Markers for the early detection of colon cell proliferative disorders
Inventors
O'DONOVAN, Brian D. • MAHAJAN, Shivani
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12372528-B2
Publication Date
2025-07-29
Expiration Date
Abstract
Systems, media, compositions, methods, and kits disclosed herein relate to a panel of autoantibody biomarkers for the early detection of colon cell proliferative disorders, including colorectal cancer. The presence or levels of the autoantibodies in a biological sample for the autoantibody panels described herein may be used for classifier generation, and as inputs in machine learning models useful to classify subjects in a population for the detection of colon cell proliferative disorders.
Core Innovation
The disclosure describes a method of treating colorectal cancer in a subject using a specified IgM and IgG autoantibody profile and a trained machine-learning model to detect colorectal cancer, followed by administration of a colorectal cancer treatment in response to detection. The autoantibody profile is obtained by measuring IgM and IgG autoantibodies from predetermined antigen sets in a biological sample. A computer processes the profile using the trained machine-learning model configured to distinguish subjects with colorectal cancer from subjects without colorectal cancer.
The subject matter also encompasses detection and classification of colorectal cancer and precursor lesions, including benign-polyp and advanced-adenoma groups, alongside optional methylation and protein profiles and monitoring applications. Drawing-sheet summaries report logistic-regression ROC and coefficient analyses distinguishing colorectal cancer or pre-cancer from negative controls and benign cases. Reported mean ROC AUC values include 0.75 for a top-five colorectal cancer panel and 0.78 for a top-six panel including UBE2S.
Claims Coverage
The provided relevant claims identify one independent claim with three inventive features directed to detecting and treating colorectal cancer.
Specified IgM and IgG autoantibody profile
The pre-determined set comprises IgM autoantibodies to at least three antigens selected from NME5, USP16, UBE2S, RNF41, CD20, and SDCBP; IgM autoantibodies to at least three selected from PELO, CDK4, MTP1, PRMT6, ZBTB2, and PCOLCE; IgG autoantibodies to at least three selected from ANKHD1, TXNL1, NAT6, Supt6h, PRDM8, OTUD5, PNKP, SRSF7, PCOLCE, and ASB9; IgG autoantibodies to at least three selected from TSSC4, BRD9, BCCIP, and TP53; or a combination of these groups.
Machine-learning detection of colorectal cancer
A computer processes the autoantibody profile using a trained machine-learning model configured to distinguish subjects with colorectal cancer from subjects without colorectal cancer.
Treatment following detection
Responsive to detection, the method administers a colorectal cancer treatment selected from surgery, radiofrequency ablation, chemotherapy, radiation therapy, targeted therapy, and immune therapy.
The independent claim combines specified IgM and IgG autoantibody panels with machine-learning detection and responsive colorectal cancer treatment.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Detecting colorectal cancer from an autoantibody profile and treating the subject in response to detection.
Distinguishing colorectal cancer or colorectal pre-cancer from negative controls and colorectal benign cases using autoantibody-panel analyses and machine-learning classifiers.
Monitoring applications for colorectal cancer.
Interested in licensing this patent?