Data based cancer research and treatment systems and methods

Patent No. US11640859 (titled "Data based cancer research and treatment systems and methods") on Oct 17, 2019. The application was issued on May 2, 2023.

What is this patent about?

’859 is related to the field of genomic sequencing and clinical data management, specifically within the context of cancer research and personalized treatment planning. The invention addresses the technical challenge of integrating disparate, often unstructured data sources—such as raw medical records, next-generation sequencing (NGS) results, and experimental organoid responses—into a unified system that can drive diverse clinical and analytical software applications.

The underlying idea behind ’859 is a multi-tiered data architecture that progressively transforms raw, messy medical information into highly specialized, application-ready formats. Instead of forcing all users to query a single, rigid database, the system utilizes a cascading data-shaping pipeline. This pipeline moves data from a flexible 'lake' for raw storage to a 'vault' optimized for global searching, and finally into 'marts' where the data is restructured specifically to meet the unique interface requirements of different end-user tools, such as physician dashboards or researcher analytics.

The claims of ’859 focus on a method for managing genomic and clinical data through a three-database hierarchy. The process involves capturing original clinical records and NGS data from both cancerous and normal cells, storing them in a semi-structured first database, and then 'shaping' this information into a second database optimized for search. Crucially, the independent claims cover the further step of selecting application-specific subsets of this data and storing them in a third database with a structure specifically optimized for application program interfacing.

In practice, the invention functions as a high-speed translation layer between the lab and the clinic. When a patient’s tumor is sequenced or grown into tissue organoids for drug testing, the resulting efficacy data is ingested alongside historical clinical records. Automated micro-services, such as OCR and natural language processing, work in tandem with human abstractors to normalize this data. This ensures that when a physician opens a treatment planning tool, the system doesn't just provide a list of mutations, but rather a curated, application-specific view that correlates those mutations with proven treatment efficacies and available clinical trials.

This approach differs from prior solutions by decoupling the data storage format from the user interface requirements, allowing for a loosely coupled micro-service architecture. Traditional systems often suffer from performance bottlenecks or rigid schemas that cannot easily adapt to new types of genomic insights. By maintaining three distinct database layers—the data lake, the data vault, and the data marts—the invention allows for rapid system evolution and ensures that complex queries for large-scale research do not interfere with the real-time performance of clinical decision-support tools.

How does this patent fit in bigger picture?

Technical Landscape

In the late 2010s when ’859 was filed, clinical oncology systems commonly relied on fragmented data silos where genomic sequencing, pathology reports, and longitudinal clinical records were managed as disparate datasets rather than integrated assets. At a time when next-generation sequencing (NGS) was typically implemented using specialized, standalone bioinformatics pipelines, the lack of standardized data normalization made the correlation between specific genetic alterations and long-term treatment efficacy non-trivial. Furthermore, software constraints in medical informatics often forced a trade-off between system speed and data depth, as monolithic architectures made it difficult to rapidly update clinical decision support tools with emerging research insights without extensive manual reprogramming.

Prosecution Position

The disclosed invention represents a meaningful technical advancement through the implementation of a modular micro-service architecture that enables the rapid integration and normalization of multi-modal healthcare data, including NGS results, clinical records, and organoid treatment efficacy. By compartmentalizing system processes into loosely coupled micro-services that consume and generate defined data products, the architecture overcomes the technical constraint of system rigidity, allowing for the simultaneous development and updating of analytical tools without disrupting the core database. This structural shift is further enhanced by a multi-tier database strategy—comprising a data lake for auditing, a data vault for optimized searching, and data marts for application-specific interfacing—which enables the high-speed delivery of complex genomic-clinical correlations to diverse user types, such as physicians and researchers, through purpose-built interfaces.

Claims

This patent contains a total of 83 claims, with claims 1 and 81 serving as the independent claims. The independent claims focus on methods for conducting genomic sequencing and managing cancer patient data through a multi-stage database architecture that integrates clinical records, genomic sequencing data, and organoid treatment efficacy information to optimize data for searching and application-specific interfacing. The dependent claims serve to further specify technical implementations such as the use of micro-service programs and alert lists, identify specific genetic markers and sequencing panels, define various cancer treatment types and immunotherapies, and detail the specific biological sources and formats of the clinical and genomic data processed within the system.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Next generation genomic sequencer
(Claim 1)
Next generation sequencing involves using specialized equipment such as a next generation gene sequencer, which is an automated instrument that determines the order of nucleotides in DNA and RNA. The instrument reports the sequences as a string of letters, called a read, which the analyst compares to one or more reference genomes of the same genes.An automated instrument used to determine the nucleotide order in DNA and RNA, generating 'reads' that are compared against reference genomes to identify variants.
Semi-structured first database
(Claim 1, Claim 81)
The data lake database includes, among other data, original raw data as well as interim micro-service data products and is used primarily to memorialize original raw data and data progression for auditing purposes and to enable data recreation that is tied to prior points in time. In at least some embodiments the first database includes both unstructured original clinical data records and semi-structured data generated by the micro-service programs.A primary storage repository (referred to as a 'data lake') that holds raw, original clinical records and genomic data in their native formats to memorialize data progression and enable auditing.
Structure optimized for application program interfacing
(Claim 1, Claim 81)
The data marts database includes data structured to support specific user application programs and user interfaces including original as well as derived data. By storing system data in purpose specific data structures, a diverse array of system functionality is optimally enabled.A specialized data arrangement (referred to as 'data marts') tailored to the specific requirements of individual user interfaces or software tools, such as physician suites or pathology modules.
System structured data
(Claim 1, Claim 81)
The data vault database includes data structured optimally to support database access and manipulation and typically includes routinely accessed original data as well as derived data. Shaping at least a subset of the first database data to generate system structured data including clinical record data and sequencing data wherein the system structured data is optimized for searching.Data that has been processed and normalized from its original form into a specific schema (referred to as a 'data vault') designed to facilitate efficient database searching and manipulation by researchers or data scientists.
Tissue organoids
(Claim 81)
The method comprising the steps of... obtaining a tumor specimen from the patient; growing the tumor specimen into a plurality of tissue organoids; treating each tissue organoids with an organoid specific treatment; collecting and storing organoid treatment efficacy information in the first database.In vitro biological structures grown from a patient's tumor specimen used to test the efficacy of specific treatments outside of the patient's body.

Litigation Cases New

US Latest litigation cases involving this patent.

Case NumberFiling DateTitle
3:25-cv-00621Mar 14, 2025Tempus Ai, Inc. V. Guardant Health, Inc.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Get instant alerts for new documents

US11640859

Application Number
US16771451A
Filing Date
Oct 17, 2019
Publication Date
May 2, 2023
External Links
Slate, USPTO , Google Patents