1. Dataset Construction to Explore Chemical Space with 3D Geometry and Deep Learning
- Author
-
Yingkai Zhang, Song Xia, Jianing Lu, and Jieyu Lu
- Subjects
Models, Molecular ,010304 chemical physics ,Basis (linear algebra) ,business.industry ,Computer science ,General Chemical Engineering ,Deep learning ,General Chemistry ,Large fragment ,Library and Information Sciences ,01 natural sciences ,Article ,Chemical space ,0104 chemical sciences ,Computer Science Applications ,Merck Molecular Force Field ,010404 medicinal & biomolecular chemistry ,Deep Learning ,0103 physical sciences ,Molecule ,Artificial intelligence ,3d geometry ,business ,Algorithm ,Energy (signal processing) - Abstract
A dataset is the basis of deep learning model development, and the success of deep learning models heavily relies on the quality and size of the dataset. In this work, we present a new data preparation protocol and build a large fragment-based dataset Frag20, which consists of optimized 3D geometries and calculated molecular properties from Merck molecular force field (MMFF) and DFT at the B3LYP/6-31G* level of theory for more than half a million molecules composed of H, B, C, O, N, F, P, S, Cl, and Br with no larger than 20 heavy atoms. Based on the new dataset, we develop robust molecular energy prediction models using a simplified PhysNet architecture for both DFT-optimized and MMFF-optimized geometries, which achieve better than or close to chemical accuracy (1 kcal/mol) on multiple test sets, including CSD20 and Plati20 based on experimental crystal structures.
- Published
- 2021