RNA Secondary Structure Prediction Using Neural Machine Translation Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_projects/pv63g4248

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • RNA secondary structure prediction maps a RNA sequence to its secondary structure (set of AU, CG, and GU pairs). It is an important problem in computational biology be-cause such structures reveals crucial information about the RNAs function, which is useful in many applications ranging from noncoding RNA detection to folding dynamics simulation. Traditionally, RNA structure prediction is often accomplished computationally by the cubic-time CKY parsing algorithm borrowed from computational linguistics, with the energy parameters either estimated physically or learned from data. With the advent of deep learning, we propose a brand-new way of looking at this problem, and cast it as a machine translation problem where the RNA sequence is the source language and the dot-parenthesis structure is the target language. Using a state-of-the-art open source neural machine translation package, we are able to build an RNA structure predictor without any hand-designed features.
License
Resource Type
Date Available
Date Copyright
Date Issued
Advisor
Committee Member
Keyword
Rights Statement
Language
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Steven Van Tuyl(steve.vantuyl@oregonstate.edu) on 2016-09-16T22:15:33Z (GMT) No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) ZhangLuyao2016.pdf: 1589424 bytes, checksum: 9ee994df0c8c5496d9028e675abc5b29 (MD5)
  • description.provenance : Submitted by Luyao Zhang (zhangluy@oregonstate.edu) on 2016-09-13T04:10:14Z No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) ZhangLuyao2016.pdf: 1589424 bytes, checksum: 9ee994df0c8c5496d9028e675abc5b29 (MD5)
  • description.provenance : Made available in DSpace on 2016-09-16T22:15:34Z (GMT). No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) ZhangLuyao2016.pdf: 1589424 bytes, checksum: 9ee994df0c8c5496d9028e675abc5b29 (MD5) Previous issue date: 2016-08-30

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items