Literature DB >> 12855459

An ENSEMBLE machine learning approach for the prediction of all-alpha membrane proteins.

Pier Luigi Martelli1, Piero Fariselli, Rita Casadio.   

Abstract

MOTIVATION: All-alpha membrane proteins constitute a functionally relevant subset of the whole proteome. Their content ranges from about 10 to 30% of the cell proteins, based on sequence comparison and specific predictive methods. Due to the paucity of membrane proteins solved with atomic resolution, the training/testing sets of predictive methods for protein topography and topology routinely include very few well-solved structures mixed with a hundred proteins known with low resolution. Moreover, available predictors fail in predicting recently crystallised membrane proteins (Chen et al., 2002). Presently the number of well-solved membrane proteins comprises some 59 chains of low sequence homology. It is therefore possible to train/test predictors only with the set of proteins known with atomic resolution and evaluate more thoroughly the performance of different methods.
RESULTS: We implement a cascade-neural network (NN), two different hidden Markov models (HMM), and their ensemble (ENSEMBLE) as a new method. We train and test in cross validation the three methods and ENSEMBLE on the 59 well resolved membrane proteins. ENSEMBLE scores with a per-protein accuracy of 90% for topography and 71% for topology, outperforming the best single method of 7 and 5 percentage points, respectively. When tested on a low resolution set of 151 proteins, with no homology with the 59 proteins, the per-protein accuracy of ENSEMBLE is 76% for topography and 68% for topology. Our results also indicate that the performance of ENSEMBLE is higher than that of the best predictors presently available on the Web.

Mesh:

Substances:

Year:  2003        PMID: 12855459     DOI: 10.1093/bioinformatics/btg1027

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  26 in total

1.  An analysis of reentrant loops.

Authors:  Changhui Yan; Jingru Luo
Journal:  Protein J       Date:  2010-07       Impact factor: 2.371

2.  The implications of alternative splicing in the ENCODE protein complement.

Authors:  Michael L Tress; Pier Luigi Martelli; Adam Frankish; Gabrielle A Reeves; Jan Jaap Wesselink; Corin Yeats; Páll Isólfur Olason; Mario Albrecht; Hedi Hegyi; Alejandro Giorgetti; Domenico Raimondo; Julien Lagarde; Roman A Laskowski; Gonzalo López; Michael I Sadowski; James D Watson; Piero Fariselli; Ivan Rossi; Alinda Nagy; Wang Kai; Zenia Størling; Massimiliano Orsini; Yassen Assenov; Hagen Blankenburg; Carola Huthmacher; Fidel Ramírez; Andreas Schlicker; France Denoeud; Phil Jones; Samuel Kerrien; Sandra Orchard; Stylianos E Antonarakis; Alexandre Reymond; Ewan Birney; Søren Brunak; Rita Casadio; Roderic Guigo; Jennifer Harrow; Henning Hermjakob; David T Jones; Thomas Lengauer; Christine A Orengo; László Patthy; Janet M Thornton; Anna Tramontano; Alfonso Valencia
Journal:  Proc Natl Acad Sci U S A       Date:  2007-03-19       Impact factor: 11.205

Review 3.  Membrane protein prediction methods.

Authors:  Marco Punta; Lucy R Forrest; Henry Bigelow; Andrew Kernytsky; Jinfeng Liu; Burkhard Rost
Journal:  Methods       Date:  2007-04       Impact factor: 3.608

4.  Research resource: EPSLiM: ensemble predictor for short linear motifs in nuclear hormone receptors.

Authors:  Ran Xue; Mikhail N Zakharov; Yu Xia; Shalender Bhasin; James C Costello; Ravi Jasuja
Journal:  Mol Endocrinol       Date:  2014-03-28

Review 5.  Computational studies of membrane proteins: models and predictions for biological understanding.

Authors:  Jie Liang; Hammad Naveed; David Jimenez-Morales; Larisa Adamian; Meishan Lin
Journal:  Biochim Biophys Acta       Date:  2011-10-12

6.  The Regulatory Domain of Squalene Monooxygenase Contains a Re-entrant Loop and Senses Cholesterol via a Conformational Change.

Authors:  Vicky Howe; Ngee Kiat Chua; Julian Stevenson; Andrew J Brown
Journal:  J Biol Chem       Date:  2015-10-03       Impact factor: 5.157

7.  Transmembrane protein topology prediction using support vector machines.

Authors:  Timothy Nugent; David T Jones
Journal:  BMC Bioinformatics       Date:  2009-05-26       Impact factor: 3.169

8.  MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering.

Authors:  Eun-Youn Kim; Seon-Young Kim; Daniel Ashlock; Dougu Nam
Journal:  BMC Bioinformatics       Date:  2009-08-22       Impact factor: 3.169

9.  HMM_RA: an improved method for alpha-helical transmembrane protein topology prediction.

Authors:  Jing Hu; Changhui Yan
Journal:  Bioinform Biol Insights       Date:  2008-01-31

10.  MetaTM - a consensus method for transmembrane protein topology prediction.

Authors:  Martin Klammer; David N Messina; Thomas Schmitt; Erik L L Sonnhammer
Journal:  BMC Bioinformatics       Date:  2009-09-28       Impact factor: 3.169

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.