Data based cancer research and treatment systems and methods

Inventors

Colley, Christopher Shane • Simpson, Isaiah • Reuter, Brian • Tell, Robert • Lefkofsky, Hailey • Lane, Hunter • White, Kevin • Beaubier, Nike • Bush, Stephen • Khan, Aly • Lau, Denise • Shah, Kaanan • Lefkofsky, Eric

Assignees

Tempus AI Inc

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Publication Number

US-12112839-B2

Patent

Publication Date

2024-10-08

Expiration Date


Abstract

A method and system comprising storing a set of user application programs each requiring an application specific subset of data to perform application processes and generate a respective genomic variant characterization for each of a plurality of patients with cancerous cells and receiving cancer treatment. The method including, obtaining clinical records data including cancer related information, generating genomic sequencing data for the patient's cancerous cells and normal cells, shaping at least a subset of the genomic sequencing data to generate system structured data. Storing the system structured data in a first database, selecting the application specific data from the first database, storing the application specific data in a second database for application program interfacing, receiving the respective genomic variant characterization from the user application program, and storing the genomic variant characterization from the user application program in a third database.

Core Innovation

The disclosed subject matter provides a method, system, and non-transitory computer-readable storage medium for managing clinical records and conducting genomic sequencing for subjects with cancer who receive cancer treatment. The platform obtains clinical records data comprising cancer state, treatment type, and treatment efficacy information, and generates genomic sequencing data for cancerous and normal cells. It shapes at least a subset of the genomic sequencing data into system structured data and stores the structured data in a first database.

For each user application program, the platform selects an application-specific subset of data and stores it in an interface-optimized structure within a second database. The user application programs execute application processes using these subsets and return genomic variant characterizations, which are received and stored in a third database. Because the provided inputs do not include the background section, the specific problem being solved is not explicitly described in patent.

The additional disclosure details clinical-document abstraction, histology image analysis for microsatellite instability or PD-L1 prediction, and RNA-sequencing deconvolution for sample composition analysis. The platform further incorporates voice-activated oncology collaboration interfaces, propensity-score-matched cohort survival analyses, and patient matching to investigational therapies or clinical trials based on clinical and genomic datasets.

Claims Coverage

The claims include three independent claims, comprising an independent method claim, an independent system claim, and an independent non-transitory computer-readable storage medium claim, encompassing three core inventive features.

Method for conducting genomic sequencing and structured data management

Claim 1 covers obtaining original clinical records data and generating genomic sequencing data for cancerous and normal cells from cancer subjects receiving treatment, shaping at least a subset into system structured data in a first database, selecting and storing application-specific data subsets in an interface-optimized second database, and storing resulting genomic variant characterizations in a third database.

Processing-device system for clinical and genomic data management

Claim 19 covers a computer with a processing device configured to obtain clinical records data and genomic sequencing data for cancerous and normal cells, shape sequencing data into system structured data in a first database, provide application-specific data subsets to user application programs via a second database, and store resulting genomic variant characterizations in a third database.

Computer-readable storage medium for genomic sequencing data processing

Claim 20 covers a non-transitory computer-readable storage medium storing program instructions that cause a processor to obtain clinical records and genomic sequencing data, shape and store system structured data, supply application-specific data subsets to user application programs, and store the resulting genomic variant characterizations in a third database.

The three independent claims recite a shared genomic and clinical data-processing workflow across method, system, and non-transitory computer-readable storage medium implementations. The inventive features require structuring and storing clinical and genomic sequencing data, supplying application-specific subsets to user application programs, and storing returned genomic variant characterizations.

Stated Advantages

Adversarial training is described as reducing cancer-type bias and improving cross-cancer generalization, while also improving validation accuracy compared with non-adversarial training.

Documented Applications

Conducting genomic sequencing and processing clinical records data and genomic variant characterizations via user application programs for subjects with cancerous cells receiving treatment.

Clinical-record management, abstraction, and quality-assurance validation using platforms featuring configurable validation rules and interfaces.

Predictive cancer applications and analytics, including identifying highly efficacious treatments, comparing treatment efficacy across genomic subsets, and identifying immunotherapies associated with clinical response based on biomarkers such as genomic alterations, microsatellite instability, and tumor-mutational burden.

Deep-learning histopathology image analysis to predict microsatellite instability and PD-L1 status, including digital tissue segmentation into tissue-class and cell-level overlays for tumor, immune, epithelium, and stroma.

RNA-sequencing data processing, including multimodal normalization, RNA-seq deconvolution, and cancer composition analysis using cell-type expression profiles.

Cohort analysis and propensity-score-matched survival analyses comparing treatment and control cohorts to assess treatment effects and prognostic factors.

Patient-similarity analytics, matching patients to clinical trials and investigational therapies, tracking research-site capabilities, and voice-activated collaboration querying of clinical and genomic datasets.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.