基于无末端修复酶促甲基化测序的循环游离 DNA 和预训练神经网络早期检测肝细胞癌

BACKGROUND: Early detection of hepatocellular carcinoma (HCC) is important in order to improve patient prognosis and survival rate. Methylation sequencing combined with neural networks to identify cell-free DNA (cfDNA) carrying aberrant methylation offers an appealing and non-invasive approach for HCC detection. However, some limitations exist in traditional methylation detection technologies and models, which may impede their performance in the read-level detection of HCC. METHODS: We developed a low DNA damage and high-fidelity methylation detection method called No End-repair Enzymatic Methyl-seq (NEEM-seq). We further developed a read-level neural detection model called DeepTrace that can better identify HCC-derived sequencing reads through a pre-trained and fine-tuned neural network. After pre-training on 11 million reads from NEEM-seq, DeepTrace was fine-tuned using 1.2 million HCC-derived reads from tumor tissue DNA after noise reduction, and 2.7 million non-tumor reads from non-tumor cfDNA. We validated the model using data from 130 individuals with cfDNA whole-genome NEEM-seq at around 1.6X depth. RESULTS: NEEM-seq overcomes the drawbacks of traditional enzymatic methylation sequencing methods by avoiding the introduction of unmethylation errors in cfDNA. DeepTrace outperformed other models in identifying HCC-derived reads and detecting HCC individuals. Based on the whole-genome NEEM-seq data of cfDNA, our model showed high accuracy of 96.2%, sensitivity of 93.6%, and specificity of 98.5% in the validation cohort consisting of 62 HCC patients, 48 liver disease patients, and 20 healthy individuals. In the early stage of HCC (BCLC 0/A and TNM I), the sensitivity of DeepTrace was 89.6 and 89.5% respectively, outperforming Alpha Fetoprotein (AFP) which showed much lower sensitivity in both BCLC 0/A (50.5%) and TNM I (44.7%). CONCLUSIONS: By combining high-fidelity methylation data from NEEM-seq with the DeepTrace model, our method has great potential for HCC early detection with high sensitivity and specificity, making it potentially suitable for clinical applications. DeepTrace: https://github.com/Bamrock/DeepTrace.

背景：早期发现肝细胞癌（HCC）对于改善患者预后和生存率至关重要。利用甲基化测序结合神经网络来识别携带异常甲基化的游离 DNA（cfDNA），为 HCC 检测提供了一种有吸引力且非侵入性的方法。然而，传统甲基化检测技术和模型存在一些局限性，可能会影响其在 HCC 读级检测中的性能。

方法：我们开发了一种称为无末端修复酶甲基化测序（NEEM-seq）的低 DNA 损伤和高保真度甲基化检测方法。我们进一步开发了一种称为 DeepTrace 的读级神经检测模型，该模型可以通过预先训练和微调神经网络更好地识别来自 HCC 的测序reads。在使用来自 NEEM-seq 的 1100 万reads 进行预训练后，DeepTrace 使用经过降噪处理的来自肿瘤组织 DNA 的 120 万 HCC 衍生reads 和来自非肿瘤 cfDNA 的 270 万非肿瘤reads 进行了微调。我们使用来自 130 名个体的 cfDNA 全基因组 NEEM-seq 数据（深度约为 1.6X）验证了该模型。

结果：NEEM-seq 通过避免在 cfDNA 中引入非甲基化错误，克服了传统酶甲基化测序方法的缺点。DeepTrace 在识别 HCC 衍生 reads 和检测 HCC 个体方面优于其他模型。基于 cfDNA 的全基因组 NEEM-seq 数据，我们的模型在由 62 名 HCC 患者、48 名肝病患者和 20 名健康个体组成的验证队列中表现出 96.2%的高准确率、93.6%的灵敏度和 98.5%的特异性。在 HCC 的早期阶段（BCLC 0/A 和 TNM I），DeepTrace 的灵敏度分别为 89.6%和 89.5%，高于 AFP（在 BCLC 0/A 中灵敏度分别为 50.5%和 TNM I 中灵敏度分别为 44.7%）。

结论：通过将来自 NEEM-seq 的高保真度甲基化数据与 DeepTrace 模型相结合，我们的方法在高灵敏度和特异性方面具有很大的潜力，可用于 HCC 的早期检测，可能适用于临床应用。DeepTrace：https://github.com/Bamrock/DeepTrace。