Table 1. Summary of the ML-based RNA secondary structure prediction methods.
| Category | Title | Date | Author | ML Technique | Resource | Reference | |
|---|---|---|---|---|---|---|---|
| Score scheme based on ML model | Free energy parameter-refining approach based on ML | Thermodynamic Parameters for an Expanded Nearest-Neighbor Model for Formation of RNA Duplexes with Watson-Crick Base Pairs | 1998 | Xia et al. | Linear regression | Table 1 in the paper (https://pubs.acs.org/doi/10.1021/bi9809425#) | [56] |
| Efficient parameter estimation for RNA secondary structure prediction | 2007 | Andronescu et al. | Constraint generation | http://www.rnasoft.ca/CG/ | [73] | ||
| Computational approaches for RNA energy parameter estimation | 2010 | Andronescu et al. | Loss-augmented max-margin constraint generation model, Boltzmann-likelihood model | http://www.cs.ubc.ca/labs/beta/Projects/RNA-Params | [74] | ||
| Weighted approach based on ML | Rich Parameterization Improves RNA Structure Prediction | 2011 | Zakov et al. | Discriminative structured-prediction learning framework combined, online learning algorithm | http://www.cs.bgu.ac.il/?negevcb/contextfold | [77] | |
| A Max-Margin Training of RNA Secondary Structure Prediction Integrated with the Thermodynamic Model | 2018 | Akiyama et al. | SSVM | https://github.com/keio-bioinformatics/mxfold | [78] | ||
| RNA secondary structure prediction using deep learning with thermodynamic integration |
2021 | Sato et al. | Deep neural network | http://www.dna.bio.keio.ac.jp/mxfold2/ | [79] | ||
| Probabilistic approach based on ML | Stochastic context-free grammars for tRNA modeling | 1994 | Sakakibara et al. | EM method | - | [29] | |
| RNA secondary structure prediction using stochastic context-free grammars and evolutionary history | 1999 | Knudsen and Hein | EM method | - | [82] | ||
| Pfold: RNA secondary structure prediction using stochastic context-free grammars | 2003 | Knudsen and Hein | EM method | [81] | |||
| CONTRAfold: RNA secondary structure prediction without physics-based models | 2006 | Do et al. | CLLM | http://contra.stanford.edu/contrafold/ | [86] | ||
| A semi-supervised learning approach for RNA secondary structure prediction | 2015 | Yonemoto et al. | Semi-supervised learning algorithm | - | [87] | ||
| Preprocessing and postprocessing based on ML model | Preprocessing based on ML model | A tool preference choice method for RNA secondary structure prediction by SVM with statistical tests | 2013 | Hor et al. | SVM | - | [88] |
| Research on folding diversity in statistical learning methods for RNA secondary structure prediction | 2018 | Zhu et al. | Statistical context-free grammar model | - | [89] | ||
| Postprocessing based on ML model | Using a neural network to identify secondary RNA structures quantified by graphical invariants | 2008 | Haynes et al. | MLP | - | [90] | |
| A predictive model for secondary RNA structure using graph theory and a neural network | 2010 | Koessler et al. | MLP | - | [91] | ||
| Predicting process based on ML model | End-to-end approach | Parallel algorithms for finding a near-maximum independent set of a circle graph | 1990 | Takefuji et al. | System composed of several interactional neurons | - | [92] |
| An Hopfield Neural Network-Based Algorithm for RNA Secondary Structure Prediction | 2006 | Liu et al. | Hopfield networks | - | [93] | ||
| Secondary Structure Prediction of RNA using Machine Learning Method | 2011 | Qasim et al. | MLP | - | [96] | ||
| Neural Networks, Adaptive Optimization, and RNA Secondary Structure Prediction | 1993 | Steeg | MFT network | - | [94] | ||
| RNA secondary structure prediction by MFT neural networks | 2003 | Apolloni et al. | MFT network with mean field approximation to update network’s nodes | - | [139] | ||
| RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning | 2019 | Singh et al. | Compound deep neural networks, transfer learning | https://sparks-lab.org/server/spot-rna/ | [97] | ||
| RNA secondary structure prediction by learning unrolled algorithms | 2020 | Chen et al. | Compound deep neural networks | https://github.com/ml4bio/e2efold | [99] | ||
| Machine learning a model for RNA structure prediction | 2020 | Calonaci et al. | CNN, MLP | - | [100] | ||
| Hybrid approach | RNA secondary structure prediction from sequence alignments using a network of k-nearest neighbor classifiers | 2006 | Bindewald et al. | Hierarchical network of k-nearest neighbor model | - | [49] | |
| Developing parallel ant colonies filtered by deep learned constrains for predicting RNA secondary structure with pseudo-knots | 2020 | Quan et al. | Bi-LSTM | - | [103] | ||
| RNA Secondary Structure Prediction Based on Long Short-Term Memory Model | 2018 | Wu et al. | Bi-LSTM | - | [102] | ||
| Predicting RNA secondary structure via adaptive deep recurrent neural networks with energy-based filter | 2019 | Lu et al. | Bi-LSTM | - | [101] | ||
| A New Method of RNA Secondary Structure Prediction Based on Convolutional Neural Network and Dynamic Programming | 2019 | Zhang et al. | CNN | - | [104] | ||
| DMfold: A Novel Method to Predict RNA Secondary Structure with Pseudoknots Based on Deep Learning and Improved Base Pair Maximization Principle | 2019 | Wang et al. | Bi-LSTM | https://github.com/linyuwangPHD/RNA-Secondary-Structure-Database. | [105] | ||
| Improving RNA secondary structure prediction via state inference with deep recurrent neural networks | 2020 | Willmott et al. | Bi-LSTM | https://github.com/dwillmott/rna-state-inf | [107] | ||
“-”indicates “not available.”
CLLM, conditional log-linear model; CNN, convolutional neural network; EM, expectation-maximization; MFT, mean field theory; ML, machine learning; MLP, multilayer perceptron; SSVM, structured support vector machine; SVM, support vector machine.