System and method for prediction of protein-ligand bioactivity using point-cloud machine learning
US11256995B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 22, 2021 |
| Grant date | Feb 22, 2022 |
| Priority date | — |
| Expiry date | Apr 22, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method that predicts whether a given protein-ligand pair is active or inactive, the ground-truth protein-ligand complex crystalline-structure similarity, and an associated bioactivity value. The system and method further produce 3-D visualizations of previously unknown protein-ligand pairs that show directly the importance assigned to protein-ligand interactions, the positive/negative-ness of the saliencies, and magnitude. Furthermore, the system and method make enhancements in the art by accurately predicting protein-ligand pair bioactivity from decoupled models, removing the need for docking simulations, as well as restricting attention of the machine learning between protein and ligand atoms only.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.