Genome-wide enhancer prediction from epigenetic signatures using genetic algorithm-optimized support vector machines.
Genome-wide enhancer prediction from epigenetic signatures using genetic algorithm-optimized support vector machines.
复制标题
DOI：
10.1093/nar/gks149
复制
发表时间：
2012-05
影响因子：
14.9
通讯作者：
Miranda-Saavedra D
中科院分区：
文献类型：
--
作者：
Fernández M;Miranda-Saavedra D
组蛋白在特定DNA调控元件处的化学修饰与基因的激活、失活和平衡有关。存在许多工具来从染色质修饰图谱预测增强子，但它们的实际应用是有限的，因为它们（i）考虑比定义各种增强子类别所需的标记数量更少的标记，或（ii）使用过多数量的标记，这在实验上是不可行的。我们已经开发了一种方法，染色质状态检测支持向量机结合遗传算法优化，称为ChromaGenSVM。ChromaGenSVM选择特定组蛋白表观遗传标记的最佳组合来预测增强子。在一项独立的测试中，ChromaGenSVM在干扰素γ处理的HeLa细胞的先导ENCODE区域中回收了88%的实验支持的增强子。此外，ChromaGenSVM成功地结合了在人类CD 4 + T细胞中完成的ChIP-seq文库中仅5个不同甲基化和乙酰化标记的特征，预测了1.0 kb区域内的21000个实验支持的增强子，精确度为90%，从而将先前对同一数据集的预测提高了21%。综合结果表明，ChromaGenSVM舒适地优于以前发表的方法，增强子最好通过组蛋白甲基化和乙酰化标记的特定组合来预测。
The chemical modification of histones at specific DNA regulatory elements is linked to the activation, inactivation and poising of genes. A number of tools exist to predict enhancers from chromatin modification maps, but their practical application is limited because they either (i) consider a smaller number of marks than those necessary to define the various enhancer classes or (ii) work with an excessive number of marks, which is experimentally unviable. We have developed a method for chromatin state detection using support vector machines in combination with genetic algorithm optimization, called ChromaGenSVM. ChromaGenSVM selects optimum combinations of specific histone epigenetic marks to predict enhancers. In an independent test, ChromaGenSVM recovered 88% of the experimentally supported enhancers in the pilot ENCODE region of interferon gamma-treated HeLa cells. Furthermore, ChromaGenSVM successfully combined the profiles of only five distinct methylation and acetylation marks from ChIP-seq libraries done in human CD4+ T cells to predict ∼21 000 experimentally supported enhancers within 1.0 kb regions and with a precision of ∼90%, thereby improving previous predictions on the same dataset by 21%. The combined results indicate that ChromaGenSVM comfortably outperforms previously published methods and that enhancers are best predicted by specific combinations of histone methylation and acetylation marks.
登录
查看更多内容
影响因子：
64.8
作者：
Heintzman, Nathaniel D.;Hon, Gary C.;Hawkins, R. David;Kheradpour, Pouya;Stark, Alexander;Harp, Lindsey F.;Ye, Zhen;Lee, Leonard K.;Stuart, Rhona K.;Ching, Christina W.;Ching, Keith A.;Antosiewicz-Bourget, Jessica E.;Liu, Hui;Zhang, Xinmin;Green, Roland D.;Lobanenkov, Victor V.;Stewart, Ron;Thomson, James A.;Crawford, Gregory E.;Kellis, Manolis;Ren, Bing
通讯作者：
Ren, Bing
影响因子：
16
作者：
Hatzis, P;Talianidis, I
通讯作者：
Talianidis, I
DOI：
10.1073/pnas.112212199
发表时间：
2002-05-28
影响因子：
11.1
作者：
Lettice, LA;Horikoshi, T;Noji, S
通讯作者：
Noji, S
影响因子：
0.7
作者：
Alonso, M. Eva;Pernaute, Barbara;Manzanares, Miguel
通讯作者：
Manzanares, Miguel
影响因子：
--
作者：
Aparicio, Oscar;Geisberg, Joseph V;Struhl, Kevin
通讯作者：
Struhl, Kevin