通过几何约束提升分子与蛋白结合亲和力预测精度
Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity
- 用特征线性调制让蛋白信息指导分子表征
- 在DTI-DG基准上达到当前最优性能
- 模型轻量且可解释，适合药物研发初筛
准确预测药物-靶点结合亲和力可加速药物发现，减少昂贵的湿实验筛选。尽管深度学习已推动该任务发展，但多数模型仅通过简单拼接融合分子与蛋白表征，缺乏显式的几何约束，导致在化学空间和时间上的泛化能力差。我们提出FIRM-DTI，一种轻量级框架，通过特征式线性调制（FiLM）层将分子嵌入条件化于蛋白嵌入，并利用三元组损失强制保持度量结构。基于嵌入距离的RBF回归头生成平滑且可解释的亲和力预测。尽管模型规模小，FIRM-DTI在Therapeutics Data Commons DTI-DG基准上表现优异，经广泛的消融实验和域外评估验证。结果表明，条件化与度量学习对鲁棒的药物-靶点亲和力预测具有重要价值。
原文摘要 · Abstract (English)
Accurate prediction of drug-target binding affinity can accelerate drug discovery by prioritizing promising compounds before costly wet-lab screening. While deep learning has advanced this task, most models fuse ligand and protein representations via simple concatenation and lack explicit geometric regularization, resulting in poor generalization across chemical space and time. We introduce FIRM-DTI, a lightweight framework that conditions molecular embeddings on protein embeddings through a feature-wise linear modulation (FiLM) layer and enforces metric structure with a triplet loss. An RBF regression head operating on embedding distances yields smooth, interpretable affinity predictions. Despite its modest size, FIRM-DTI achieves state-of-the-art performance on the Therapeutics Data Commons DTI-DG benchmark, as demonstrated by an extensive ablation study and out-of-domain evaluation. Our results underscore the value of conditioning and metric learning for robust drug-target affinity prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。