Molecular Conformer Search with Low-Energy Latent Space

Xiaomi Guo, Lincan Fang, Yong Xu, Wenhui Duan, Patrick Rinke, Milica Todorović, Xi Chen*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)
37 Downloads (Pure)


Identifying low-energy conformers with quantum mechanical accuracy for molecules with many degrees of freedom is challenging. In this work, we use the molecular dihedral angles as features and explore the possibility of performing molecular conformer search in a latent space with a generative model named variational auto-encoder (VAE). We bias the VAE towards low-energy molecular configurations to generate more informative data. In this way, we can effectively build a reliable energy model for the low-energy potential energy surface. After the energy model has been built, we extract local-minimum conformations and refine them with structure optimization. We have tested and benchmarked our low-energy latent-space (LOLS) structure search method on organic molecules with 5-9 searching dimensions. Our results agree with previous studies.

Original languageEnglish
Pages (from-to)4574−4585
JournalJournal of Chemical Theory and Computation
Issue number7
Publication statusPublished - 12 Jul 2022
MoE publication typeA1 Journal article-refereed


Dive into the research topics of 'Molecular Conformer Search with Low-Energy Latent Space'. Together they form a unique fingerprint.

Cite this