CONTRAfold: RNA secondary structure prediction without physics-based models

By Chuong B. Do, Daniel A. Woods, Serafim Batzoglou. Intelligent Systems in Molecular Biology, 2006

612 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d5b78078c432369f8ff4de5b3e6eafdc08d7a173

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Knowledge-based machine learning methods for macromolecular 3D structure prediction (2016, methodology): “Folding RNA using predicted secondary structures: we use the secondary structures predicted by CONTRAfold (Do et al., 2006) and sample 1000 decoys for each RNA.”
Coarse-grained modeling of large RNA molecules with knowledge-based potentials and structural filters. (2009, methodology): “secondary structure is available through tools such as the thermodynamic method, Mfold (Zuker 2003), and the probabilistic method, Contrafold (Do et al. 2006).”
RNA Secondary Structure Prediction By Learning Unrolled Algorithms (2020, methodology): “Learning-based RNA folding methods such as ContraFold (Do et al., 2006) and ContextFold (Za-kov et al., 2011) have been proposed for energy parameters estimation due to the increasing availability of known RNA structures, resulting in higher prediction accuracies, but these methods still rely on the”
Tighter Bounds for Structured Estimation (2008, methodology): “The features of the model were chosen to match the energetic terms in standard thermodynamic models for RNA folding [4].”
Efficient multiple hyperparameter learning for log-linear models (2007, methodology): “To control overfitting, CONTRAfold uses flatL2 regularization.”
Accurate SHAPE-directed RNA structure determination (2009, methodology): “All structure calculations were performed using RNAstructure (11).”
Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions (2022, methodology): “Table 1 presents the accuracy of proposed RNA-FM and other advanced approaches [18, 19, 21, 22, 24, 25, 28, 30–32, 46, 47] to secondary structure prediction.”
RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning (2019, methodology): “We downloaded the stand-alone version of mxfold 33 (available at https:// github.com/keio-bioinformatics/mxfold), ContextFold 16 (available at https://www. cs.bgu.ac.il/negevcb/contextfold/), CONTRAfold 14 (available at http://contra. stanford.edu/contrafold/), Knotty 24 (available at https://github”
Rfam 14: expanded coverage of metagenomic, viral and microRNA families (2020, methodology): “The manually curated multiple sequence alignments from Rfam are also used for training and benchmarking new software, such as secondary structure prediction algorithms (11,12).”
PicXAA-R: Efficient structural alignment of multiple RNA sequences using a greedy approach (2011, methodology): “Thus, Wang et al. [44] These results conﬁrm that PicXAA-R can eﬃciently yield an accurate structural alignment for a set of large number of locally similar RNAs.”
Using Rosetta for RNA homology modeling (2019, methodology): “…is not available, tools for secondary structure prediction including RNAstructure (Reuter & Mathews, 2010), NUPACK (Dirks & Pierce, 2003), ViennaRNA (Lorenz et al., 2011), and CONTRAfold (Do, Woods, & Batzoglou, 2006) are appropriate although none reliably return information on pseudoknots.”
ViennaRNA Package 2.0 (2011, methodology): “The contrafold tools in fact recently bridged the apparent gap between the thermodynamic and the machine learning approach to RNA bioinformatics proposing to learn a parameter set for a SCFG that structurally matches the standard energy model [18].”