Predictive modelling of brain metastasis risk and non-invasive biomarker detection using DNA methylation signatures

Methylated cell-free DNA was sequenced for 123 BM plasma and compared to plasma methylomes from 107 gliomas, central nervous system (CNS) lymphomas (CNSL), and non-CNS tumor controls. Plasma methylome-based classifiers of BM from other entities were built in fifty 80% discovery set iterations of 92/123 BM samples. External publicly-available tissue methylation data on 442 LUAD, 85 BM, and 146 glioma/CNSL/control samples were acquired for validation and the remaining 31/123 BM plasma samples were used for additional validation.针对123份脑转移瘤（Brain Metastasis, BM）血浆样本的甲基化无细胞DNA（methylated cell-free DNA）进行测序，并将其与107例胶质瘤、中枢神经系统（Central Nervous System, CNS）淋巴瘤（CNSL）及非中枢神经系统肿瘤对照的血浆甲基化组开展比对。基于血浆甲基化组的脑转移瘤分类器，通过以92/123份脑转移瘤样本构成的80%发现集进行50次迭代训练构建得到。获取了公开可用的外部组织甲基化数据集用于验证，该数据集包含442例肺腺癌（LUAD）、85例脑转移瘤及146例胶质瘤/中枢神经系统淋巴瘤/对照样本；剩余31/123份脑转移瘤血浆样本则用于额外验证。