CONTRAfold: RNA secondary structure prediction without physics-based models.

@article{citeulike:804401, abstract = {MOTIVATION: For several decades, free energy minimization methods have been the dominant strategy for single sequence RNA secondary structure prediction. More recently, stochastic context-free grammars (SCFGs) have emerged as an alternative probabilistic methodology for modeling RNA structure. Unlike physics-based methods, which rely on thousands of experimentally-measured thermodynamic parameters, SCFGs use fully-automated statistical learning algorithms to derive model parameters. Despite this advantage, however, probabilistic methods have not replaced free energy minimization methods as the tool of choice for secondary structure prediction, as the accuracies of the best current SCFGs have yet to match those of the best physics-based models. RESULTS: In this paper, we present CONTRAfold, a novel secondary structure prediction method based on conditional log-linear models (CLLMs), a flexible class of probabilistic models which generalize upon SCFGs by using discriminative training and feature-rich scoring. In a series of cross-validation experiments, we show that grammar-based secondary structure prediction methods formulated as CLLMs consistently outperform their SCFG analogs. Furthermore, CONTRAfold, a CLLM incorporating most of the features found in typical thermodynamic models, achieves the highest single sequence prediction accuracies to date, outperforming currently available probabilistic and physics-based techniques. Our result thus closes the gap between probabilistic and thermodynamic models, demonstrating that statistical learning procedures provide an effective alternative to empirical measurement of thermodynamic parameters for RNA secondary structure prediction. AVAILABILITY: Source code for CONTRAfold is available at http://contra.stanford.edu/contrafold/. CONTACT: chuongdo@cs.stanford.edu.}, address = {Computer Science Department, Stanford University Stanford, CA 94305, USA.}, author = {Do, C. B. and Woods, D. A. and Batzoglou, S. }, citeulike-article-id = {804401}, doi = {http://dx.doi.org/10.1093/bioinformatics/btl246}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {folding, prediction, rna, secondary, structure}, month = {July}, number = {14}, posted-at = {2008-07-17 02:09:45}, priority = {0}, title = {CONTRAfold: RNA secondary structure prediction without physics-based models.}, url = {http://dx.doi.org/10.1093/bioinformatics/btl246}, volume = {22}, year = {2006} }

TY - JOUR ID - citeulike:804401 L3 - citeulike-article-id:804401 TI - CONTRAfold: RNA secondary structure prediction without physics-based models. JF - Bioinformatics VL - 22 IS - 14 AD - Computer Science Department, Stanford University Stanford, CA 94305, USA. SN - 1460-2059 N2 - MOTIVATION: For several decades, free energy minimization methods have been the dominant strategy for single sequence RNA secondary structure prediction. More recently, stochastic context-free grammars (SCFGs) have emerged as an alternative probabilistic methodology for modeling RNA structure. Unlike physics-based methods, which rely on thousands of experimentally-measured thermodynamic parameters, SCFGs use fully-automated statistical learning algorithms to derive model parameters. Despite this advantage, however, probabilistic methods have not replaced free energy minimization methods as the tool of choice for secondary structure prediction, as the accuracies of the best current SCFGs have yet to match those of the best physics-based models. RESULTS: In this paper, we present CONTRAfold, a novel secondary structure prediction method based on conditional log-linear models (CLLMs), a flexible class of probabilistic models which generalize upon SCFGs by using discriminative training and feature-rich scoring. In a series of cross-validation experiments, we show that grammar-based secondary structure prediction methods formulated as CLLMs consistently outperform their SCFG analogs. Furthermore, CONTRAfold, a CLLM incorporating most of the features found in typical thermodynamic models, achieves the highest single sequence prediction accuracies to date, outperforming currently available probabilistic and physics-based techniques. Our result thus closes the gap between probabilistic and thermodynamic models, demonstrating that statistical learning procedures provide an effective alternative to empirical measurement of thermodynamic parameters for RNA secondary structure prediction. AVAILABILITY: Source code for CONTRAfold is available at http://contra.stanford.edu/contrafold/. CONTACT: chuongdo@cs.stanford.edu. KW - folding KW - prediction KW - rna KW - secondary KW - structure AU - Do, CB AU - Woods, DA AU - Batzoglou, S PY - 2006/07/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btl246 ER -