US 12,423,622 B2
Generative machine learning systems for generating structural information regarding chemical compound
Kenta Oono, Tokyo (JP); Justin Clayton, Tokyo (JP); and Nobuyuki Ota, Tokyo (JP)
Assigned to Preferred Networks, Inc., Tokyo (JP)
Filed by Preferred Networks, Inc., Tokyo (JP)
Filed on Dec. 22, 2023, as Appl. No. 18/394,019.
Application 18/394,019 is a continuation of application No. 17/000,746, filed on Aug. 24, 2020, granted, now 11,900,225.
Application 17/000,746 is a continuation of application No. 15/015,044, filed on Feb. 3, 2016, granted, now 10,776,712, issued on Sep. 15, 2020.
Claims priority of provisional application 62/262,337, filed on Dec. 2, 2015.
Prior Publication US 2024/0144092 A1, May 2, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06N 3/047 (2023.01); G06N 7/01 (2023.01); G16C 20/50 (2019.01); G16C 20/70 (2019.01)
CPC G06N 20/00 (2019.01) [G06N 3/047 (2023.01); G06N 7/01 (2023.01); G16C 20/50 (2019.02); G16C 20/70 (2019.02)] 29 Claims
OG exemplary drawing
 
1. A computer system comprising:
one or more memories; and
one or more processors configured to:
cause a generative model to generate structural information regarding a chemical compound by inputting a latent representation into the generative model,
wherein the generative model has been trained such that differences between structural information regarding other chemical compounds and reconstructions of the structural information regarding the other chemical compounds generated by the generative model are reduced, the reconstructions being generated by inputting latent representations into the generative model, the latent representations being generated based on the structural information regarding the other chemical compounds,
wherein the structural information regarding the chemical compound expresses, and uniquely identifies, a chemical structure of atoms and bonds of the chemical compound, and
wherein the generative model is a deep-neural-network-based decoder that decodes the latent representation into the structural information regarding the chemical compound that expresses, and uniquely identifies, the chemical structure of the atoms and bonds of the chemical compound.