Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion

Autor:	Du, Weitao, Chen, Jiujiu, Zhang, Xuecang, Ma, Zhiming, Liu, Shengchao
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Quantitative Biology - Biomolecules
Druh dokumentu:	Working Paper
Popis:	Recently, artificial intelligence for drug discovery has raised increasing interest in both machine learning and chemistry domains. The fundamental building block for drug discovery is molecule geometry and thus, the molecule's geometrical representation is the main bottleneck to better utilize machine learning techniques for drug discovery. In this work, we propose a pretraining method for molecule joint auto-encoding (MoleculeJAE). MoleculeJAE can learn both the 2D bond (topology) and 3D conformation (geometry) information, and a diffusion process model is applied to mimic the augmented trajectories of such two modalities, based on which, MoleculeJAE will learn the inherent chemical structure in a self-supervised manner. Thus, the pretrained geometrical representation in MoleculeJAE is expected to benefit downstream geometry-related tasks. Empirically, MoleculeJAE proves its effectiveness by reaching state-of-the-art performance on 15 out of 20 tasks by comparing it with 12 competitive baselines. Comment: NeurIPS 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.03475 Zobrazit plný text záznamu View this record from Arxiv