How Many 3D Structures Do We Need to Train a Predictor?
It has been shown that the progress in the determination of membrane protein structure grows exponentially, with approximately the same growth rate as that of the water-soluble proteins. In order to investigate the effect of this, on the perfor-mance of prediction algorithms for both a-helical and β-barrel membrane proteins, we conducted a prospective study based on historical records. We trained separate hidden Markov models with different sized training sets and evaluated their per-formance on topology prediction for the two classes of transmembrane proteins. We show that the existing top-scoring algorithms for predicting the transmem-brahe segments of α-helical membrane proteins perform slightly better than that of β-barrel outer membrane proteins in all measures of accuracy. With the same rationale, a meta-analysis of the performance of the secondary structure predic-tion algorithms indicates that existing algorithmic techniques cannot be further improved by just adding more non-homologous sequences to the training sets. The upper limit for secondary structure prediction is estimated to be no more than 70% and 80% of correctly predicted residues for single sequence based methods and multiple sequence based ones, respectively. Therefore, we should concentrate our efforts on utilizing new techniques for the development of even better scoring predictors.
作 者： Pantelis G. Bagos Georgios N. Tsaousis Stavros J. Hamodrakas 作者单位： Pantelis G. Bagos(Department of Cell Biology and Biophysics, Faculty of Biology, University of Athens, Athens 15701, Greece;Department of Computer Science and Biomedical Informatics, University of Central Greece, Lamia 35100, Greece)Georgios N. Tsaousis,Stavros J. Hamodrakas(Department of Cell Biology and Biophysics, Faculty of Biology, University of Athens, Athens 15701, Greece)
刊 名： 基因组蛋白质组与生物信息学报（英文版） 英文刊名： GENOMICS、PROTEOMICS & BIOINFORMATICS 年，卷(期)： 2009 7(3) 分类号： Q5 关键词： membrane protein secondary structure prediction alpha-helical beta-barrel 3D structure