Zeyuan Yu, Jilei Wu, Ziyao Ning, Chunxia Qiao, Jing Wang, Xinying Li, Chenghua Liu, Guojiang Chen, Jiannan Feng, Jijun Yu
We present Physics-Informed Mamba (PI-Mamba), a generative model that enforces exact local covalent geometry by construction while enabling linear-time inference. PI-Mamba integrates a differentiable constraint-enforcement operator into a flow-matching framework and couples it with a Mamba-based state-space architecture. To improve optimization stability and backbone realism, we introduce a spectral initialization derived from the Rouse polymer model and an auxiliary cis-proline awareness head. Across benchmark tasks, PI-Mamba demonstrates the advantage in scalable, physically valid backbone generation: on a single A5000 GPU (24GB), it generates backbones beyond 2000 residues, producing 2000-residue samples in 9.49 s with only 0.91 GB peak VRAM, while preserving exact local geometry with 0.0% local geometry violations and maintaining strong designability on short-chain benchmarks (mean scTM = 0.910 at L = 100).
MOTIVATION: Computational antibody engineering requires reliable prediction of antibody variable-fragment structures, antigen-antibody complexes, and binding interfaces. However, publicly available tools for these tasks have rarely been compared across the complete workflow under a controlled and statistically grounded design.
RESULTS: We evaluated ImmuneBuilder, IgFold, AlphaFold3, GRAMM, and dyMEAN on 50 non-redundant humanized antibody-antigen complexes using multiple retained predictions and paired statistical testing. All three antibody structure predictors were accurate, with AlphaFold3 performing best overall and for the third complementarity-determining region of the heavy chain. AlphaFold3 also substantially outperformed GRAMM and dyMEAN in complex prediction, producing medium- or high-quality binding interfaces for 46% of the complexes, although overall interface accuracy remained limited. When docking was reliable, AlphaFold3 accurately recovered epitope and paratope residues, salt bridges, and non-bonded contacts, but reproduced hydrogen bonds and fine-grained contact strengths less consistently. These findings provide practical guidance for selecting tools across antibody-modeling workflows and identify persistent limitations in fine-grained interface prediction.
AVAILABILITY AND IMPLEMENTATION: Data, structural predictions, evaluation results, and analysis code are available from Zenodo under record 20710876.