US 12542196 B2 / Feb 3, 2026

Unsupervised invertible physics-based vector representation for molecules

The Artificial Intelligence engine can perform one or more operations. A query can be submitted to the Artificial Intelligence engine to search directly for a set of targeted properties for an unnamed molecule having the set of targeted properties. An indication of a structure of one or more candidate molecules found to have the set of targeted properties with the Artificial Intelligence engine is generated by applying one or more machine learning algorithms. The indication of the structure of the one or more candidate molecules found to satisfy the set of targeted properties in 3-dimensional space is supplied to a user in response to the query for the set of targeted properties to the Artificial Intelligence engine.

Publication details

Recorded assignee
SRI International
Publication number
US 12542196 B2
Publication type
Utility patent grant
Publication date
Feb 3, 2026
Filing date
Jun 23, 2021
CPC classes
G06N20/00, G06N3/042, G06N3/044, G06N3/0442, G06N3/0455, G06N3/0464, G06N3/0475, G06N3/09, G06N3/092, G16B15/00, G16B40/00, G16C20/30, G16C20/50, G16C20/70
Inventors
Byrnes; John J., Rohwer; Richard J., Luebke; Kevin J., Madrid; Peter

Party names reflect the published document. Current ownership and legal status can change.

View patent publication →

Your defense tech briefing

Security verification will run before you submit.