Show simple item record

dc.contributor.authorBeebe-Wang, Nicasia
dc.date.accessioned2019-03-26T10:57:23Z
dc.date.created2017-05
dc.date.issued2017-07-14
dc.date.submitted2017
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:38811503*
dc.description.abstractPromoters play a key role in gene regulation. Although progress has been made to understand the elements which make up a promoter, the identification of all of the regulatory elements which comprise the promoter remains challenging due to the high variability of promoter sequences. In this thesis, I aim to identify regulatory elements in promoter regions using deep learning. Specifically, I employ a convolutional neural network (CNN) to predict whether a given genomic sequence contains a promoter versus several null models, i.e. background sequences. I compare the performance of the CNN model for each null model and perform saliency analysis to visualize what the network has learned. The main result I found is that the null model must be carefully selected to avoid learning confounding signals such as nucleotide biases. I found that a dinucleotide shuffle of transcription start sites was able to find known regulatory elements associated with bi-directional promoters.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dash.licenseLAA
dc.subjectComputer Science
dc.titleTowards Learning Regulatory Elements of Promoter Sequences With Deep Learning
dc.typeThesis or Dissertation
dash.depositing.authorBeebe-Wang, Nicasia
dc.date.available2019-03-26T10:57:23Z
thesis.degree.date2017
thesis.degree.disciplineComputer Science
thesis.degree.grantorHarvard College
thesis.degree.levelUndergraduate
thesis.degree.nameAB
dc.type.materialtext
thesis.degree.departmentComputer Science
thesis.degree.discipline-jointMind Brain Behavior
dash.identifier.vireohttp://etds.lib.harvard.edu/college/admin/view/217
dc.identifier.orcid0000-0001-7031-2665
dash.author.emailnbbwang@gmail.com


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record