalable, sequence-driven solutions to binding affinity prediction.
Yunrui Li, Yue Zhao, K. Sonmez et al.· iScience· 0 citations
This thesis examines the integration of machine learning into computational structural biology, with an emphasis on modelling and predicting antibody–antigen interactions. Such interactions are fundamental to numerous biological processes and are central to therapeutic antibody design. Despite recent advances in AI-based protein structure prediction, antibodies remain particularly challenging targets due to the high variability of their complementarity-determining regions, the limited availability of experimental structures, and the lack of strong co-evolutionary signal.
To address these challenges, this work introduces several methodological contributions. In Chapter 2,DeepRank-GNN-esm incorporates embeddings from protein language models to replace computationally expensive evolutionary features, thereby improving both predictive performance and efficiency in scoring protein–protein complexes. In Chapter 3, a modelling pipeline is introduced that employs a flow-matching algorithm to effectively sample the conformational diversity of the antibody CDR-H3 loop. When integrated with ensemble docking, this approach significantly improves the accuracy of antibody–antigen complex modelling compared to existing methods. In Chapter 4, the thesis presents AbTune, a sequence-specific fine-tuning strategy for protein language models that enhances predictive performance across multiple antibody-related tasks, including structure prediction, mutation effect estimation, and binding affinity prediction, while remaining computationally efficient. In Chapter 5, DeepRank-Ab is developed as a geometric deep learning-based scoring function tailored to antibody–antigen complexes, achieving state-of-the-art performance in ranking near-native docking conformations. Chapter 6 summarizes the main findings of the thesis and discusses future research directions.
Collectively, these contributions demonstrate how machine learning can be applied to address key limitations in antibody modelling and to facilitate the rational design of antibody-based therapeutics.
The resulting model, HydrAffinity, is an interaction-free, dynamic sparse model that uses pre-trained encoders and MoE for parameter-efficient learning and outperforms all interaction-free methods and matches state-of-the-art interaction-based methods on CASF-2016.
Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level. To address these limitations, we introduce AAMFM, an Antigen-specific Antibody Multimodal Foundation Model that learns unified representations of antibody sequences and structures conditioned on antigen context. AAMFM incorporates rich antigen information including geometric interfaces and epitope annotations via a cross-modal adapter, enabling joint modeling of antibody-antigen interactions in a shared latent space. To further guide the model toward functional relevance, we fine-tune AAMFM using Calibrated Direct Preference Optimization (Cal-DPO), leveraging preference signals extracted from a strong structural prior to align learning with binding-specific objectives. Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design, revealing its potential for antigen-specific antibody engineering. Our code is available at https://github.com/XL-S224/AAMFM.
Xiaoliang Shi, Zichen Wang, Runze Ma et al.· 0 citations
Antibody polyreactivity refers to the ability of a monoclonal antibody to non-specifically bind to a diverse range of antigens. While this property may be an intrinsic mechanism of the immune response, it poses significant challenges in therapeutic antibody development, often leading to off-target effects, poor pharmacokinetics, and potential toxicity. This review compiles the data resources related to polyreactive antibodies and places a particular emphasis on computational models for predicting antibody polyreactivity. The latter includes empirical models based on physicochemical properties, traditional machine learning models, deep learning networks, and protein language models. Through delineating the complexity of antibody polyreactivity, this review emphasizes the critical role and growing potential of computational prediction tools in selecting and engineering antibody drug candidates at early stages, thereby reducing development risks and accelerating the development of safer and better therapeutic antibodies.
Haoxian Tang, Zixuan Zhang, Wenzhi Li et al.· Computational Biomedicine· 0 citations
Accurate computational prediction of antibody-antigen binding affinity and specificity is critical for accelerating the design of next-generation therapeutics. In computational antibody design, the central challenge is not merely predicting binding, but determining whether an antibody preferentially binds its intended antigen over realistic off-targets. Existing antibody-antigen benchmarks largely focus on affinity prediction or docking accuracy on known binders, and therefore do not directly evaluate antibody specificity. We introduce SAASBench, an adversarial diagnostic benchmark that isolates antibody specificity as a set-based ranking problem. For 20 therapeutically approved full-length antibodies, SAASBench constructs an antibody-conditioned synthetic candidate set containing the true antigen and hard negative decoys drawn from the human extracellular proteome. The decoys are selected to be similar to the positive on structural plausibility of the synthetic Ab-Ag complex and on the change in solvent accessible surface area. Evaluation uses per-antibody ranking metrics aligned with practical downselection decisions. Across 20 antibody panels, affinity-based predictors display heterogeneous performance, ranging from below-random to moderate success. Overall, these results indicate that strong performance on traditional affinity benchmarks does not automatically translate into reliable antibody specificity estimation in proteome-derived settings. SAASBench provides a framework for evaluating the model's ability to estimate the specificity of a candidate antibody in relevant settings.
Dmitriy Umerenkov, Ivan Poddiakov· Proceedings of the 32nd ACM...· 0 citations