Augmented training of hidden Markov models to recognize remote homologs via simulated evolution.

Augmented training of hidden Markov models to recognize remote homologs via simulated evolution.
复制标题

DOI:
10.1093/bioinformatics/btp265
复制
发表时间:
2009-07-01
期刊:
Bioinformatics (Oxford, England)
影响因子:
--
通讯作者:
Cowen L
Cowen L
中科院分区:
其他
文献类型:
--
作者:
Kumar A;Cowen L

文献摘要

参考文献

被引文献

相似文献

动机:虽然轮廓隐马尔可夫模型 (HMM) 是识别同源蛋白质的成功且强大的方法,但当由于缺乏足够的训练数据而同源性变得太远时,它们可能会崩溃。我们证明,通过使用简单的模拟进化模型来创建增强训练集,我们可以提高 HMM 在该领域的性能。结果:我们表明,在两个不同的远程蛋白质同源任务中,通过模拟进化增强训练的 HMM 优于仅在真实数据上训练的 HMM。我们发现,15% 至 20% 之间的突变率最适合识别不同类别的 G 蛋白偶联受体蛋白,以及识别来自不同家族的 SCOP 超家族蛋白。联系方式: anoop.kumar@tufts.edu;lenore.cowen@tufts.edu
Motivation: While profile hidden Markov models (HMMs) are successful and powerful methods to recognize homologous proteins, they can break down when homology becomes too distant due to lack of sufficient training data. We show that we can improve the performance of HMMs in this domain by using a simple simulated model of evolution to create an augmented training set. Results: We show, in two different remote protein homolog tasks, that HMMs whose training is augmented with simulated evolution outperform HMMs trained only on real data. We find that a mutation rate between 15 and 20% performs best for recognizing G-protein coupled receptor proteins in different classes, and for recognizing SCOP super-family proteins from different families. Contacts: anoop.kumar@tufts.edu;lenore.cowen@tufts.edu
Pfam:氏族、网络工具和服务。
DOI: 10.1093/nar/gkj149
发表时间: 2006-01-01
影响因子: 14.9
作者:
Finn, Robert D.;Mistry, Jaina;Schuster-Bockler, Benjamin;Griffiths-Jones, Sam;Hollich, Volker;Lassmann, Timo;Moxon, Simon;Marshall, Mhairi;Khanna, Ajay;Durbin, Richard;Eddy, Sean R.;Sonnhammer, Erik L. L.;Bateman, Alex
通讯作者: Bateman, Alex
DOI: 10.1016/j.jmb.2004.03.023
发表时间: 2004-05-07
影响因子: 5.6
作者:
Wistrand, M;Sonnhammer, ELL
通讯作者: Sonnhammer, ELL
DOI: 10.1093/bioinformatics/14.10.846
发表时间: 1998-01-01
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Karplus, K;Barrett, C;Hughey, R
通讯作者: Hughey, R
DOI: 10.1093/bib/bbm064
发表时间: 2008-05-01
影响因子: 9.5
作者:
Sonego, Paolo;Kocsor, Andras;Pongor, Sandor
通讯作者: Pongor, Sandor
DOI: 10.1093/nar/gkj063
发表时间: 2006-01-01
影响因子: 14.9
作者:
Hulo, Nicolas;Bairoch, Amos;Bulliard, Virginie;Cerutti, Lorenzo;De Castro, Edouard;Langendijk-Genevaux, Petra S.;Pagni, Marco;Sigrist, Christian J. A.
通讯作者: Sigrist, Christian J. A.