Epigenetic Classifier for Tumor Variant Origin Differentiation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current liquid biopsy next-generation sequencing (NGS) assays face challenges in differentiating between tumor and clonal hematopoiesis of indeterminate potential (CHIP) nucleic acid variants, as they often observe confounding genomic signals from white blood cells, making it difficult to determine the origin of nucleic acid variants.

Innovation Solution

The method involves determining sequence data and epigenetic or fragmentomic data from nucleic acid samples, using machine learning algorithms to train predictive models that differentiate between tumor and CHIP origin nucleic acid variants by identifying epigenetic signatures and fragment patterns specific to each origin.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If liquid biopsy NGS assays are used to detect nucleic acid variants, then cancer detection capability is improved, but differentiation between tumor and CHIP origin variants deteriorates due to confounding genomic signals from white blood cells

Engineering Contradiction:

Improvecancer detection capabilityVSAvoidvariant origin differentiation accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent introduces an epigenetic classifier as an intermediary tool that processes NGS data to distinguish tumor-derived variants from CHIP-derived variants. This classifier uses epigenetic features (such as methylation patterns) as mediating characteristics to resolve the ambiguity in variant origin attribution, thereby improving measurement precision without compromising cancer detection capability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the analytical parameters by incorporating epigenetic features (methylation levels, chromatin accessibility) alongside traditional sequence data. By adding these new parameters to the analysis framework, the system can differentiate between tumor and CHIP variants more accurately while maintaining the sensitivity required for cancer detection

Inventive Principle:

Principle #35Parameter changes

2Quantity of substance

If conventional NGS assays sequence genomic regions from multiple samples, then variant detection coverage is improved, but the ability to adjudicate variant origin deteriorates due to accumulated mutations in blood cells

Engineering Contradiction:

Improvesequence data coverageVSAvoidvariant origin information

Core Design Contradiction:

Quantity of substanceVSLoss of information

Solution Approach 1:

The patent adds another dimension to the analysis by incorporating epigenetic data (such as methylation status and chromatin conformation) alongside traditional sequence data. This multi-dimensional approach allows the system to maintain comprehensive variant detection coverage while recovering lost variant origin information through orthogonal biological features that differ between tumor and blood cell variants

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS20240021271A1Methods and systems for predicting an origin of a variant

Publication Date: 2024.01.18 GUARDANT HEALTH INC

AI summary

Provided herein are methods for differentiating tumor and non-tumor (e.g., clonal hematopoiesis of indeterminate potential (CHIP)) origin nucleic acid variants from one another in a test sample obtained from a test subject at least partially using a computer. Other aspects are directed to methods of treating disease in subjects. Yet other aspects include related systems and computer readable media used to differentiating tumor and non-tumor origin nucleic acid variants from one another.