Freenome had two patents in artificial intelligence during Q3 2023. Freenome Inc has filed patents for methods and systems that use autoantibody biomarkers and cell-free nucleic acids to detect and classify colon cell proliferative disorders, including colorectal cancer. The methods involve using machine learning models to generate classifiers that can stratify populations and distinguish between healthy individuals, cancer patients, and different disease subtypes or stages. These techniques can be used for early detection, prediction, prognosis, and monitoring of treatment response and disease development. GlobalData’s report on Freenome gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Freenome grant share with artificial intelligence as a theme is 0% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.
Application: Markers for the early detection of colon cell proliferative disorders (Patent ID: US20230243830A1)
Freenome Inc. has filed a patent for a method of detecting and treating colorectal cancer using a computer programmed with specific instructions. The method involves obtaining an autoantibody profile from a biological sample of the subject, which includes measuring the amount of autoantibodies from a predetermined panel of autoantibodies. The panel consists of autoantibodies to at least three antigens, such as NME5, USP16, UBE2S, RNF41, CD20, ANKHD1, TXNL1, NAT6, Supt6h, PRDM8, OTUD5, PNKP, SRSF7, ASB9, NXN, ZBTB21, EYA1, GSPT1, MLIP, RBM38, ARMC5, TP53, BRD9, CDK4, PRMT6, PCOLCE, and SDCBP. The autoantibody profile is then processed using a trained machine learning model to distinguish between subjects with colorectal cancer and those without. This provides an output value associated with the presence of colorectal cancer, allowing for the identification of the cancer in the subject. The method also includes detecting or treating the colorectal cancer based on the identification.
The patent claims also include variations of the method, such as using IgG autoantibodies, IgM autoantibodies, or a combination of both. The predetermined autoantibody panel can be configured to distinguish between healthy subjects, subjects with benign colon polyps, subjects with advanced adenoma, and subjects with colorectal cancer. The biological sample can be obtained from various sources, including body fluids, stool, urine, blood, tissue biopsy, and more. The colorectal cancer can encompass different types, such as adenoma, polyposis disorder, Lynch syndrome, colorectal dysplasia, colon cancer, rectal cancer, lymphoma, and sarcoma.
The patent also covers the use of the computer to determine the methylation status of nucleic acid molecules in the biological sample and to measure the amount of proteins in the sample. These additional data can be processed using the trained machine learning model to further enhance the detection and treatment of colorectal cancer.
In summary, Freenome Inc.'s patent describes a method of detecting and treating colorectal cancer using a computer programmed with specific instructions. The method involves obtaining an autoantibody profile from a biological sample, processing it using a trained machine learning model, and using the output value to identify and treat the cancer. The patent also covers variations of the method, including the use of different types of autoantibodies, sample sources, and additional data such as methylation status and protein levels.