Junaid Muhammad, Zeeshan Muhammad, Khan Abbas, Alshabrmi Fahad M, Li Wenjin
Institute for Advanced Study, Shenzhen University, Shenzhen 518060, China.
College of Physics and Optoelectronics Engineering, Shenzhen University, Shenzhen 518060, China.
ACS Omega. 2025 Apr 16;10(16):16748-16761. doi: 10.1021/acsomega.5c00538. eCollection 2025 Apr 29.
Structure-based virtual screening (SBVS) is a cornerstone of modern drug discovery pipelines. However, conventional scoring functions often fail to capture the complexities of protein-ligand binding interactions. To address this limitation, we developed DeepMETTL3, a novel scoring function that integrates 3D convolutional neural networks (CNNs) with multihead attention mechanisms and high-dimensional Structural Protein-Ligand Interaction Fingerprints (SPLIF). This approach enables the model to capture intricate 3D interaction patterns while refining and prioritizing features for precise classification of active and inactive compounds. We validated DeepMETTL3 using METTL3 as a therapeutic target, employing a scaffold-based data-splitting strategy and multiple test sets, including challenging sets with minimal chemical similarity to the training data. Our results demonstrate that DeepMETTL3 outperforms traditional scoring functions, achieving superior accuracy, robustness, and scalability. Key findings include the importance of an active-to-decoy ratio (1:50) in the training set for enhanced performance and the optimal placement of the attention mechanism after CNN1 for improved generalization. DeepMETTL3 represents a significant advancement in target-specific machine learning for SBVS, offering a framework that can be adapted to other biological targets. This work underscores the potential of deep learning in artificial intelligence-based drug design, balancing computational efficiency and predictive power in molecular docking and virtual screening. The scoring function is freely available at https://github.com/juniML/DeepMETTL3.
基于结构的虚拟筛选（SBVS）是现代药物发现流程的基石。然而，传统的评分函数常常无法捕捉蛋白质-配体结合相互作用的复杂性。为了解决这一局限性，我们开发了DeepMETTL3，这是一种新颖的评分函数，它将3D卷积神经网络（CNN）与多头注意力机制以及高维结构蛋白质-配体相互作用指纹（SPLIF）相结合。这种方法使模型能够捕捉复杂的3D相互作用模式，同时优化并对特征进行优先级排序，以便对活性和非活性化合物进行精确分类。我们以METTL3作为治疗靶点对DeepMETTL3进行了验证，采用基于支架的数据拆分策略和多个测试集，包括与训练数据化学相似性极低的挑战性数据集。我们的结果表明，DeepMETTL3优于传统评分函数，具有更高的准确性、稳健性和可扩展性。关键发现包括训练集中活性与诱饵比例（1:50）对提高性能的重要性，以及在CNN1之后注意力机制的最佳位置对提高泛化能力的作用。DeepMETTL3代表了SBVS在特定靶点机器学习方面的重大进展，提供了一个可适用于其他生物靶点的框架。这项工作强调了深度学习在基于人工智能的药物设计中的潜力，在分子对接和虚拟筛选中平衡了计算效率和预测能力。该评分函数可在https://github.com/juniML/DeepMETTL3上免费获取。
