Patent · US Active

Molecular graph generation from structural features using an artificial neural network

US12217834B2 · kind B2 · utility

0Cited by
2References
31Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 29, 2020
Grant dateFeb 4, 2025
Priority date
Expiry dateJul 5, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG16C20/80
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Discovering molecules (which may be known or may never have been cataloged or ever synthesized) that have desired characteristics is addressed using a machine learning approach. As compared to a brute-force search of a database of known molecules, which may not be computationally feasible, the present machine learning approach renders identification of both known and unknown molecules computationally tractable. Furthermore, the computational effort is largely shifted to training of the machine learning system using a database of known molecules, and the generation of molecules to match any particular characteristics requires relatively little computation. The molecules using the present approach may be further studied, for example, with computer-based simulation or after physical synthesis using biological experimentation to ultimately yield useful chemical compounds.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.