Graduate Thesis Or Dissertation


Computational Approaches for RNA Structure Prediction with Dynamic Programming and Deep Neural Networks Public Deposited

Downloadable Content

Download PDF


Attribute NameValues
  • Our goal is to build a system to model the RNA sequences that reveals their structural information by using efficient dynamic programming algorithms and deep learning approaches. We aim to 1) achieve linear-time for RNA secondary structure prediction based on existing minimum free energy models; 2) utilize deep neural networks to learn high-level features directly from RNA sequences without looking at any indirect information from MFE models, in order to predict RNA secondary structures directly; 3) we also investigate RNA structure visualization approaches. Here we organize our line of research all the way from a novel annotated dataset to systematic RNA secondary structure prediction using deep learning, including bpRNA (a RNA structure annotation tool with its generated, large-scale RNA meta-database bpRNA-1m), LinearFold (a linear-time dynamic programming algorithm for RNA secondary structure prediction), DeepSloop (a deep learning approach that learns complex rules to detect stem-loop-forming RNA sequences), and DeepStructure (an end-to-end RNA secondary structure prediction approach via deep neural networks). We also presented bpRNA-Visual for RNA structure visualization purposes.
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Committee Member
Academic Affiliation
Rights Statement
Peer Reviewed
Embargo reason
  • Ongoing Research
Embargo date range
  • 2019-12-13 to 2020-07-13



This work has no parents.

In Collection: