Author:
Xu Yuzhi,Liu Xinxin,Ge Jiankai,Xia Wei,Ju Cheng-Wei,Zhang Haiping,Zhang John Z.H.
Abstract
AbstractThe rapid advancement of machine learning, particularly deep learning, has propelled significant strides in drug discovery, offering novel methodologies for molecular property prediction. However, despite these advancements, existing approaches often face challenges in effectively extracting and selecting relevant features from molecular data, which is crucial for accurate predictions. Our work introduces ChemXTree, a novel graph-based model that integrates tree-based algorithms to address these challenges. By incorporating a Gate Modulation Feature Unit (GMFU) for refined feature selection and a differentiable decision tree in the output layer. Extensive evaluations on benchmark datasets, including MoleculeNet and eight additional drug databases, have demonstrated ChemXTree’s superior performance, particularly in feature optimization. Permutation experiments and ablation studies further validate the effectiveness of GMFU, positioning ChemXTree as a significant advancement in molecular informatics, capable of rivaling state-of-the-art models.
Publisher
Cold Spring Harbor Laboratory