Transfer learning for molecular structure generation
US12079730B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 28, 2020 |
| Grant date | Sep 3, 2024 |
| Priority date | — |
| Expiry date | May 31, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG16C20/70
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques regarding generating molecular structures with attributes of interest are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a transfer learning component that determines a molecular structure of a compound by employing a transfer learning process that utilizes lessons learned from an unconditional generative machine learning model to train a conditional machine learning model that regards a target attribute profile.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.