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.
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.
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