Events Calendar

PhD Final Exam – Dezhong Deng

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

Our goal is to build a system to model the RNA sequences that reveal the structural information (Stem-Loops, Secondary Structures) 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 in datasets, without looking at any indirect information from MFE models. We propose our line of research all the way from a novel annotated dataset to the systematic deep learning RNA secondary structure prediction approach. Benefit from bpRNA, a large-scale RNA dataset with rich structural information we proposed, we firstly present DeepSloop, which uses deep learning architecture to predict RNA stem-loops and reveal biological information like structure destabilization from nucleotide insertion and mutation from deep neural networks, showing the feasibility of deep neural networks on RNA structure prediction. Based on this, we propose DeepStructure, a deep learning approach to predict secondary structure from RNA sequences combining dynamic programming algorithm and deep neural network features directly learned from our dataset. As an alternative, we also present LinearFold, a linear-time RNA secondary structure prediction algorithm utilizing dynamic programming and beam search for the speed-up, which favors structural prediction on long RNA sequences.

Major Advisor: David Hendrix
Committee: Prasad Tadepalli
Committee: Alan Fern
Committee: Glencora Borradaile
GCR: Leonard Coop

Tuesday, December 10, 2019 at 10:00am to 12:00pm

Kelley Engineering Center, 1007
110 SW Park Terrace, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic


Electrical Engineering and Computer Science
Contact Name

Calvin Hughes

Contact Email

Google Calendar iCal Outlook

Recent Activity