Prediction of coordination number and relative solvent accessibility in proteins

Knowing the coordination number and relative solvent accessibility of all the residues in a protein is crucial for deriving constraints useful in modeling protein folding and protein structure and in scoring remote homology searches. We develop ensembles of bidirectional recurrent neural network architectures to improve the state of the art in both contact and accessibility prediction, leveraging a large corpus of curated data together with evolutionary information. The ensembles are used to discriminate between two different states of residue contacts or relative solvent accessibility, higher or lower than a threshold determined by the average value of the residue distribution or the accessibility cutoff. For coordination numbers, the ensemble achieves performances ranging within 70.6–73.9% depending on the radius adopted to discriminate contacts (6Å–12Å). These performances represent gains of 16–20% over the baseline statistical predictor, always assigning an amino acid to the largest class, and are 4–7% better than any previous method. A combination of different radius predictors further improves performance. For accessibility thresholds in the relevant 15–30% range, the ensemble consistently achieves a performance above 77%, which is 10–16% above the baseline prediction and better than other existing predictors, by up to several percentage points. For both problems, we quantify the improvement due to evolutionary information in the form of PSI‐BLAST‐generated profiles over BLAST profiles. The prediction programs are implemented in the form of two web servers, CONpro and ACCpro, available at http://promoter.ics.uci.edu/BRNN‐PRED/. Proteins 2002;47:142–153. © 2002 Wiley‐Liss, Inc.

[1]  W. Kabsch,et al.  Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features , 1983, Biopolymers.

[2]  S H Kim,et al.  Predicting surface exposure of amino acids from protein sequence. , 1990, Protein engineering.

[3]  E. Myers,et al.  Basic local alignment search tool. , 1990, Journal of molecular biology.

[4]  A. Lupas,et al.  Predicting coiled coils from protein sequences , 1991, Science.

[5]  U. Hobohm,et al.  Selection of representative protein data sets , 1992, Protein science : a publication of the Protein Society.

[6]  M. Karplus,et al.  How does a protein fold? , 1994, Nature.

[7]  B. Rost,et al.  Combining evolutionary information and neural networks to predict protein secondary structure , 1994, Proteins.

[8]  B. Rost,et al.  Conservation and prediction of solvent accessibility in protein families , 1994, Proteins.

[9]  C. Sander,et al.  Can three-dimensional contacts in protein structures be predicted by analysis of correlated mutations? , 1994, Protein engineering.

[10]  W. Taylor,et al.  Global fold determination from a small number of distance restraints. , 1995, Journal of molecular biology.

[11]  M J Sippl,et al.  Progress in fold recognition , 1995, Proteins.

[12]  R A Goldstein,et al.  Predicting solvent accessibility: Higher accuracy using Bayesian statistics and optimized residue substitution classes , 1996, Proteins.

[13]  J. Wootton,et al.  Analysis of compositionally biased regions in sequence databases. , 1996, Methods in enzymology.

[14]  Thomas L. Madden,et al.  Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. , 1997, Nucleic acids research.

[15]  A. Valencia,et al.  Improving contact predictions by the combination of correlated mutations and other sources of sequence information. , 1997, Folding & design.

[16]  R. Abagyan,et al.  Do aligned sequences share the same fold? , 1997, Journal of molecular biology.

[17]  O. Lund,et al.  Protein distance constraints predicted by neural networks and probability density functions. , 1997, Protein engineering.

[18]  S Pascarella,et al.  Easy method to predict solvent accessibility from multiple protein sequence alignments , 1998, Proteins.

[19]  D J Barlow,et al.  The bottom line for prediction of residue solvent accessibility. , 1999, Protein engineering.

[20]  Pierre Tufféry,et al.  PredAcc: prediction of solvent accessibility , 1999, Bioinform..

[21]  R. Casadio,et al.  A neural network based predictor of residue contacts in proteins. , 1999, Protein engineering.

[22]  K. Dill.  Polymer principles and protein folding , 1999, Protein science : a publication of the Protein Society.

[23]  B. Rost,et al.  Effective use of sequence correlation and conservation in fold recognition. , 1999, Journal of molecular biology.

[24]  Giovanni Soda,et al.  Exploiting the past and the future in protein secondary structure prediction , 1999, Bioinform..

[25]  D T Jones,et al.  Protein secondary structure prediction based on position-specific scoring matrices. , 1999, Journal of molecular biology.

[26]  J. Skolnick,et al.  Ab initio folding of proteins using restraints derived from evolutionary information , 1999, Proteins.

[27]  Ole Lund,et al.  Using Sequence Motifs for Enhanced Neural Network Prediction of Protein Distance Constraints , 1999, ISMB.

[28]  G J Barton,et al.  Application of multiple sequence alignment profiles to improve protein secondary structure prediction , 2000, Proteins.

[29]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[30]  Piero Fariselli,et al.  Prediction of the Number of Residue Contacts in Proteins , 2000, ISMB.

[31]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[32]  O. Carugo,et al.  Predicting residue solvent accessibility from protein sequence by considering the sequence environment. , 2000, Protein engineering.

[33]  Matching Protein-Sheet Partners by Feedforward and Recurrent Neural Networks , 2000 .

[34]  Gregory R. Grant,et al.  Bioinformatics - The Machine Learning Approach , 2000, Comput. Chem..

[35]  Pierre Baldi,et al.  Matching Protein b-Sheet Partners by Feedforward and Recurrent Neural Networks , 2000, ISMB.

[36]  Gianluca Pollastri,et al.  Machine Learning Structural and Functional Proteomics , 2001 .

[37]  Giovanni Soda,et al.  Bidirectional Dynamics for Protein Secondary Structure Prediction , 2001, Sequence Learning.

[38]  A. Lesk,et al.  Assessment of novel fold targets in CASP4: Predictions of three‐dimensional structures, secondary structures, and interresidue contacts , 2001, Proteins.

[39]  Thomas G. Dietterich,et al.  Bioinformatics The Machine Learning Approach 2nd ed. , 2001 .

[40]  Xian-Ming Pan,et al.  New method for accurate prediction of solvent accessibility from protein sequence , 2001, Proteins.

[41]  H Naderi-Manesh,et al.  Prediction of protein surface accessibility with information theory. , 2000, Proteins.

[42]  Pierre Baldi,et al.  Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles , 2002, Proteins.

[43]  B. Rost,et al.  Alignments grow, secondary structure prediction improves , 2002, Proteins.