Neural networks to predict protein stability changes upon mutation

Black box modelling is used here to improve the performances of the PoPMuSiC program that predicts protein stability changes caused by single-site mutations. For that purpose previously developed statistical energy functions are exploited, which are based on a formalism that highlights the coupling between 4 different protein descriptors (sequence, distance, torsion angles and solvent-accessibility), as well as the volume variation of the mutated amino acid. As the importance of the different types of interactions may depend on the protein region, the stability change is expressed as a linear combination of these energetic functions, whose proportionality coefficients vary with the solvent-accessibility of the mutated residue. Two alternative structures are considered for these coefficients: a Radial Basis Function network, and a MultiLayer Perceptron with sigmoid nodes. These two structures are identified, leading to an improvement of the predictive capabilities of PoPMuSiC, and are discussed in terms of their biophysical interpretation.

[1]  M Karplus,et al.  Simulation analysis of the stability mutant R96H of T4 lysozyme. , 1991, Biochemistry.

[2]  T. Creighton.  Proteins: Structures and Molecular Properties , 1986 .

[3]  P. A. Bash,et al.  Free energy calculations by computer simulation. , 1987, Science.

[4]  W E Stites,et al.  Contributions of the large hydrophobic amino acids to the stability of staphylococcal nuclease. , 1990, Biochemistry.

[5]  Akinori Sarai,et al.  ProTherm, version 4.0: thermodynamic database for proteins and mutants , 2004, Nucleic Acids Res..

[6]  Marianne Rooman,et al.  PoPMuSiC, rationally designing point mutations in protein structures , 2002, Bioinform..

[7]  M. Michael Gromiha,et al.  3P068 Latest developments in ProTherm : Thermodynamic Database for Proteins and Mutants , 2004 .

[8]  V. Muñoz,et al.  Intrinsic secondary structure propensities of the amino acids, using statistical phi-psi matrices: comparison with experimental scales. , 1994, Proteins.

[9]  Liang-Tsung Huang,et al.  Sequence analysis and rule development of predicting protein stability change upon mutation using decision tree model , 2007, Journal of molecular modeling.

[10]  G. Rose,et al.  Hydrophobicity of amino acid residues in globular proteins. , 1985, Science.

[11]  R L Jernigan,et al.  Protein stability for single substitution mutants and the extent of local compactness in the denatured state. , 1994, Protein engineering.

[12]  W F van Gunsteren,et al.  Prediction of the activity and stability effects of site-directed mutagenesis on a protein core. , 1992, Journal of molecular biology.

[13]  M J Sippl,et al.  Knowledge-based potentials for proteins. , 1995, Current opinion in structural biology.

[14]  D Gilis,et al.  A new generation of statistical potentials for proteins. , 2006, Biophysical journal.

[15]  L. Serrano,et al.  Predicting changes in the stability of proteins and protein complexes: a study of more than 1000 mutations. , 2002, Journal of molecular biology.

[16]  B. Matthews,et al.  Response of a protein structure to cavity-creating mutations and its relation to the hydrophobic effect. , 1992, Science.

[17]  M. Michael Gromiha,et al.  CUPSAT: prediction of protein stability upon point mutations , 2006, Nucleic Acids Res..

[18]  S. Wodak,et al.  Prediction of protein backbone conformation based on seven structure assignments. Influence of local interactions. , 1991, Journal of molecular biology.

[19]  D Gilis,et al.  PoPMuSiC, an algorithm for predicting protein mutant stability changes: application to prion proteins. , 2000, Protein engineering.

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

[21]  Piero Fariselli,et al.  I-Mutant2.0: predicting stability changes upon mutation from the protein sequence or structure , 2005, Nucleic Acids Res..

[22]  A. Lehninger.  Principles of Biochemistry , 1984 .