Comprehensive tissue deconvolution of cell-free DNA by deep learning for disease diagnosis and monitoring.
Comprehensive tissue deconvolution of cell-free DNA by deep learning for disease diagnosis and monitoring.
复制标题
通过深度学习疾病诊断和监测，无细胞DNA的全面组织反卷积。
DOI：
10.1073/pnas.2305236120
复制
发表时间：
2023-07-11
影响因子：
11.1
通讯作者：
Zhoua, Xianghong Jasmine
中科院分区：
文献类型：
--
作者：
Li, Shuo;Zeng, Weihua;Ni, Xiaohui;Liu, Qiao;Li, Wenyuan;Stackpole, Mary L.;Zhou, Yonggang;Gower, Arjan;Krysan, Kostyantyn;Ahuja, Preeti;Lu, David S.;Raman, Steven S.;Hsu, William;Aberle, Denise R.;Magyar, Clara E.;French, Samuel W.;Han, Steven -Huy B.;Garon, Edward B.;Agopian, Vatche G.;Wong, Wing Hung;Dubinett, Steven M.;Zhoua, Xianghong Jasmine
血浆游离DNA（cfDNA）是所有器官细胞死亡的非侵入性生物标志物。破译cfDNA的组织起源可以揭示疾病导致的细胞异常死亡，在疾病检测和监测方面具有巨大的临床潜力。为了充分利用这一潜力，我们提出了一个最大的综合性和高质量的组织甲基化图谱，从521个非癌组织样本跨越29个主要的人体组织构建。基于这些丰富的数据，我们开发了第一个深度学习驱动的模型cfSort，用于组织去卷积。我们证明，cfSort具有上级的灵敏度和准确性相比，现有的方法。我们在肝硬化和癌症患者中验证了cfSort。我们的图谱和cfSort将在疾病检测和监测方面具有广泛的研究和临床应用。血浆游离DNA（cfDNA）是所有器官细胞死亡的非侵入性生物标志物。破译cfDNA的组织起源可以揭示疾病导致的细胞异常死亡，在疾病检测和监测方面具有巨大的临床潜力。尽管前景广阔，但由于组织甲基化的有限表征和对无监督方法的依赖，组织来源的cfDNA的灵敏和准确定量对现有方法仍然具有挑战性。为了充分利用组织来源的cfDNA的临床潜力，在这里，我们提出了一个最大的综合性和高分辨率的甲基化图谱，该图谱基于521个非癌组织样本，涵盖29种主要类型的人类组织。我们系统地鉴定了片段水平的组织特异性甲基化模式，并在正交数据集中对其进行了广泛的验证。基于丰富的组织甲基化图谱，我们开发了第一种有监督的组织去卷积方法，一种深度学习动力模型cfSort，用于cfDNA中灵敏和准确的组织去卷积。在基准数据上，cfSort显示出比现有方法上级的灵敏度和准确性。我们进一步证明了cfSort的临床实用性和两个潜在的应用：辅助疾病诊断和监测治疗副作用。从cfSort估计的组织来源的cfDNA分数反映了患者的临床结果。总之，组织甲基化图谱和cfSort增强了cfDNA中组织去卷积的性能，从而促进了基于cfDNA的疾病检测和纵向治疗监测。
Plasma cell-free DNA (cfDNA) is a noninvasive biomarker for cell death of all organs. Deciphering the tissue origin of cfDNA can reveal abnormal cell death because of diseases, which has great clinical potential in disease detection and monitoring. To fully exploit this potential, we present one of the largest comprehensive and high-quality tissue methylation atlases, constructed from 521 noncancer tissue samples spanning 29 major human tissues. Based on this rich data, we develop the first deep-learning-powered model, cfSort, for tissue deconvolution. We demonstrated that cfSort has superior sensitivity and accuracy compared to existing methods. We validated cfSort in patients with cirrhosis and cancer. Our atlas and cfSort shall have broad research and clinical applications in disease detection and monitoring. Plasma cell-free DNA (cfDNA) is a noninvasive biomarker for cell death of all organs. Deciphering the tissue origin of cfDNA can reveal abnormal cell death because of diseases, which has great clinical potential in disease detection and monitoring. Despite the great promise, the sensitive and accurate quantification of tissue-derived cfDNA remains challenging to existing methods due to the limited characterization of tissue methylation and the reliance on unsupervised methods. To fully exploit the clinical potential of tissue-derived cfDNA, here we present one of the largest comprehensive and high-resolution methylation atlas based on 521 noncancer tissue samples spanning 29 major types of human tissues. We systematically identified fragment-level tissue-specific methylation patterns and extensively validated them in orthogonal datasets. Based on the rich tissue methylation atlas, we develop the first supervised tissue deconvolution approach, a deep-learning-powered model, cfSort, for sensitive and accurate tissue deconvolution in cfDNA. On the benchmarking data, cfSort showed superior sensitivity and accuracy compared to the existing methods. We further demonstrated the clinical utilities of cfSort with two potential applications: aiding disease diagnosis and monitoring treatment side effects. The tissue-derived cfDNA fraction estimated from cfSort reflected the clinical outcomes of the patients. In summary, the tissue methylation atlas and cfSort enhanced the performance of tissue deconvolution in cfDNA, thus facilitating cfDNA-based disease detection and longitudinal treatment monitoring.
登录
查看更多内容
影响因子：
14.8
作者：
Li, Shuo;Hu, Ran;Small, Colin;Kang, Ting-Yu;Liu, Chun-Chi;Zhou, Xianghong Jasmine;Li, Wenyuan
通讯作者：
Li, Wenyuan
DOI：
10.1016/j.annonc.2020.02.011
发表时间：
2020-06
期刊：
Annals of oncology : official journal of the European Society for Medical Oncology
影响因子：
--
作者：
Liu MC;Oxnard GR;Klein EA;Swanton C;Seiden MV;CCGA Consortium
通讯作者：
CCGA Consortium
影响因子：
64.8
作者：
Loyfer, Netanel;Magenheim, Judith;Peretz, Ayelet;Cann, Gordon;Bredno, Joerg;Klochendler, Agnes;Fox-Fisher, Ilana;Shabi-Porat, Sapir;Hecht, Merav;Pelet, Tsuria;Moss, Joshua;Drawshy, Zeina;Amini, Hamed;Moradi, Patriss;Nagaraju, Sudharani;Bauman, Dvora;Shveiky, David;Porat, Shay;Dior, Uri;Rivkin, Gurion;Or, Omer;Hirshoren, Nir;Carmon, Einat;Pikarsky, Alon;Khalaileh, Abed;Zamir, Gideon;Grinbaum, Ronit;Abu Gazala, Machmud;Mizrahi, Ido;Shussman, Noam;Korach, Amit;Wald, Ori;Izhar, Uzi;Erez, Eldad;Yutkin, Vladimir;Samet, Yaacov;Rotnemer Golinkin, Devorah;Spalding, Kirsty L.;Druid, Henrik;Arner, Peter;Shapiro, A. M. James;Grompe, Markus;Aravanis, Alex;Venn, Oliver;Jamshidi, Arash;Shemer, Ruth;Dor, Yuval;Glaser, Benjamin;Kaplan, Tommy
通讯作者：
Kaplan, Tommy
影响因子：
12.3
作者：
Lokk K;Modhukur V;Rajashekar B;Märtens K;Mägi R;Kolde R;Koltšina M;Nilsson TK;Vilo J;Salumets A;Tõnisson N
通讯作者：
Tõnisson N
影响因子：
14.9
作者：
Li W;Li Q;Kang S;Same M;Zhou Y;Sun C;Liu CC;Matsuoka L;Sher L;Wong WH;Alber F;Zhou XJ
通讯作者：
Zhou XJ