REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network
Abstract Background As the RNA secondary structure is highly related to its stability and functions, the structure prediction is of great value to biological research. The traditional computational prediction for RNA secondary prediction is mainly based on the thermodynamic model with dynamic progra...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-03-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-023-05238-8 |
| _version_ | 1797853512234696704 |
|---|---|
| author | Chun-Chi Chen Yi-Ming Chan |
| author_facet | Chun-Chi Chen Yi-Ming Chan |
| author_sort | Chun-Chi Chen |
| collection | DOAJ |
| description | Abstract Background As the RNA secondary structure is highly related to its stability and functions, the structure prediction is of great value to biological research. The traditional computational prediction for RNA secondary prediction is mainly based on the thermodynamic model with dynamic programming to find the optimal structure. However, the prediction performance based on the traditional approach is unsatisfactory for further research. Besides, the computational complexity of the structure prediction using dynamic programming is $$O(N^3)$$ O ( N 3 ) ; it becomes $$O(N^6)$$ O ( N 6 ) for RNA structure with pseudoknots, which is computationally impractical for large-scale analysis. Results In this paper, we propose REDfold, a novel deep learning-based method for RNA secondary prediction. REDfold utilizes an encoder-decoder network based on CNN to learn the short and long range dependencies among the RNA sequence, and the network is further integrated with symmetric skip connections to efficiently propagate activation information across layers. Moreover, the network output is post-processed with constrained optimization to yield favorable predictions even for RNAs with pseudoknots. Experimental results based on the ncRNA database demonstrate that REDfold achieves better performance in terms of efficiency and accuracy, outperforming the contemporary state-of-the-art methods. |
| first_indexed | 2024-04-09T19:51:49Z |
| format | Article |
| id | doaj.art-5538fc82f5494ef6bd3f38b92633a876 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-09T19:51:49Z |
| publishDate | 2023-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-5538fc82f5494ef6bd3f38b92633a8762023-04-03T05:42:37ZengBMCBMC Bioinformatics1471-21052023-03-0124111310.1186/s12859-023-05238-8REDfold: accurate RNA secondary structure prediction using residual encoder-decoder networkChun-Chi Chen0Yi-Ming Chan1Department of Electrical Engineering, National Chiayi UniversityMindtronicAI Co., Ltd.Abstract Background As the RNA secondary structure is highly related to its stability and functions, the structure prediction is of great value to biological research. The traditional computational prediction for RNA secondary prediction is mainly based on the thermodynamic model with dynamic programming to find the optimal structure. However, the prediction performance based on the traditional approach is unsatisfactory for further research. Besides, the computational complexity of the structure prediction using dynamic programming is $$O(N^3)$$ O ( N 3 ) ; it becomes $$O(N^6)$$ O ( N 6 ) for RNA structure with pseudoknots, which is computationally impractical for large-scale analysis. Results In this paper, we propose REDfold, a novel deep learning-based method for RNA secondary prediction. REDfold utilizes an encoder-decoder network based on CNN to learn the short and long range dependencies among the RNA sequence, and the network is further integrated with symmetric skip connections to efficiently propagate activation information across layers. Moreover, the network output is post-processed with constrained optimization to yield favorable predictions even for RNAs with pseudoknots. Experimental results based on the ncRNA database demonstrate that REDfold achieves better performance in terms of efficiency and accuracy, outperforming the contemporary state-of-the-art methods.https://doi.org/10.1186/s12859-023-05238-8RNA secondary structureDeep learningPseudoknot structureEncoder-decoder network |
| spellingShingle | Chun-Chi Chen Yi-Ming Chan REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network BMC Bioinformatics RNA secondary structure Deep learning Pseudoknot structure Encoder-decoder network |
| title | REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network |
| title_full | REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network |
| title_fullStr | REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network |
| title_full_unstemmed | REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network |
| title_short | REDfold: accurate RNA secondary structure prediction using residual encoder-decoder network |
| title_sort | redfold accurate rna secondary structure prediction using residual encoder decoder network |
| topic | RNA secondary structure Deep learning Pseudoknot structure Encoder-decoder network |
| url | https://doi.org/10.1186/s12859-023-05238-8 |
| work_keys_str_mv | AT chunchichen redfoldaccuraternasecondarystructurepredictionusingresidualencoderdecodernetwork AT yimingchan redfoldaccuraternasecondarystructurepredictionusingresidualencoderdecodernetwork |