Integrative modeling of tumor genomes and epigenomes for enhanced cancer diagnosis by cell-free DNA
Mingyun Bae, Gyuhee Kim, Tae-Rim Lee, Jin Mo Ahn, Hyunwook Park, Sook Ryun Park, Ki Byung Song, Eunsung Jun, Dongryul Oh, Jeong‐Won Lee, Young Sik Park, Kiwon Song, Jeong‐Sik Byeon, Bo Hyun Kim, Joohyuk Sohn, Min Hwan Kim, Gun Min Kim, Eui Kyu Chie, Hyun‐Cheol Kang, Sun‐Young Kong, Sang Myung Woo, Jeong Eon Lee, Jai Min Ryu, Junnam Lee, Da-Som Kim, Chang‐Seok Ki, Eun‐Hae Cho, Jung Kyoon Choi
Abstract
Multi-cancer early detection remains a key challenge in cell-free DNA (cfDNA)-based liquid biopsy. Here, we perform cfDNA whole-genome sequencing to generate two test datasets covering 2125 patient samples of 9 cancer types and 1241 normal control samples, and also a reference dataset for background variant filtering based on 20,529 low-depth healthy samples. An external cfDNA dataset consisting of 208 cancer and 214 normal control samples is used for additional evaluation. Accuracy for cancer detection and tissue-of-origin localization is achieved using our algorithm, which incorporates cancer type-specific profiles of mutation distribution and chromatin organization in tumor tissues as model references. Our integrative model detects early-stage cancers, including those of pancreatic origin, with high sensitivity that is comparable to that of late-stage detection. Model interpretation reveals the contribution of cancer type-specific genomic and epigenomic features. Our methodologies may lay the groundwork for accurate cfDNA-based cancer diagnosis, especially at early stages.