Therapy Areas: Inflammatory Diseases
New Data from Universal DX Demonstrates Effective Detection of Early-stage Colorectal Cancer Using Combination of Methylation, Fragmentation and Machine Learning
26 January 2023 - - US-based bioinformatics and multi-omics company Universal Diagnostics (Universal DX) has posted the results of an international, observational cohort study which evaluated the effectiveness of utilizing a combination of cell-free DNA (cfDNA) methylation, fragmentation and machine learning to detect early-stage colorectal cancer, the company said.

This is the latest in a series of findings from Universal DX; TODAY's news demonstrates the use of methylation and fragmentation characteristics of cancer-related cfDNA regions, combined with a machine-learning algorithm is highly accurate for early-stage CRCs (92% sensitivity at 94% specificity).

These results were achieved on a prospectively collected patient sample set from four different populations: the US, Spain, Germany, and Ukraine.

Universal DX has previously shown that non-invasive blood testing can be used to detect CRC and pre-cancerous advanced adenomas through both analysis of cell-free circulating tumor DNA (ctDNA) methylation, fragmentation and microbiome patterns with single targeted sequencing analysis and combining it with advanced computational biology and machine learning algorithms.

In 2022, the company extended early-stage colorectal cancer detection to prognostics and stratification; the ability to do so could lead to better outcomes and improved survival rates.

Prediction model that utilized a panel of methylation and fragmentation scores originating from cfDNA biomarkers that belong to relevant cancer development and progression-related pathways correctly classified 92% (87/95) of CRC patients.

Sensitivity per cancer stage ranged from 91% (21/23) for stage I, 92% (23/25) for stage II, 91% (30/33) for stage III and 93% (13/14) for stage IV.

Fragmentation signals contributed most to early-stage cancers, while methylation signals were more significant for late stage (III-IV) detection.

Specificity of the model was 94% (199/204), with 97% (28/29) NAA (non-advanced adenoma), 93% (116/125) BEN (benign colonoscopy findings of diverticulosis/diverticulitis, hemmorhoids, hyperplastic/inflammatory polyps) and 94% (47/50) cNEG (colonoscopy negative) patients correctly identified.

Lesion location, gender, age and country of origin were not significantly correlated to prediction outcome.

Universal DX leverages proprietary computational biology tools combined with a targeted next generation sequencing assay platform that allows for simultaneous detection of methylation, fragmentation and microbiome signals for highly-sensitive cancer signal scoring of cell-free DNA regions linked to cancer of interest.

Universal DX will present its findings live at the ASCO Gastrointestinal Cancers Symposium in San Francisco, CA on January 21st as poster #201 titled "Use of methylation and fragmentation signals in the detection of early-stage colorectal cancer."


Related Headlines