ABOPD: Antibody CDR Design via On-Policy Distillation

• URL: http://arxiv.org/abs/2607.18835v1
• Date: Tue, 21 Jul 2026 08:18:04 GMT
• Title: ABOPD: Antibody CDR Design via On-Policy Distillation
• Abstract summary: We introduce ABOPD, an antibody design framework based on on-policy distillation to supervise states visited along the model's own denoising trajectories.<n>ABOPD substantially improves structural recovery on RAbD CDR-H3 generation, reducing RMSD by 0.42 (from 2.37 to 1.95 ) and outperforming supervised fine-tuning and offline distillation controls.
• Score: 47.64921673177562
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Antibodies are essential therapeutic molecules, and their complementarity-determining regions (CDRs) form the primary antigen-recognition interface. Recent protein generative models have demonstrated broad capabilities in biomolecular design, yet post-training strategies for downstream objectives remain limited. Standard denoising training operates on noisy states obtained by perturbing native structures, whereas recursive generation proceeds through model-generated intermediate states. For flexible antibody CDR loops such as CDR-H3, this mismatch can allow backbone deviations to accumulate along the denoising trajectory and compromise antigen-facing loop geometry. We introduce ABOPD, an antibody design framework based on on-policy distillation that leverages privileged native geometry during training to supervise states visited along the model's own denoising trajectories. With this fine-grained structural supervision, ABOPD substantially improves structural recovery on RAbD CDR-H3 generation, reducing RMSD by 0.42 Å (from 2.37 Å to 1.95 Å) and outperforming supervised fine-tuning and offline distillation controls, offering a path to higher-fidelity protein design.

Related papers

• APO: Unsupervised Atomic Policy Optimization for 3D Structure Prediction of Atomic Systems [64.56252173115246]
  We propose (Atomic Policy Optimization) a fully unsupervised alignment framework that eliminates the need for ground-truth reference structures.<n>APO adapts group-relative policy optimization to 3D atomic environments, utilizing a novel dual-reward mechanism.<n>Our results suggest that intrinsic physical consistency can serve as a superior guide for alignment compared to noisy, supervised coordinate matching.
  arXiv  Detail & Related papers  (2026-07-30T17:21:58Z)
• FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation [19.153777175873547]
  We introduce FP-AbDiff, the first antibody generator to enforce Fokker-Planck Equation (FPE) physics along the entire generative trajectory.<n>By aligning generative dynamics with physical laws, FP-AbDiff enhances robustness and generalizability, establishing a principled approach for physically faithful and functionally viable antibody design.
  arXiv  Detail & Related papers  (2025-11-05T01:44:37Z)
• Efficient Antibody Structure Refinement Using Energy-Guided SE(3) Flow Matching [16.192361788505558]
  FlowAB is a novel antibody structure refinement method based on energy-guided flow matching. It achieves new state-of-the-art performance on the antibody structure prediction task when used in conjunction with an appropriate prior model.
  arXiv  Detail & Related papers  (2024-10-22T04:13:55Z)
• AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions [9.427196604657215]
  Therapeutic antibodies are specialized protective proteins that bind to antigens in a lock-to-key manner. The binding strength/affinity between an antibody and a specific antigen is heavily determined by the complementarity-determining regions (CDRs) on the antibodies. Existing machine learning methods cast in silico development of CDRs as either sequence or 3D graph (with a single chain) generation tasks.
  arXiv  Detail & Related papers  (2024-06-19T02:31:23Z)
• A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design [54.30457372514873]
  We propose a hierarchical training paradigm (HTP) for the antibody sequence-structure co-design. HTP consists of four levels of training stages, each corresponding to a specific protein modality. Empirical experiments show that HTP sets the new state-of-the-art performance in the co-design problem.
  arXiv  Detail & Related papers  (2023-10-30T02:39:15Z)
• Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer [58.97153056120193]
  The specificity of an antibody is determined by its complementarity-determining regions (CDRs) Previous studies have utilized complex techniques to generate CDRs, but they suffer from inadequate geometric modeling. We propose a textitsimple yet effective model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
  arXiv  Detail & Related papers  (2023-04-21T13:24:26Z)
• xTrimoABFold: De novo Antibody Structure Prediction without MSA [77.47606749555686]
  We develop a novel model named xTrimoABFold to predict antibody structure from antibody sequence. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame-aligned point loss.
  arXiv  Detail & Related papers  (2022-11-30T09:26:08Z)
• Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design [134.65287929316673]
  Deep learning-based computational antibody design has attracted popular attention since it automatically mines the antibody patterns from data that could be complementary to human experiences. The computational methods heavily rely on high-quality antibody structure data, which is quite limited. Fortunately, there exists a large amount of sequence data of antibodies that can help model the CDR and alleviate the reliance on structure data.
  arXiv  Detail & Related papers  (2022-10-26T15:31:36Z)
• Conditional Antibody Design as 3D Equivariant Graph Translation [28.199522831859998]
  We propose Multi-channel Equivariant Attention Network (MEAN) to co-design 1D sequences and 3D structures of CDRs. Our method significantly surpasses state-of-the-art models in sequence and structure modeling, antigen-binding CDR design, and binding affinity optimization.
  arXiv  Detail & Related papers  (2022-08-12T01:00:59Z)
• Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design [35.215029426177004]
  We propose a generative model to automatically design antibodies with enhanced binding specificity or neutralization capabilities. Our method achieves superior log-likelihood on the test set and outperforms previous baselines in designing antibodies capable of neutralizing the SARS-CoV-2 virus.
  arXiv  Detail & Related papers  (2021-10-09T18:23:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.