SMURFLite: combining simplified Markov random fields with simulated evolution improves remote homology detection for beta-structural proteins into the twilight zone.
SMURFLite: combining simplified Markov random fields with simulated evolution improves remote homology detection for beta-structural proteins into the twilight zone.
复制标题
DOI：
10.1093/bioinformatics/bts110
复制
发表时间：
2012-05-01
期刊：
影响因子：
--
通讯作者：
Cowen LJ
中科院分区：
文献类型：
--
作者：
Daniels NM;Hosur R;Berger B;Cowen LJ
动机：迄今为止，识别进化相关的蛋白质序列的最成功的方法之一是轮廓隐马尔可夫模型（HMRM）。然而，这些模型不能捕获在β折叠中氢键键合的残基的成对统计偏好。这些依赖关系已经部分捕获的HMM设置在训练阶段的模拟进化，可以完全捕获的马尔可夫随机场（MRF）。然而，当β链在复杂拓扑结构中交织时，MRF可能在计算上是禁止的。我们介绍SMURFLite，一种方法，结合了简化的MRF和模拟进化，大大提高远程同源检测β结构。与以前的基于MRF的方法不同，SMURFLite在任何β结构基序上都是计算可行的。结果：我们在严格的交叉验证实验中对SCOP层次结构的主要β类中的所有螺旋桨和桶折叠测试SMURFLite。我们显示平均26%与HMMER相比，β结构基序识别的曲线下面积（AUC）改善（中位数16%）（一种著名的HMM方法）和平均33%（中位数19%）与RAPTOR相比改善（一种众所周知的穿线方法），甚至平均18%尽管HHpred使用了大量额外的训练数据，但其AUC相对于HHpred（一种轮廓-轮廓HMM方法）的改善（中位数10%）仍然是显著的。我们证明了SMURFLite的能力，通过运行SMURFLite库的207个β-结构SCOP超家族对整个基因组的海栖热袍菌，并作出超过100个新的倍预测。可用性和实施：运行SMURFLite的Web服务器可在以下网址获得：http://smurf.cs.tufts.edu/smurflite/联系人：lenore. tufts.edu; bab@mit.edu
Motivation: One of the most successful methods to date for recognizing protein sequences that are evolutionarily related has been profile hidden Markov models (HMMs). However, these models do not capture pairwise statistical preferences of residues that are hydrogen bonded in beta sheets. These dependencies have been partially captured in the HMM setting by simulated evolution in the training phase and can be fully captured by Markov random fields (MRFs). However, the MRFs can be computationally prohibitive when beta strands are interleaved in complex topologies. We introduce SMURFLite, a method that combines both simplified MRFs and simulated evolution to substantially improve remote homology detection for beta structures. Unlike previous MRF-based methods, SMURFLite is computationally feasible on any beta-structural motif. Results: We test SMURFLite on all propeller and barrel folds in the mainly-beta class of the SCOP hierarchy in stringent cross-validation experiments. We show a mean 26% (median 16%) improvement in area under curve (AUC) for beta-structural motif recognition as compared with HMMER (a well-known HMM method) and a mean 33% (median 19%) improvement as compared with RAPTOR (a well-known threading method) and even a mean 18% (median 10%) improvement in AUC over HHPred (a profile–profile HMM method), despite HHpred's use of extensive additional training data. We demonstrate SMURFLite's ability to scale to whole genomes by running a SMURFLite library of 207 beta-structural SCOP superfamilies against the entire genome of Thermotoga maritima, and make over a 100 new fold predictions. Availability and implementaion: A webserver that runs SMURFLite is available at: http://smurf.cs.tufts.edu/smurflite/ Contact: lenore.cowen@tufts.edu; bab@mit.edu
登录
查看更多内容
影响因子：
2.9
作者：
Peng, Jian;Xu, Jinbo
通讯作者：
Xu, Jinbo
DOI：
10.1073/pnas.0909950107
发表时间：
2010-03-02
影响因子：
11.1
作者：
Menke, Matt;Berger, Bonnie;Cowen, Lenore
通讯作者：
Cowen, Lenore
影响因子：
5.6
作者：
LIFSON, S;SANDER, C
通讯作者：
SANDER, C
影响因子：
2.9
作者：
SVENSSON, B;SVENDSEN, I;POULSEN, FM
通讯作者：
POULSEN, FM
DOI：
10.1093/bioinformatics/btp265
发表时间：
2009-07-01
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Kumar A;Cowen L
通讯作者：
Cowen L