Multimodal Analysis of ctDNA Methylation and Fragmentomic Profiles Enhances Detection of Nonmetastatic Colorectal Cancer

<b>Aims:</b> Early detection of colorectal cancer (CRC) provides substantially better survival rates. This study aimed to develop a blood-based screening assay named SPOT-MAS (‘screen for the presence of tumor by DNA methylation and size’) for early CRC detection with high accuracy. <b>Methods:</b> Plasma cell-free DNA samples from 159 patients with nonmetastatic CRC and 158 healthy controls were simultaneously analyzed for fragment length and methylation profiles. We then employed a deep neural network with fragment length and methylation signatures to build a classification model. <b>Results:</b> The model achieved an area under the curve of 0.989 and a sensitivity of 96.8% at 97% specificity in detecting CRC. External validation of our model showed comparable performance, with an area under the curve of 0.96. <b>Conclusion:</b> SPOT-MAS based on integration of cancer-specific methylation and fragmentomic signatures could provide high accuracy for early-stage CRC detection. A novel blood test for early detection of colorectal cancer. Colorectal cancer is a cancer of the colon or rectum, located at the lower end of the digestive tract. The early detection of colorectal cancer can help people with the disease have a higher chance of survival and a better quality of life. Current screening methods can be invasive, cause discomfort or have low accuracy; therefore newer screening methods are needed. In this study we developed a new screening method, called SPOT-MAS, which works by measuring the signals of cancer DNA in the blood. By combining different characteristics of cancer DNA, SPOT-MAS could distinguish blood samples of people with colorectal cancer from those of healthy individuals with high accuracy. SPOT-MAS technology combines methylation and fragmentomic signatures of blood-based circulating tumor DNA in a multimodal deep-learning analysis to enable early detection of colorectal cancer with high accuracy.

**研究目的：** 结直肠癌（colorectal cancer, CRC）的早期筛查可显著提升患者生存率。本研究旨在开发一款名为SPOT-MAS（即通过DNA甲基化与片段大小筛查肿瘤存在的检测方法）的血液筛查检测技术，以实现高精度的早期结直肠癌检测。
**研究方法：** 本研究同步分析了159例非转移性结直肠癌患者与158名健康对照者的血浆游离DNA（plasma cell-free DNA）样本的片段长度与甲基化谱特征；随后基于片段长度与甲基化特征构建深度神经网络分类模型。
**研究结果：** 该模型在检测结直肠癌时的曲线下面积（area under the curve, AUC）达0.989，在特异性为97%的前提下灵敏度达96.8%；模型的外部验证结果表现相当，曲线下面积为0.96。
**研究结论：** 基于癌症特异性甲基化与片段组学特征整合的SPOT-MAS技术，可实现高精度的早期结直肠癌筛查。

本研究开发了一款用于结直肠癌早期筛查的新型血液检测技术。结直肠癌是发生于消化道末端结肠或直肠的恶性肿瘤，早期筛查可提升患者的生存概率与生活质量。现有筛查手段多存在侵入性、易引发不适或灵敏度不足等缺陷，因此亟需开发新型筛查技术。本研究开发的SPOT-MAS检测技术，通过检测血液中肿瘤DNA的相关信号实现筛查；通过整合肿瘤DNA的多项特征，SPOT-MAS可高精度区分结直肠癌患者与健康个体的血液样本。SPOT-MAS技术通过多模态深度学习分析整合血液循环肿瘤DNA的甲基化与片段组学特征，实现高精度的结直肠癌早期筛查。