论文标题
在结合亲和力预测中提高梯度的高性能
High Performance of Gradient Boosting in Binding Affinity Prediction
论文作者
论文摘要
蛋白质 - 配体（PL）结合亲和力的预测仍然是药物发现的关键。近年来，流行的方法涉及图形神经网络（GNN），这些神经网络用于学习PL复合物的拓扑和几何形状。但是，GNN在计算上很重，并且图形大小的可扩展性较差。另一方面，传统的机器学习（ML）方法，例如提高梯度的决策树（GBDTS），对表格数据轻巧但非常有效。我们建议在GBDT中使用PL相互作用功能以及PL图级功能。我们表明，这种组合的表现优于现有解决方案。
Prediction of protein-ligand (PL) binding affinity remains the key to drug discovery. Popular approaches in recent years involve graph neural networks (GNNs), which are used to learn the topology and geometry of PL complexes. However, GNNs are computationally heavy and have poor scalability to graph sizes. On the other hand, traditional machine learning (ML) approaches, such as gradient-boosted decision trees (GBDTs), are lightweight yet extremely efficient for tabular data. We propose to use PL interaction features along with PL graph-level features in GBDT. We show that this combination outperforms the existing solutions.
