基于机器学习的循环肿瘤DNA中体拷贝数畸变的全基因组查询

StephenW

Machine Learning-Based Genome-Wide Interrogation of Somatic Copy Number Aberrations in Circulating Tumor DNA for Early Detection of Hepatocellular Carcinoma
Kaishan Tao  1 , Zhenyuan Bian  2 , Qiong Zhang  3 , Xu Guo  4 , Chun Yin  4 , Yang Wang  1 , Kaixiang Zhou  4 , Shaogui Wan  5 , Meifang Shi  6 , Dengke Bao  7 , Chuhu Yang  8 , Jinliang Xing  9
Affiliations
Affiliations

    1
    Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi 710032, China.
    2
    Department of Hepatobiliary Surgery, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi 710032, China; Department of General Surgery, General Hospital of Shenyang Military Area Command, Shenyang, Liaoning 110016, China.
    3
    Research and Development Division, Oriomics Biotech, Hangzhou, Zhejiang 310018, China.
    4
    State Key Laboratory of Cancer Biology and Department of Physiology and Pathophysiology, Fourth Military Medical University, Xi'an, Shaanxi 710032, China.
    5
    Center for Molecular Pathology, First Affiliated Hospital, Gannan Medical University, Ganzhou, Jiangxi 341000, China.
    6
    Department of Liver Surgery and Transplantation, Liver Cancer Institute, Zhongshan Hospital of Fudan University, Shanghai 200032, China; Key Laboratory of Carcinogenesis and Cancer Invasion, Ministry of Education, Shanghai 200032, China.
    7
    Laboratory of Cancer Biomarkers and Liquid Biopsy, School of Pharmacy, Henan University, Kaifeng 475001, China.
    8
    Research and Development Division, Oriomics Biotech, Hangzhou, Zhejiang 310018, China. Electronic address: [email protected].
    9
    State Key Laboratory of Cancer Biology and Department of Physiology and Pathophysiology, Fourth Military Medical University, Xi'an, Shaanxi 710032, China. Electronic address: [email protected].

    PMID: 32512514 DOI: 10.1016/j.ebiom.2020.102811

Abstract

Background: DNAs released from tumor cells into blood (circulating tumor DNAs, ctDNAs) carry tumor-specific genomic aberrations, providing a non-invasive means for cancer detection. In this study, we aimed to leverage somatic copy number aberration (SCNA) in ctDNA to develop assays to detect early-stage HCCs.

Methods: We conducted low-depth whole-genome sequencing (WGS) to profile SCNAs in 384 plasma samples of hepatitis B virus (HBV)-related HCC and cancer-free HBV patients, using one discovery and two validation cohorts. To fully capture the robust signals of WGS data from the complete genome, we developed a machine learning-based statistical model that is focused on detection accuracy in early-stage HCC.

Findings: We built the model using a discovery cohort of 209 patients, achieving an overall area under curve (AUC) of 0.893, with 0.874 for early-stage (Barcelona clinical liver cancer [BCLC] stage 0-A) and 0.933 for advanced-stage (BCLC stage B-D). The performance of the model was then assessed in two validation cohorts (76 and 99 patients) that only consisted of patients with stage 0-A HCC. Our model exhibited a robust predictive performance, with an AUC of 0.920 and 0.812 for the two validation cohorts. Further analyses showed the impact of tumor sample heterogeneity in model training on detecting early-stage tumors, and a refined model addressing the heterogeneity in the discovery cohort significantly increased model performance in validation.

Interpretation: We developed an SCNA-based, machine learning-driven model in the non-invasive detection of early-stage HCC in HBV patients and demonstrated its performance through strict independent validations.

Keywords: Copy number aberration (CNA); Early detection; Hepatocellular carcinoma (HCC); Machine learning.

Copyright © 2020 The Authors. Published by Elsevier B.V. All rights reserved.

StephenW

基于机器学习的循环肿瘤DNA中体拷贝数畸变的全基因组查询，以早期检测肝细胞癌。
开山陶1，振远变2，琼章3，徐国4，春音4，杨旺1，周开祥4，少归湾5，梅芳石6，登科宝7，楚湖杨8，金良兴9
隶属关系
隶属关系

    1个
    第四军医大学西京医院肝胆外科，陕西西安710032
    2
    第四军医大学西京医院肝胆外科，陕西西安710032；沉阳军区总医院普外科，辽宁沉阳110016
    3
    Oriomics Biotech研究与开发部，浙江杭州310018
    4
    第四军医大学肿瘤生物学国家重点实验室，生理与病理生理学教研室，陕西西安710032
    5
    赣南医科大学附属第一医院分子病理学中心，江西赣州341000
    6
    复旦大学附属中山医院肝癌研究所肝外科移植科，上海200032；癌变与癌浸润教育部重点实验室，上海200032
    7
    河南大学药学院癌症生物标志物和液体活检实验室，开封475001。
    8
    Oriomics Biotech研究与开发部，浙江杭州310018电子地址：[email protected]。
    9
    第四军医大学肿瘤生物学国家重点实验室，生理与病理生理学教研室，陕西西安710032电子地址：[email protected]。

    PMID：32512514 DOI：10.1016 / j.ebiom.2020.102811

抽象

背景：从肿瘤细胞释放到血液中的DNA（循环肿瘤DNA，ctDNA）带有肿瘤特异性基因组畸变，为癌症检测提供了一种非侵入性手段。在这项研究中，我们旨在利用ctDNA中的体细胞拷贝数畸变（SCNA）来开发检测早期HCC的检测方法。

方法：我们进行了一次低深度全基因组测序（WGS），使用一个发现和两个验证队列对384例乙型肝炎病毒（HBV）相关的HCC和无癌HBV患者的血浆样本中的SCNA进行了分析。为了从整个基因组中完全捕获WGS数据的可靠信号，我们开发了一种基于机器学习的统计模型，该模型专注于早期HCC的检测准确性。

研究结果：我们使用209名患者的发现队列建立了模型，其曲线下总面积（AUC）为0.893，其中早期阶段（巴塞罗那临床肝癌[BCLC] 0-A期）为0.874，晚期阶段为0.933。阶段（BCLC阶段BD）。然后在两个仅由0-A期HCC患者组成的验证队列（76和99位患者）中评估了模型的性能。我们的模型表现出强大的预测性能，两个验证队列的AUC为0.920和0.812。进一步的分析表明，模型训练中肿瘤样本异质性对检测早期肿瘤的影响，而解决发现队列中异质性的改进模型显着提高了验证模型的性能。

解释：我们开发了一种基于SCNA的，机器学习驱动的模型，用于无创检测HBV患者的早期HCC，并通过严格的独立验证证明了其性能。

关键字：副本号码像差（CNA）；早期发现;肝细胞癌（HCC）；机器学习。

版权所有©2020作者。由Elsevier B.V.发布。保留所有权利。

StephenW

https://www.thelancet.com/pdfs/j ... 3964(20)30186-9.pdf