US 12,119,091 B1
Utilizing masked autoencoder generative models to extract microscopy representation autoencoder embeddings
Oren Zeev Kraus, Toronto (CA); Kian Runnels Kenyon-Dean, Toronto (CA); Mohammadsadegh Saberian, Kitchener (CA); Maryam Fallah, Toronto (CA); Peter Foster McLean, Centerville, UT (US); Jessica Wai Yin Leung, Toronto (CA); Vasudev Sharma, Toronto (CA); Ayla Yasmin Khan, Salt Lake City, UT (US); Jaichitra Balakrishnan, Sudbury, MA (US); Safiye Celik, Sudbury, MA (US); Dominique Beaini, Montreal (CA); Maciej Sypetkowski, Warsaw (PL); Chi Cheng, Salt Lake City, UT (US); Kristen Rose Morse, Cottonwood Heights, UT (US); Maureen Katherine Makes, Salt Lake City, UT (US); Benjamin John Mabey, Millcreek, UT (US); and Berton Allen Earnshaw, Cedar Hills, UT (US)
Assigned to Recursion Pharmaceuticals, Inc., Salt Lake City, UT (US)
Filed by Recursion Pharmaceuticals, Inc., Salt Lake City, UT (US)
Filed on Dec. 19, 2023, as Appl. No. 18/545,438.
Int. Cl. G16B 45/00 (2019.01); G06V 10/75 (2022.01); G06V 10/82 (2022.01); G06V 20/69 (2022.01); G16B 20/00 (2019.01); G16B 40/00 (2019.01)
CPC G16B 45/00 (2019.02) [G06V 10/751 (2022.01); G06V 10/82 (2022.01); G06V 20/698 (2022.01); G16B 20/00 (2019.02); G16B 40/00 (2019.02)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a plurality of phenomic images corresponding to a plurality of cell perturbations;
generating, utilizing a masked autoencoder generative model, a plurality of phenomic image autoencoder embeddings for the plurality of cell perturbations from the plurality of phenomic images, wherein the masked autoencoder generative model is trained to generate predicted phenomic images from masked training phenomic images corresponding to training phenomic images;
generating perturbation comparisons utilizing the plurality of phenomic image autoencoder embeddings; and
providing, for display within a graphical user interface, the perturbation comparisons for the plurality of phenomic image autoencoder embeddings.