English

Learning to design drug-like molecules in three-dimensional space using deep generative models

Quantitative Methods 2021-09-16 v1 Machine Learning

Abstract

Recently, deep generative models for molecular graphs are gaining more and more attention in the field of de novo drug design. A variety of models have been developed to generate topological structures of drug-like molecules, but explorations in generating three-dimensional structures are still limited. Existing methods have either focused on low molecular weight compounds without considering drug-likeness or generate 3D structures indirectly using atom density maps. In this work, we introduce Ligand Neural Network (L-Net), a novel graph generative model for designing drug-like molecules with high-quality 3D structures. L-Net directly outputs the topological and 3D structure of molecules (including hydrogen atoms), without the need for additional atom placement or bond order inference algorithm. The architecture of L-Net is specifically optimized for drug-like molecules, and a set of metrics is assembled to comprehensively evaluate its performance. The results show that L-Net is capable of generating chemically correct, conformationally valid, and highly druglike molecules. Finally, to demonstrate its potential in structure-based molecular design, we combine L-Net with MCTS and test its ability to generate potential inhibitors targeting ABL1 kinase.

Keywords

Cite

@article{arxiv.2104.08474,
  title  = {Learning to design drug-like molecules in three-dimensional space using deep generative models},
  author = {Yibo Li and Jianfeng Pei and Luhua Lai},
  journal= {arXiv preprint arXiv:2104.08474},
  year   = {2021}
}
R2 v1 2026-06-24T01:16:16.110Z