Applying a neural network to predict the thermodynamic parameters for an expanded nearest-neighbor model.

Predicting the secondary and tertiary structure of RNAs largely depends on our capabilities in estimating the thermodynamics of RNA duplexes. In this work, an expanded nearest-neighbor model, designated INN-48, is established. The thermodynamic parameters of this model are predicted using both multiple linear regression analysis and neural network analysis. It is suggested that due to the increase in the number of parameters and the insufficiency of the existing data, neural network analysis results in more reliable predictions. Furthermore, it is suggested that INN-48 can be used to estimate the thermodynamics of RNA duplex formation for longer sequences, whereas INN-HB, the previous model on which INN-48 is based, can be used for short sequences.

[1]  I. Tinoco,et al.  Stability of ribonucleic acid double-stranded helices. , 1974, Journal of molecular biology.

[2]  D. Turner,et al.  Thermodynamic and activation parameters for binding of a pyrene-labeled substrate by the Tetrahymena ribozyme: docking is not diffusion-controlled and is driven by a favorable entropy change. , 1995, Biochemistry.

[3]  Wing Lok Abe Kurtz Chiu,et al.  NTDB: Thermodynamic Database for Nucleic Acids, Version 2.0 , 2003, Nucleic Acids Res..

[4]  D. Turner,et al.  Improved free-energy parameters for predictions of RNA duplex stability. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[5]  D. Draper,et al.  Thermodynamics of folding a pseudoknotted mRNA fragment. , 1994, Journal of molecular biology.

[6]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[7]  Sze Ki Chan,et al.  NTDB: Thermodynamic Database for Nucleic Acids , 2001, Nucleic Acids Res..

[8]  D. Turner,et al.  Comparison of binding of mixed ribose-deoxyribose analogues of CUCU to a ribozyme and to GGAGAA by equilibrium dialysis: evidence for ribozyme specific interactions with 2' OH groups. , 1991, Biochemistry.

[9]  D. Turner,et al.  Thermodynamic parameters for an expanded nearest-neighbor model for formation of RNA duplexes with Watson-Crick base pairs. , 1998, Biochemistry.

[10]  J. Sabina,et al.  Expanded sequence dependence of thermodynamic parameters improves prediction of RNA secondary structure. , 1999, Journal of molecular biology.

[11]  D. Gray,et al.  Derivation of nearest-neighbor properties from data on nucleic acid oligomers. I. Simple sets of independent sequences and the influence of absent nearest neighbors. , 1997, Biopolymers.

[12]  E. Westhof,et al.  Modelling of the three-dimensional architecture of group I catalytic introns based on comparative sequence analysis. , 1990, Journal of molecular biology.

[13]  D. Turner,et al.  Kinetics for reaction of a circularized intervening sequence with CU, UCU, CUCU, and CUCUCU: mechanistic implications from the dependence on temperature and on oligomer and Mg2+ concentrations. , 1988, Biochemistry.

[14]  M. D. Morris,et al.  Optical Melting of 128 Octamer DNA Duplexes , 1995, The Journal of Biological Chemistry.

[15]  D. Gray,et al.  Derivation of nearest-neighbor properties from data on nucleic acid oligomers. II. Thermodynamic parameters of DNA.RNA hybrids and DNA duplexes. , 1997, Biopolymers.

[16]  C. E. Longfellow,et al.  Improved parameters for prediction of RNA structure. , 1987, Cold Spring Harbor symposia on quantitative biology.

[17]  T. Cech,et al.  Ribozyme recognition of RNA by tertiary interactions with specific ribose 2′-OH groups , 1991, Nature.