RNA secondary structure prediction – revisiting an old problem from new perspectives

Abstract

RNAs need to form specific secondary structures for their functions. RNA secondary structure prediction is among the early problems being tackled in bioinformatics, yet far from being solved. The dominant dynamic programming-based methods cannot handle pseudoknots, which are present in about 40% of RNAs, whereas heuristic methods and recent deep learning methods still do not have satisfactory performance. 

In this talk, I will introduce our two recent works, NNfold and E2Efold, both of which are deep learning-based methods for RNA secondary structure prediction. NNfold predicts the pairing potential for each individual base, as well as for each pair of bases, based on which it assigns the final pairing prediction. E2Efold is an end-to-end method that learns a scoring network together with a post-processing network, which is designed based on an unrolled algorithm for solving a constraint optimization problem. Both methods show superior performance over the state-of-the-art RNA secondary structure prediction methods.

Brief Biography

Dr. Xin Gao is a professor of computer science in CEMSE Division at KAUST. He is also the Acting Associate Director of the Computational Bioscience Research Center (CBRC), Deputy Director of the Smart Health Initiative (SHI), and the Lead of the Structural and Functional Bioinformatics (SFB) Group at KAUST. Prior to joining KAUST, he was a Lane Fellow at Lane Center for Computational Biology in School of Computer Science at Carnegie Mellon University. He earned his bachelor degree in Computer Science in 2004 from Tsinghua University and his Ph.D. degree in Computer Science in 2009 from University of Waterloo. 
Dr. Gao’s research interest lies at the intersection between computer science and biology. In the field of computer science, he is interested in developing machine learning theories and methodologies related to deep learning, probabilistic graphical models, kernel methods and matrix factorization. In the field of bioinformatics, his group works on building computational models, developing machine learning techniques, and designing efficient and effective algorithms to tackle key open problems along the path from biological sequence analysis, to 3D structure determination, to function annotation, to understanding and controlling molecular behaviors in complex biological networks, and, recently, to biomedicine and healthcare. 
He has published more than 240 papers in the fields of bioinformatics and machine learning. He is the associate editor of Genomics, Proteomics & Bioinformatics, BMC Bioinformatics, Journal of Bioinformatics and Computational Biology, and Quantitative Biology, and the guest editor-in-chief of IEEE/ACM Transactions on Computational Biology and Bioinformatics, Methods, and Frontiers in Molecular Bioscience.