The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 06, 2026

Filed:

Aug. 07, 2025
Applicant:

Recursion Pharmaceuticals, Inc., Salt Lake City, UT (US);

Inventors:

Alisandra Kaye Denton, Montreal, CA;

Berton Allen Earnshaw, Cedar Hills, UT (US);

Cassandra Lynn Masschelein, Montreal, CA;

Cian Eastwood, London, GB;

Craig Terence Russell, Cambridge, GB;

Hamed Shirzad, Vancouver, CA;

Ihab Bendidi, Paris, FR;

Jan Frederik Wenkel, Montreal, CA;

Liam Duffy Hodgson, Montreal, CA;

Lin Shuan Tu, Vancouver, CA;

Shawn Tamajka Whitfield, Montreal, CA;

Assignee:

Recursion Pharmaceuticals, Inc., Salt Lake City, UT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G16B 40/00 (2019.01); G16B 50/10 (2019.01);
U.S. Cl.
CPC ...
G16B 40/00 (2019.02); G16B 50/10 (2019.02);
Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating a digital perturbed cell with a plurality of virtual perturbed cell response features. More specifically, in one or more embodiments, the present disclosure relates to a flexible, modular latent transfer perturbation neural network that accurately generates virtual perturbed cells. To illustrate, in some embodiments, the disclosed systems utilize a base state neural network to generate a control cell latent representation based on a control cell. Further, the disclosed cells utilize a perturbation neural network to generate a perturbation latent representation based on a multi-perturbation data object. Additionally, in one or more embodiments, the disclosed systems combine the control cell latent representation and the perturbation latent representation and apply a neural network decoder to generate virtual perturbed cell response features.


Find Patent Forward Citations

Loading…