Deep learning model integrating cfDNA methylation and fragment size profiles for lung cancer diagnosis

• Published in: Scientific reports 2024-06, Vol.14 (1), p.14797-12, Article 14797
• Main Authors: Kim, Minjung, Park, Juntae, Seonghee Oh, Jeong, Byeong-Ho, Byun, Yuree, Shin, Sun Hye, Im, Yunjoo, Cho, Jong Ho, Cho, Eun-Hae
• Format: Article
• Language: English
• Subjects: 631/1647/2210/2213; 631/1647/514/2254; 631/208/176/1988; 631/67/1612; 631/67/2322; Aged; Biomarkers, Tumor - blood; Biomarkers, Tumor - genetics; Cell size; Cell-Free Nucleic Acids - blood; Cell-Free Nucleic Acids - genetics; ctDNA; Deep Learning; Deoxyribonucleic acid; Diagnosis; DNA; DNA Methylation; DNA sequencing; EM-seq; Female; Gene expression; Genomes; Humanities and Social Sciences; Humans; Immunoprecipitation; Lung cancer; Lung Neoplasms - blood; Lung Neoplasms - diagnosis; Lung Neoplasms - genetics; Male; Medical diagnosis; MeDIP-seq; Methylation; Middle Aged; multidisciplinary; ROC Curve; Science; Science (multidisciplinary); Sensitivity analysis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-63411-2

Detecting aberrant cell-free DNA (cfDNA) methylation is a promising strategy for lung cancer diagnosis. In this study, our aim is to identify methylation markers to distinguish patients with lung cancer from healthy individuals. Additionally, we sought to develop a deep learning model incorporating cfDNA methylation and fragment size profiles. To achieve this, we utilized methylation data collected from The Cancer Genome Atlas and Gene Expression Omnibus databases. Then we generated methylated DNA immunoprecipitation sequencing and genome-wide Enzymatic Methyl-seq (EM-seq) form lung cancer tissue and plasma. Using these data, we selected 366 methylation markers. A targeted EM-seq panel was designed using the selected markers, and 142 lung cancer and 56 healthy samples were produced with the panel. Additionally, cfDNA samples from healthy individuals and lung cancer patients were diluted to evaluate sensitivity. Its lung cancer detection performance reached an accuracy of 81.5% and an area under the receiver operating characteristic curve of 0.87. In the serial dilution experiment, we achieved tumor fraction detection of 1% at 98% specificity and 0.1% at 80% specificity. In conclusion, we successfully developed and validated a combination of methylation panel and a deep learning model that can distinguish between patients with lung cancer and healthy individuals.