arXiv cs.AI· Abrar Rahman Abir, Haz Sameen Shahgir, Md Rownok Zahan Ratul, Md Toki Tahmid, Greg Ver Steeg, Yue Dong·· 4 小时前AI 评分37
AbFlowNet:通过 Diffusion-GFlowNet 融合优化抗体-抗原结合能
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
AI 导读
研究者提出 AbFlowNet,一个将 GFlowNet 与 Diffusion 模型融合的生成框架,把每个扩散步骤视为 GFlowNet 的一个状态,在单一训练过程中同时优化扩散损失与抗体-抗原结合能,无需依赖不可靠的能量估计器的在线强化学习。
正文 · 原文
Abstract:Complementarity Determining Regions (CDRs) are critical segments of an antibody that facilitate binding to specific antigens. Current computational methods for CDR design utilize reconstruction losses and do not jointly optimize binding energy, a crucial metric for antibody efficacy. Rather, binding energy optimization is done through computationally expensive Online Reinforcement Learning (RL) pipelines rely heavily on unreliable binding energy estimators. In this paper, we propose AbFlowNet, a novel generative framework that integrates GFlowNet with Diffusion models. By framing each diffusion step as a state in the GFlowNet framework, AbFlowNet jointly optimizes standard diffusion losses and binding energy by directly incorporating energy signals into the training process, thereby unifying diffusion and reward optimization in a single procedure. Experimental results show that AbFlowNet outperforms the base diffusion model by 3.06% in amino acid recovery, 20.40% in geometric reconstruction (RMSD), and 3.60% in binding energy improvement ratio. ABFlowNet also decreases Top-1 total energy and binding energy errors by 24.8% and 38.1% without pseudo-labeling the test dataset or using computationally expensive online RL regimes.
| Comments: | Accepted at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2505.12358 [cs.LG] |
| (or arXiv:2505.12358v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2505.12358 arXiv-issued DOI via DataCite |
Submission history
From: Haz Sameen Shahgir [view email]
[v1]
Sun, 18 May 2025 10:40:35 UTC (10,034 KB)
[v2]
Fri, 13 Nov 2026 07:07:06 UTC (9,442 KB)
来源:arXiv cs.AI · arxiv.org