A Hybrid Algorithm for Determining Protein Structure

At Thinking Machines, my colleagues and I have developed a hybrid system combining a neural network, a statistical module, and a memory-based reasoner, each of which makes its own prediction. A combiner then blends these results to produce the final predictions. This hybrid system improves its ability to determine how amino acid sequences fold into 3D protein structures. It predicts secondary structures with 66.4% accuracy. Both the neural network and the combiner are multilayer perceptrons trained with the standard backpropagation algorithm; this article focuses on the other two components, and on how we trained the hybrid system and used it for prediction. I also discuss how future work in AI and other sciences might meet the challenge of the protein folding problem. >

[1]  K Nishikawa,et al.  The folding type of a protein is relevant to the amino acid composition. , 1986, Journal of biochemistry.

[2]  Shoshana J. Wodak,et al.  Identification of predictive sequence motifs limited by protein structure data base size , 1988, Nature.

[3]  T. Sejnowski,et al.  Predicting the secondary structure of globular proteins using neural network models. , 1988, Journal of molecular biology.

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

[5]  M J Rooman,et al.  Automatic definition of recurrent local structure motifs in proteins. , 1990, Journal of molecular biology.

[6]  J. Richardson,et al.  The anatomy and taxonomy of protein structure. , 1981, Advances in protein chemistry.

[7]  J L Sussman,et al.  A 3D building blocks approach to analyzing and predicting structure of proteins , 1989, Proteins.

[8]  V. Lim.  Algorithms for prediction of α-helical and β-structural regions in globular proteins , 1974 .

[9]  L. Hunter,et al.  Bayesian classification of protein structural elements , 1991, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System Sciences.

[10]  R. Doolittle,et al.  A simple method for displaying the hydropathic character of a protein. , 1982, Journal of molecular biology.

[11]  R. Lavery,et al.  Describing protein structure: A general algorithm yielding complete helicoidal parameters and a unique overall axis , 1989, Proteins.

[12]  T. L. Blundell,et al.  Knowledge-based prediction of protein structures and the design of novel molecules , 1987, Nature.

[13]  Janet M. Thornton,et al.  Prediction of protein structure from amino acid sequence , 1978, Nature.

[14]  F. Richards,et al.  Identification of structural motifs from protein coordinate data: Secondary structure and first‐level supersecondary structure * , 1988, Proteins.

[15]  A. Kolinski,et al.  Simulations of the Folding of a Globular Protein , 1990, Science.

[16]  R J Fletterick,et al.  Secondary structure assignment for alpha/beta proteins by a combinatorial approach. , 1983, Biochemistry.

[17]  Richard H. Lathrop,et al.  ARIADNE: pattern-directed inference and hierarchical abstraction in protein structure recognition , 1987, CACM.

[18]  Russ B. Altman,et al.  PROTEAN: Deriving Protein Structure from Constraints , 1986, AAAI.

[19]  S. Doniach,et al.  A computer model to dynamically simulate protein folding: Studies with crambin , 1989, Proteins.

[20]  J. Garnier,et al.  Analysis of the accuracy and implications of simple methods for predicting the secondary structure of globular proteins. , 1978, Journal of molecular biology.

[21]  W R Taylor,et al.  Recognition of super-secondary structure in proteins. , 1984, Journal of molecular biology.

[22]  P. Y. Chou,et al.  Prediction of protein conformation. , 1974, Biochemistry.

[23]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[24]  J. Gibrat,et al.  Further developments of protein secondary structure prediction using information theory. New parameters and consideration of residue pairs. , 1987, Journal of molecular biology.