Cancer CellNet
Case ID:
C15632
Disclosure Date:
9/6/2019
Unmet Need Cancer is a formidable healthcare challenge and, in the case of solid tumors, tumor metastases are the primary cause of all mortality. Patients presenting with metastatic tumors originating from an unknown primary malignancy represent a significant clinical challenge. Unmasking the origin of metastatic tumors could advance the successful treatment and management of this patient population.
Technology Overview Cancer CellNet is a machine learning algorithm that can type and subtype cancer metastases using tumor transcriptomic data. In addition, the Johns Hopkins inventors’ method quickly identifies tumor type features, which shortens the required classifier training time. Armed with this information, clinicians can more successfully tailor patient therapy. In addition, cancer researchers can apply the machine learning algorithm to differentiate the most appropriate cancer model for their studies. Stage of Development Cancer CellNet has successfully determined cancer type and subtype from cancer cell lines, engineered mouse models, and patient-derived xenografts. Johns Hopkins University is seeking partners to validate the diagnostic in the clinical setting.
Publications N/A
Patent Information:
Title
App Type
Country
Serial No.
Patent No.
File Date
Issued Date
Expire Date
Patent Status
METHODS, SYSTEMS, AND RELATED COMPUTER PROGRAM PRODUCTS FOR EVALUATING CANCER MODEL FIDELITY
Provisional