US Patent Issued to Recursion Pharmaceuticals on Nov. 3 for "Utilizing contrastive machine learning models to extract joint-space molecular-phenomic embeddings from molecular structures or phenomic images" (Canadian, Polish Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,478, issued on Nov. 3, was assigned to Recursion Pharmaceuticals Inc. (Salt Lake City).

"Utilizing contrastive machine learning models to extract joint-space molecular-phenomic embeddings from molecular structures or phenomic images" was invented by Dominique Beaini (Kirkland, Canada), Jan Frederik Wenkel (Montreal), Karush Suri (Montreal), Maciej Sypetkowski (Warsaw, Poland), Philip Fradkin (Toronto) and Puria Azadi Moghadam (Burnaby, Canada).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing a contrastive molecular-phenomic embedding model that l...