Invention Grant
- Patent Title: Analyzing complex single molecule emission patterns with deep learning
-
Application No.: US17309027Application Date: 2019-06-10
-
Publication No.: US12002185B2Publication Date: 2024-06-04
- Inventor: Peiyi Zhang , Fang Huang , Sheng Liu
- Applicant: Purdue Research Foundation
- Applicant Address: US IN West Lafayette
- Assignee: Purdue Research Foundation
- Current Assignee: Purdue Research Foundation
- Current Assignee Address: US IN West Lafayette
- Agency: Maginot, Moore & Beck LLP
- International Application: PCT/US2019/036262 2019.06.10
- International Announcement: WO2020/081125A 2020.04.23
- Date entered country: 2021-04-15
- Main IPC: G06T3/40
- IPC: G06T3/40 ; G01J3/28 ; G01J3/443 ; G01N21/64 ; G06N3/08 ; G06T3/4046

Abstract:
A fluorescent single molecule emitter simultaneously transmits its identity, location, and cellular context through its emission patterns. A deep neural network (DNN) performs multiplexed single-molecule analysis to enable retrieving such information with high accuracy. The DNN can extract three-dimensional molecule location, orientation, and wavefront distortion with precision approaching the theoretical limit of information content of the image which will allow multiplexed measurements through the emission patterns of a single molecule.
Public/Granted literature
- US20220020115A1 Analyzing Complex Single Molecule Emission Patterns with Deep Learning Public/Granted day:2022-01-20
Information query