SNooPer: a machine learning-based method for somatic variant identification from low-pass next-generation sequencing.
SNooPer: a machine learning-based method for somatic variant identification from low-pass next-generation sequencing.
复制标题
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。
DOI：
10.1186/s12864-016-3281-2
复制
发表时间：
2016-11-14
期刊：
影响因子：
4.4
通讯作者：
Sinnett D
中科院分区：
文献类型：
--
作者：
Spinella JF;Mehanna P;Vidal R;Saillour V;Cassart P;Richer C;Ouimet M;Healy J;Sinnett D
下一代测序(NGS)允许对癌症基因组进行无偏见的、深入的询问。许多体细胞变异体已经被培育出来，但体细胞变异体的准确确定仍然是一个相当大的挑战，从体细胞变异体之间不同的突变呼叫率和低的一致性就可以看出这一点。目前可用的基于统计模型的算法在理想情况下表现良好，例如高测序深度、均匀的肿瘤样本、高体细胞变异等位基因频率(VAF)，但对于次优数据，如低通全外显子组/基因组测序数据，表现出有限的性能。虽然任何癌症测序项目的目标都是确定一组相关的、有限的体细胞变体，以便进一步进行序列/功能验证，但癌症基因组固有的复杂性加上与测序和比对直接相关的技术问题，可能会影响大多数呼叫者的特异性和/或敏感度。出于这些原因，我们开发了Snoper，一种通用的机器学习方法，使用随机森林分类模型来准确调用低深度测序数据中的体细胞变体。窥探者使用来自测序输出的变量位置的子集，对于该变量位置的子集，已知类别、真实变化或测序错误，以训练数据特定模型。在这里，使用40名儿童急性淋巴细胞白血病患者的真实数据集，我们展示了窥探算法如何不受低覆盖率或低VAFs的影响，并可用于降低总体测序成本，同时保持对体细胞变体调用的高特异性和敏感性。当与三个以身体为基准的呼叫者相比，窥探者表现出最好的整体表现。虽然任何癌症测序项目的目标都是确定一组相关的、有限的体细胞变体，以便进一步进行序列/功能验证，但癌症基因组固有的复杂性加上与测序和比对直接相关的技术问题，可能会影响大多数呼叫者的特异性和/或敏感度。窥探者的随机森林的灵活性防止了技术偏差和系统错误，并且由于它不依赖于用户定义的参数而具有吸引力。代码和用户指南可从https://sourceforge.net/projects/snooper/.下载本文的在线版本(doi：10.1186/s12864-0163281-2)包含补充材料，授权用户可以使用。
Next-generation sequencing (NGS) allows unbiased, in-depth interrogation of cancer genomes. Many somatic variant callers have been developed yet accurate ascertainment of somatic variants remains a considerable challenge as evidenced by the varying mutation call rates and low concordance among callers. Statistical model-based algorithms that are currently available perform well under ideal scenarios, such as high sequencing depth, homogeneous tumor samples, high somatic variant allele frequency (VAF), but show limited performance with sub-optimal data such as low-pass whole-exome/genome sequencing data. While the goal of any cancer sequencing project is to identify a relevant, and limited, set of somatic variants for further sequence/functional validation, the inherently complex nature of cancer genomes combined with technical issues directly related to sequencing and alignment can affect either the specificity and/or sensitivity of most callers. For these reasons, we developed SNooPer, a versatile machine learning approach that uses Random Forest classification models to accurately call somatic variants in low-depth sequencing data. SNooPer uses a subset of variant positions from the sequencing output for which the class, true variation or sequencing error, is known to train the data-specific model. Here, using a real dataset of 40 childhood acute lymphoblastic leukemia patients, we show how the SNooPer algorithm is not affected by low coverage or low VAFs, and can be used to reduce overall sequencing costs while maintaining high specificity and sensitivity to somatic variant calling. When compared to three benchmarked somatic callers, SNooPer demonstrated the best overall performance. While the goal of any cancer sequencing project is to identify a relevant, and limited, set of somatic variants for further sequence/functional validation, the inherently complex nature of cancer genomes combined with technical issues directly related to sequencing and alignment can affect either the specificity and/or sensitivity of most callers. The flexibility of SNooPer’s random forest protects against technical bias and systematic errors, and is appealing in that it does not rely on user-defined parameters. The code and user guide can be downloaded at https://sourceforge.net/projects/snooper/. The online version of this article (doi:10.1186/s12864-016-3281-2) contains supplementary material, which is available to authorized users.
登录
查看更多内容
影响因子：
64.8
作者：
Ellis, Matthew J.;Ding, Li;Shen, Dong;Luo, Jingqin;Suman, Vera J.;Wallis, John W.;Van Tine, Brian A.;Hoog, Jeremy;Goiffon, Reece J.;Goldstein, Theodore C.;Ng, Sam;Lin, Li;Crowder, Robert;Snider, Jacqueline;Ballman, Karla;Weber, Jason;Chen, Ken;Koboldt, Daniel C.;Kandoth, Cyriac;Schierding, William S.;McMichael, Joshua F.;Miller, Christopher A.;Lu, Charles;Harris, Christopher C.;McLellan, Michael D.;Wendl, Michael C.;DeSchryver, Katherine;Allred, D. Craig;Esserman, Laura;Unzeitig, Gary;Margenthaler, Julie;Babiera, G. V.;Marcom, P. Kelly;Guenther, J. M.;Leitch, Marilyn;Hunt, Kelly;Olson, John;Tao, Yu;Maher, Christopher A.;Fulton, Lucinda L.;Fulton, Robert S.;Harrison, Michelle;Oberkfell, Ben;Du, Feiyu;Demeter, Ryan;Vickery, Tammi L.;Elhammali, Adnan;Piwnica-Worms, Helen;McDonald, Sandra;Watson, Mark;Dooling, David J.;Ota, David;Chang, Li-Wei;Bose, Ron;Ley, Timothy J.;Piwnica-Worms, David;Stuart, Joshua M.;Wilson, Richard K.;Mardis, Elaine R.
通讯作者：
Mardis, Elaine R.
来自1,092个人基因组的遗传变异的综合图。
影响因子：
64.8
作者：
通讯作者：
--
影响因子：
30.8
作者：
Holmfeldt, Linda;Wei, Lei;Diaz-Flores, Ernesto;Walsh, Michael;Zhang, Jinghui;Ding, Li;Payne-Turner, Debbie;Churchman, Michelle;Andersson, Anna;Chen, Shann-Ching;McCastlain, Kelly;Becksfort, Jared;Ma, Jing;Wu, Gang;Patel, Samir N.;Heatley, Susan L.;Phillips, Letha A.;Song, Guangchun;Easton, John;Parker, Matthew;Chen, Xiang;Rusch, Michael;Boggs, Kristy;Vadodaria, Bhavin;Hedlund, Erin;Drenberg, Christina;Baker, Sharyn;Pei, Deqing;Cheng, Cheng;Huether, Robert;Lu, Charles;Fulton, Robert S.;Fulton, Lucinda L.;Tabib, Yashodhan;Dooling, David J.;Ochoa, Kerri;Minden, Mark;Lewis, Ian D.;To, L. Bik;Marlton, Paula;Roberts, Andrew W.;Raca, Gordana;Stock, Wendy;Neale, Geoffrey;Drexler, Hans G.;Dickins, Ross A.;Ellison, David W.;Shurtleff, Sheila A.;Pui, Ching-Hon;Ribeiro, Raul C.;Devidas, Meenakshi;Carroll, Andrew J.;Heerema, Nyla A.;Wood, Brent;Borowitz, Michael J.;Gastier-Foster, Julie M.;Raimondi, Susana C.;Mardis, Elaine R.;Wilson, Richard K.;Downing, James R.;Hunger, Stephen P.;Loh, Mignon L.;Mullighan, Charles G.
通讯作者：
Mullighan, Charles G.
影响因子：
30.8
作者：
Krauthammer M;Kong Y;Bacchiocchi A;Evans P;Pornputtapong N;Wu C;McCusker JP;Ma S;Cheng E;Straub R;Serin M;Bosenberg M;Ariyan S;Narayan D;Sznol M;Kluger HM;Mane S;Schlessinger J;Lifton RP;Halaban R
通讯作者：
Halaban R
影响因子：
30.8
作者：
Al-Ahmadie HA;Iyer G;Lee BH;Scott SN;Mehra R;Bagrodia A;Jordan EJ;Gao SP;Ramirez R;Cha EK;Desai NB;Zabor EC;Ostrovnaya I;Gopalan A;Chen YB;Fine SW;Tickoo SK;Gandhi A;Hreiki J;Viale A;Arcila ME;Dalbagni G;Rosenberg JE;Bochner BH;Bajorin DF;Berger MF;Reuter VE;Taylor BS;Solit DB
通讯作者：
Solit DB