RNA Secondary Structure Prediction Based on Long Short-Term Memory Model
RNA secondary structure prediction is an important issue in structural bioinformatics. The difficulty of RNA secondary structure prediction with pseudoknot is increased due to complex structure of the pseudoknot. Traditional machine learning methods, such as support vector machine, markov model and neural network, have been tried and their prediction accuracy are also increasing. The RNA secondary structure prediction problem is transferred into the classification problem of base in the sequence to reduce computational complexity to a certain extent. A model based on LSTM deep recurrent neural network is proposed for RNA secondary structure prediction. Subsequently, comparative experiments were conducted on the authoritative data set RNA STRAND containing 1488 RNA sequences with pseudoknot. The experimental results show that the SEN and PPV of this method are higher than the other two typical methods by 1% and 11%.
KeywordsRNA secondary structure prediction Recurrent neural network Pseudoknots Classification
This paper is supported by the National Natural Science Foundation of China (61772357, 61502329, 61672371), Jiangsu 333 talent project and top six talent peak project (DZXX-010), Suzhou Foresight Research Project (SYG201704, SNG201610) and Postgraduate Research & Practice Innovation Program of Jiangsu Province (SJCX17_0680).
- 2.Dong, H., Liu, Y.N.: A new method for RNA secondary structure prediction based on hidden markov model. J. Comput. Res. Dev. 49(4), 812–817 (2012)Google Scholar
- 7.Wu, H.J., Lv, Q., Wu, J.Z., et al.: A parallel ant colony method to predict protein skeleton and its application in CASP8/9. Scientia Sinica Informationis 42(8), 1034–1048 (2012)Google Scholar
- 8.Mathews, D.H., Turner, D.H., Watson, R.M.: RNA secondary structure prediction. BMC Bioinform. 11(1), 129 (2007)Google Scholar
- 9.Mathews, D.H., Turner, D.H., Watson, R.M.: RNA secondary structure prediction. In: Current Protocols in Nucleic Acid Chemistry, pp. 345–363. Wiley, Hoboken (2016)Google Scholar
- 11.Mathuriya, A., Bader, D.A., Heitsch, C.E., et al.: GTfold: a scalable multicore code for RNA secondary structure prediction. In: ACM Symposium on Applied Computing, pp. 981–988. ACM (2009)Google Scholar
- 13.Wu, H.J., Wang, K., Lu, L.Y., et al.: A deep conditional random field approach to transmembrane topology prediction and application to GPCR three-dimensional structure modeling. IEEE/ACM Trans. Comput. Biol. Bioinform. PP(99), 1 (2016)Google Scholar
- 14.Wu, H.J., Cao, C.Y., Xia, X.Y., et al.: Unified deep learning architecture for modeling biology sequence. IEEE/ACM Trans. Comput. Biol. Bioinform. PP(99), 1 (2017)Google Scholar