arXiv：cs.LG（机器学习，全量分类）· Richard Zhu, Darren Xu, Lee-Shin Chu, Jeffrey J. Gray·· 14 小时前AI 评分35
用 LambdaLoss 改进蛋白质-蛋白质对接打分函数
Improving scoring functions for protein-protein docking with LambdaLoss
AI 导读
研究者提出用 Learning-to-Rank 领域的 LambdaLoss 损失函数改进蛋白质-蛋白质构象排序的通用框架，并在 DIPS 数据集衍生的 2.9M decoy 构象上微调 DFMDock 的能量预测头。
正文
Abstract:Modeling protein-protein interactions requires accurate scoring functions that can rank potential poses (conformations) of a protein-protein complex to differentiate near-native poses from incorrect ones. Here, we propose a general framework for improving protein-protein pose ranking and other biomolecular interaction models using the LambdaLoss loss function from the Learning-to-Rank field. We test this framework by fine-tuning the energy prediction head of DFMDock with the LambdaLoss on an augmented dataset of 2.9M decoy poses derived from the DIPS dataset. On targets from the CAPRI score set benchmark, our fine-tuned ranking model LambdaDockScore is better at identifying correct poses in its top-1 and top-5 predictions compared to EuDockScore, a state-of-the-art method. LambdaDockScore also improves upon baseline DFMDock ranking performance for scoring antibody-antigen complexes and protein-protein complexes with very large or small binding interfaces.
| Subjects: | Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Biomolecules (q-bio.BM) |
| ACM classes: | I.2.6; I.2.0; J.3 |
| Cite as: | arXiv:2610.00191 [q-bio.QM] |
| (or arXiv:2610.00191v1 [q-bio.QM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00191 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Richard Zhu [view email]
[v1]
Fri, 18 Sep 2026 01:52:02 UTC (584 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org