Optimized mixed Markov models for motif identification.

Optimized mixed Markov models for motif identification.
复制标题

DOI:
10.1186/1471-2105-7-279
复制
发表时间:
2006-06-02
期刊:
影响因子:
3
通讯作者:
Li L
Li L
中科院分区:
生物学4区
文献类型:
--
作者:
Huang W;Umbach DM;Ohler U;Li L

文献摘要

参考文献

被引文献

相似文献

识别功能元件(例如转录因子结合位点)是重建基因调控网络的基本步骤,并且仍然是一个具有挑战性的问题,这主要是由于训练样本的可用性有限。我们引入了一种新颖且灵活的模型,即优化混合马尔可夫模型(OMiMa)和相关方法,以允许调整不同主题的模型复杂性。与其他领先方法相比,OMiMa 可以包含的不仅仅是 NNSplice 的成对依赖关系; OMiMa 比置换变长马尔可夫模型 (PVLMM) 更好地避免模型过拟合; OMiMa 需要比最大熵模型 (MEM) 更小的训练样本。对模拟数据和实际数据(监管顺式元件和剪接位点)进行测试,我们发现 OMiMa 在预测精度、所需训练数据大小或计算时间方面的性能优于其他领先方法。据我们所知,我们的 OMiMa 系统是唯一能够自动选择最佳模型的主题查找工具。 OMiMa 可在以下位置免费获取。我们优化的马尔可夫模型混合代表了对生物基序内的依赖结构进行建模的现有方法的替代方法。我们的模型在概念上简单有效,并且可以比其他领先方法提高预测精度和/或计算速度。
Identifying functional elements, such as transcriptional factor binding sites, is a fundamental step in reconstructing gene regulatory networks and remains a challenging issue, largely due to limited availability of training samples. We introduce a novel and flexible model, the Optimized Mixture Markov model (OMiMa), and related methods to allow adjustment of model complexity for different motifs. In comparison with other leading methods, OMiMa can incorporate more than the NNSplice's pairwise dependencies; OMiMa avoids model over-fitting better than the Permuted Variable Length Markov Model (PVLMM); and OMiMa requires smaller training samples than the Maximum Entropy Model (MEM). Testing on both simulated and actual data (regulatory cis-elements and splice sites), we found OMiMa's performance superior to the other leading methods in terms of prediction accuracy, required size of training data or computational time. Our OMiMa system, to our knowledge, is the only motif finding tool that incorporates automatic selection of the best model. OMiMa is freely available at. Our optimized mixture of Markov models represents an alternative to the existing methods for modeling dependent structures within a biological motif. Our model is conceptually simple and effective, and can improve prediction accuracy and/or computational speed over other leading methods.
DOI: 10.1016/0022-2836(86)90165-8
发表时间: 1986-04-05
影响因子: 5.6
作者:
SCHNEIDER, TD;STORMO, GD;EHRENFEUCHT, A
通讯作者: EHRENFEUCHT, A
DOI: 10.1093/nar/30.5.1255
发表时间: 2002-03-01
影响因子: 14.9
作者:
Bulyk, ML;Johnson, PLF;Church, GM
通讯作者: Church, GM
DOI: 10.1038/nbt718
发表时间: 2002-08-01
影响因子: 46.9
作者:
Roulet, E;Busso, S;Bucher, P
通讯作者: Bucher, P
DOI: 10.1038/nature01644
发表时间: 2003-05-15
期刊: NATURE
影响因子: 64.8
作者:
Kellis, M;Patterson, N;Lander, ES
通讯作者: Lander, ES
DOI: 10.1016/0005-2795(75)90109-9
发表时间: 1975-01-01
期刊: BIOCHIMICA ET BIOPHYSICA ACTA
影响因子: --
作者:
MATTHEWS, BW
通讯作者: MATTHEWS, BW