Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity
Mohammadsaleh Refahi, Bahrad A. Sokhansanj, James R. Brown, Gail Rosen
准确预测药物靶标结合亲和力可以通过在昂贵的湿实验室筛选之前优先考虑有前途的化合物来加速药物发现。 虽然深度学习已经推进了这项任务,但大多数模型通过简单的连接融合了配体和蛋白质表示,并且缺乏明确的几何正则化,导致化学空间和时间的泛化不良。 我们引入了FILM-DTI,这是一种轻量级框架,通过特征性线性调制(FiLM)层对蛋白质嵌入进行分子嵌入的条件,并以三胞胎损耗强制公制结构。 在嵌入距离上运行的RBF回归头产生平滑,可解释的亲和力预测。 尽管规模不大,但FILM-DTI在治疗数据共享DTI-DG基准上取得了最先进的性能,广泛的消融研究和域外评估证明了这一点。 我们的研究结果强调了调节和度量学习对稳健的药物目标亲和力预测的价值。
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 fea...