Inference of RNA structural contacts by direct coupling analysis

He, Xiaoling; Li, Shuaimin; Ou, Xiujuan; Wang, Jun; Xiao, Yi

doi:10.4310/cis.2019.v19.n3.a3

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, He et al compared the performance of different approaches of inferring RNA contacts and found that a deep learning model of fully convolutional neural network improved the performance of DCA. [66] More examples can be found in the literature. [67,68] It should be noted that a simple transferring of the approaches developed for protein structure prediction may not work for RNAs, since the latter is very flexible in the structures, [69] and the available experimental structures are far less than the former.…”

Section: Electrostatic Interactions In Rna Structuresmentioning

confidence: 99%

Computational prediction of RNA tertiary structures using machine learning methods*

Huang¹,

Du²,

Zhang³

et al. 2020

Chinese Phys. B

Self Cite

View full text Add to dashboard Cite

RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, and facilitating the design of new RNAs. Machine learning (ML) techniques have made tremendous progress in many fields in the past few years. Although their usage in protein-related fields has a long history, the use of ML methods in predicting RNA tertiary structures is new and rare. Here, we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation, the difficulties and potentials of these approaches when applied in the field.

show abstract

Section: Electrostatic Interactions In Rna Structuresmentioning

confidence: 99%

Computational prediction of RNA tertiary structures using machine learning methods*

Huang¹,

Du²,

Zhang³

et al. 2020

Chinese Phys. B

Self Cite

View full text Add to dashboard Cite

show abstract

“…[24] The basic principle of DCA is briefly presented according to the detailed description in our previously published papers. [21,30] For a target RNA sequence, we can do multiple sequence alignment (MSA) with its homologous sequences from the same RNA family. The MSA can be represented as…”

Section: Direct Coupling Analysismentioning

confidence: 99%

Improving RNA secondary structure prediction using direct coupling analysis

He¹,

Wang²,

Wang³

et al. 2020

Chinese Phys. B

Self Cite

View full text Add to dashboard Cite

Secondary structures of RNAs are the basis of understanding their tertiary structures and functions and so their predictions are widely needed due to increasing discovery of noncoding RNAs. In the last decades, a lot of methods have been proposed to predict RNA secondary structures but their accuracies encountered bottleneck. Here we present a method for RNA secondary structure prediction using direct coupling analysis and a remove-and-expand algorithm that shows better performance than four existing popular multiple-sequence methods. We further show that the results can also be used to improve the prediction accuracy of the single-sequence methods.

show abstract

“…Additionally, MXfold2 [ 20 ] introduces a deep neural network into an RNA folding score function to learn Turner’s nearest-neighbour free energy parameters. We proposed a deep learning method to improve RNA secondary structure prediction using direct coupling analysis of aligned homologous sequences [ 21 ]. Recently, we also proposed an RNA secondary structure prediction method with pseudoknots named as 2dRNA [ 22 ], which used coupled deep learning neural networks of bidirectional LSTM [ 23 ] and U-net [ 24 ], and was trained, validated and tested by using the dataset ArchiveII [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Length-Dependent Deep Learning Model for RNA Secondary Structure Prediction

2022

Self Cite

View full text Add to dashboard Cite

Deep learning methods for RNA secondary structure prediction have shown higher performance than traditional methods, but there is still much room to improve. It is known that the lengths of RNAs are very different, as are their secondary structures. However, the current deep learning methods all use length-independent models, so it is difficult for these models to learn very different secondary structures. Here, we propose a length-dependent model that is obtained by further training the length-independent model for different length ranges of RNAs through transfer learning. 2dRNA, a coupled deep learning neural network for RNA secondary structure prediction, is used to do this. Benchmarking shows that the length-dependent model performs better than the usual length-independent model.

show abstract

Inference of RNA structural contacts by direct coupling analysis

Cited by 5 publications

References 0 publications

Computational prediction of RNA tertiary structures using machine learning methods*

Computational prediction of RNA tertiary structures using machine learning methods*

Improving RNA secondary structure prediction using direct coupling analysis

Length-Dependent Deep Learning Model for RNA Secondary Structure Prediction

Contact Info

Product

Resources

About