mitoSomatic: a tool for accurate identification of mitochondrial DNA somatic mutations without paired controls.
mitoSomatic: a tool for accurate identification of mitochondrial DNA somatic mutations without paired controls.
复制标题
mitoSomatic：一种用于准确鉴定线粒体DNA体细胞突变的工具，无需配对对照。
DOI：
10.1002/1878-0261.13335
复制
发表时间：
2023-05
影响因子：
6.6
通讯作者：
Xing, Jinliang
中科院分区：
文献类型：
--
作者：
Guo, Wenjie;Liu, Yang;Su, Liping;Guo, Shanshan;Xie, Fanfan;Ji, Xiaoying;Zhou, Kaixiang;Guo, Xu;Gu, Xiwen;Xing, Jinliang
线粒体 DNA (mtDNA) 体细胞突变在癌症的发生和进展中发挥着重要作用。尽管配对肿瘤和对照样本的下一代测序 (NGS) 已成为识别肿瘤特异性 mtDNA 突变的常见做法，但 mtDNA 的独特性质和 NGS 相关测序偏差可能会导致假阳性/阴性体细胞突变检测。此外，在某些临床情况下，无法获得匹配的对照组织以进行比较。因此，非常需要一种准确识别体细胞 mtDNA 变异的新方法，特别是在缺乏匹配对照的情况下。在这项研究中，通过三对肿瘤、邻近非肿瘤和血液样本正交验证的真实 mtDNA 变异被用于开发 mitoSomatic，一种基于随机森林的机器学习工具。我们证明，mitoSomatic 在三种肿瘤类型中无需配对对照即可识别体细胞 mtDNA 变异，其曲线下面积 (AUC) 值超过 0.99。此外，mitoSomatic还适用于非肿瘤组织，例如邻近非肿瘤和血液样本，这表明mitoSomatic分类能力的灵活性。此外，对三对样本的分析发现了一小群具有不确定体细胞/种系起源的变异，而 mitoSomatic 的应用显着促进了对其可能来源的预测。最后，使用 mitoSomatic 对公共泛癌 NGS 数据集进行的无对照评估揭示了大量可能被传统肿瘤对照比较错误分类的变异，进一步强调了 mitoSomatic 在应用中的有用性。综上所述，我们的研究表明，mitoSomatic 对于在没有配对对照的情况下准确识别 mtDNA NGS 数据中的体细胞 mtDNA 变异非常有价值，适用于肿瘤和非肿瘤组织。线粒体 DNA (mtDNA) 体细胞突变在癌症中发挥着重要作用。由于mtDNA异质性，配对肿瘤和对照样本的传统NGS测序策略存在缺陷，并且不适用于没有匹配正常组织的情况。我们提出了 mitoSomatic，一种基于随机森林的新型机器学习工具，无需配对对照即可准确识别 mtDNA NGS 数据中的 mtDNA 体细胞突变，适用于肿瘤和非肿瘤组织。
Mitochondrial DNA (mtDNA) somatic mutations play important roles in the initiation and progression of cancer. Although next‐generation sequencing (NGS) of paired tumor and control samples has become a common practice to identify tumor‐specific mtDNA mutations, the unique nature of mtDNA and NGS‐associated sequencing bias could cause false‐positive/‐negative somatic mutation calling. Additionally, there are clinical scenarios where matched control tissues are unavailable for comparison. Therefore, a novel approach for accurately identifying somatic mtDNA variants is greatly needed, particularly in the absence of matched controls. In this study, the ground truth mtDNA variants orthogonally validated by triple‐paired tumor, adjacent nontumor, and blood samples were used to develop mitoSomatic, a random forest‐based machine learning tool. We demonstrated that mitoSomatic achieved area under the curve (AUC) values over 0.99 for identifying somatic mtDNA variants without paired control in three tumor types. In addition, mitoSomatic was also applicable in nontumor tissues such as adjacent nontumor and blood samples, suggesting the flexibility of mitoSomatic's classification capability. Furthermore, analysis of triple‐paired samples identified a small group of variants with uncertain somatic/germline origin, whereas application of mitoSomatic significantly facilitated the prediction of their possible source. Finally, a control‐free evaluation of the public pan‐cancer NGS dataset with mitoSomatic revealed a substantial number of variants that were probably misclassified by conventional tumor‐control comparison, further emphasizing the usefulness of mitoSomatic in application. Taken together, our study demonstrates that mitoSomatic is valuable for accurately identifying somatic mtDNA variants in mtDNA NGS data without paired controls, applicable for both tumor and nontumor tissues. Mitochondrial DNA (mtDNA) somatic mutations play important roles in cancer. Due to mtDNA heterogeneity, conventional NGS sequencing strategy of paired tumor and control samples is flawed and inapplicable for scenarios without matched normal tissue. We present mitoSomatic, a novel random forest‐based machine learning tool, to accurately identify mtDNA somatic mutations in mtDNA NGS data without paired controls, applicable for both tumor and nontumor tissues.
登录
查看更多内容
DOI：
10.1038/nrg3275
发表时间：
2012-12
期刊：
Nature reviews. Genetics
影响因子：
--
作者：
通讯作者：
--
Snooper：一种基于机器学习的方法，用于从低通的下一代测序中进行体细胞变体识别。
影响因子：
4.4
作者：
Spinella JF;Mehanna P;Vidal R;Saillour V;Cassart P;Richer C;Ouimet M;Healy J;Sinnett D
通讯作者：
Sinnett D
影响因子：
7.7
作者：
Ju YS;Alexandrov LB;Gerstung M;Martincorena I;Nik-Zainal S;Ramakrishna M;Davies HR;Papaemmanuil E;Gundem G;Shlien A;Bolli N;Behjati S;Tarpey PS;Nangalia J;Massie CE;Butler AP;Teague JW;Vassiliou GS;Green AR;Du MQ;Unnikrishnan A;Pimanda JE;Teh BT;Munshi N;Greaves M;Vyas P;El-Naggar AK;Santarius T;Collins VP;Grundy R;Taylor JA;Hayes DN;Malkin D;ICGC Breast Cancer Group;ICGC Chronic Myeloid Disorders Group;ICGC Prostate Cancer Group;Foster CS;Warren AY;Whitaker HC;Brewer D;Eeles R;Cooper C;Neal D;Visakorpi T;Isaacs WB;Bova GS;Flanagan AM;Futreal PA;Lynch AG;Chinnery PF;McDermott U;Stratton MR;Campbell PJ
通讯作者：
Campbell PJ
DOI：
10.1073/pnas.1419651112
发表时间：
2015-02-24
影响因子：
11.1
作者：
Li, Mingkun;Schroeder, Roland;Stoneking, Mark
通讯作者：
Stoneking, Mark
影响因子：
5.8
作者：
Smith, Kyle S.;Yadav, Vinod K.;De, Subhajyoti
通讯作者：
De, Subhajyoti