USPTO Machine-Learning Framework Patent for Cancer Analysis

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted a patent (US12584176B2) to Tempus AI, Inc. for an integrated machine-learning framework designed to estimate homologous recombination deficiency in cancer patients. This framework aims to improve cancer treatment predictions and outcomes by analyzing various genetic and tumor purity factors.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has issued patent US12584176B2 to Tempus AI, Inc. The patent covers methods, systems, and software for determining a homologous recombination pathway status of cancer in a test subject. This technology utilizes machine learning classifiers that analyze DNA damage repair gene heterozygosity, loss of heterozygosity across the genome, variant alleles in DNA damage repair genes (in both cancerous and non-cancerous tissue), and tumor sample purity to enhance cancer treatment predictions.

This patent grant represents a new intellectual property asset for Tempus AI, Inc. in the field of AI-driven cancer diagnostics and treatment. While not a regulatory rule imposing obligations on other entities, it signifies innovation in the application of AI and machine learning within the healthcare and pharmaceutical sectors. Companies operating in this space, particularly those developing AI-powered diagnostic tools or personalized medicine solutions, should be aware of this granted patent as it may impact their own patent strategies and freedom to operate in related areas.

Source document (simplified)

← USPTO Patent Grants

Integrated machine-learning framework to estimate homologous recombination deficiency

Grant US12584176B2 Kind: B2 Mar 24, 2026

Assignee

Tempus AI, Inc.

Inventors

Aarti Venkat, Jerod Parsons, Joshua SK Bell, Catherine Igartua, Yilin Zhang, Ameen Salahudeen, Verönica Sänchez Freire, Robert Tell

Abstract

Methods, systems, and software are provided for determining a homologous recombination pathway status of a cancer in a test subject, e.g., to improve cancer treatment predictions and outcomes. In some embodiments, classifiers using one or more of (i) a heterozygosity status for DNA damage repair genes in a cancerous tissue, (ii) a measure of the loss of heterozygosity across the genome of the cancerous tissue, (iii) a measure of variant alleles detected in a second plurality of DNA damage repair genes in the genome of the cancerous tissue, (iv) a measure of variant alleles detected in the second plurality of DNA damage repair genes in the genome of a non-cancerous tissue, and (v) tumor sample purity are provided.