Noninvasive cancer detection by extracting and integrating multi-modal data from whole-methylome sequencing of plasma cell-free DNA

Abstract

Plasma cell-free DNA (cfDNA) methylation and fragmentation signatures have been shown to be valid biomarkers for blood-based cancer detection. However, conventional methylation sequencing assays are inapplicable for fragmentomic profiling due to bisulfite-induced DNA damage. Here using enzymatic conversion-based low-pass whole-methylome sequencing (WMS), we developed a novel approach to comprehensively interrogate the genome-wide plasma methylation, fragmentation, and copy number profiles for sensitive and noninvasive multi-cancer detection. With plasma WMS data from a clinical cohort comprising 497 healthy controls and 780 patients with both early- and advanced-stage cancers of the breast, colorectum, esophagus, stomach, liver, lung, or pancreas, genomic features including methylation, fragmentation size, copy number alteration, and fragment end motif were extracted individually and subsequently integrated to develop an ensemble cancer classifier, called THEMIS, using machine learning algorithms. THEMIS outperformed individual biomarkers for differentiating cancer patients of all seven types from healthy individuals and achieved a combined area under the curve value of 0.971 in the independent test cohort, translating to a sensitivity of 86% and early-stage (I and II) sensitivity of 77% at 99% specificity. In addition, we built a cancer signal origin classifier with true-positive cancer samples at 100% specificity based on methylation and fragmentation profiling of tissue-specific accessible regulatory elements, which localized cancer-like signal to a limited number of clinically informative sites with 66% accuracy. Overall, this proof-of-concept work demonstrates the feasibility of extracting and integrating multi-modal biomarkers from a single WMS run for noninvasive detection and localization of common cancers across stages.

Multidimensional Analysis of a Cell-Free DNA Whole Methylome Sequencing Assay for Early Detection of Gastric Cancer: Protocol for an Observational Case-Control Study

“…We have also previously developed a multidimensional ensemble model named Thorough Epigenetic Marker Integration Solution (THEMIS). This model integrates various cfDNA features, including methylated fragment ratio (MFR), chromosomal aneuploidy of featured fragments (CAFF), fragment size index (FSI), and fragment end motif (FEM), enabling highly sensitive early detection across a pan-cancer cohort [ 27 ]. In a subgroup comprising 114 patients with GC and 497 healthy controls, the THEMIS model showed an estimated area under the curve of 0.983 for the training data set ( Figure 1 A) and 0.986 for the test data set ( Figure 1 B).…”

Multidimensional Analysis of a Cell-Free DNA Whole Methylome Sequencing Assay for Early Detection of Gastric Cancer: Protocol for an Observational Case-Control Study (Preprint)

“…We have also previously developed a multidimensional ensemble model named Thorough Epigenetic Marker Integration Solution (THEMIS). This model integrates various cfDNA features, including methylated fragment ratio (MFR), chromosomal aneuploidy of featured fragments (CAFF), fragment size index (FSI), and fragment end motif (FEM), enabling highly sensitive early detection across a pan-cancer cohort [27]. In a subgroup comprising 114 patients with GC and 497 healthy controls, the THEMIS model showed an estimated area under the curve of 0.983 for the training data set (Figure 1A) and 0.986 for the test data set (Figure 1B).…”

Development and validation of a blood-based assay for gastric cancer early detection: A multidimensional analysis of cell-free DNA whole methylome sequencing—protocol for an observational, case‒control study

“…The combination of several features has enhanced detection sensitivity compared to a single feature in kidney cancer (25), hepatocellular cancer, and pancreatic ductal cancer (26). We have also previously developed a multidimensional ensemble model named THorough Epigenetic Marker Integration Solution (THEMIS), which integrates several cfDNA features, such as methylation patterns, chromosomal copy number alterations, and fragmentation pro les, enabling highly sensitive early detection in a pancancer cohort (27). In the subgroup comprising 114 GC patients and 497 healthy controls, the THEMIS model showed an estimated AUC of 0.983 for the training dataset (Fig.…”