Multiplex methylation detection assays using a blocking FRET probe with machine learning-assisted quantitative melting curve method targeting early-stage breast cancer

• Published in: Chemical engineering journal (Lausanne, Switzerland : 1996) Switzerland : 1996), 2024-10, Vol.498, p.155093, Article 155093
• Main Authors: Tao, Mingli, Yang, Qi, Huan, Changxiang, Zhang, Zhiqi, Li, Peilong, Huang, Runhu, Li, Juan, Zhang, Yueye, Li, Chao, Li, Chuanyu, Yao, Jia, Li, Shuli, Guo, Zhen, Zhang, Wei, Li, Jinze, Zhou, Lianqun
• Format: Article
• Language: English
• Subjects: Breast cancer; FRET probe; Machine learning; Melting curve analysis; Methylation quantitative detection; Multiplex qPCR
• ISSN: 1385-8947
• DOI: 10.1016/j.cej.2024.155093

•An assay called BFML-qMC was developed for multiplex methylation detection.•The BFML-qMC assay combines blocking FRET probes with machine learning.•The assay blocks unmethylated amplification and produces melting curves with probes.•Validation with 80 clinical samples showed 83.33% sensitivity and 84.62% specificity. Breast cancer (BC) is the second most prevalent form of cancer, and poses a significant threat to public health. DNA methylation is an ideal marker for the early detection of BC. Fluorescence quantitative polymerase chain reaction (PCR)-based DNA methylation detection is simpler and faster but is constrained by its multiplexing capability and specificity. To address this, we developed a multiplex quantitative methylation PCR assay for the simultaneous analysis of methylation status at multiple sites specific to BC (cg11754974, cg13828440, cg18637238, and cg16652347). The machine learning model was trained using 1200 cases of multipeak data to enhance the melting curve resolution. Performance testing demonstrated the method’s ability to selectively amplify methylated genes at a DNA concentration of 1 × 105 copies μL−1, with high replicability (coefficient of variation