Show simple item record

dc.contributor.authorZhang, Christine
dc.date.accessioned2019-03-26T11:07:40Z
dc.date.created2018-05
dc.date.issued2018-06-29
dc.date.submitted2018
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:38811524*
dc.description.abstractThe goal of this project was to build a predictive model that could correlate genetic features to radiation sensitivity in cancer cell lines. This would ultimately work to-ward the creation of personalized medicine for cancer patients to help them make more informed decisions while convalescing. The project focused on the incorporation of biological domain knowledge including using tSNE dimensionality reduction and stratification to explore the addition of site histology. Furthermore, we collaborated with cancer biology experts on the curation of biologically informed datasets focused on apoptosis and cell division regulation. Modern machine learning models were tested with random forest outperforming and tuned using Monte-Carlo cross validation. These results were summarized in the creation of an API to handle the machine learning analysis and facilitate further research into personalized medicine development.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dash.licenseLAA
dc.subjectComputer Science
dc.subjectBiology, General
dc.titleSelf-Prescribed Prescriptions: Personalized Radiation Treatment Using Genomic Biomarkers
dc.typeThesis or Dissertation
dash.depositing.authorZhang, Christine
dc.date.available2019-03-26T11:07:40Z
thesis.degree.date2018
thesis.degree.grantorHarvard College
thesis.degree.levelUndergraduate
thesis.degree.nameAB
dc.type.materialtext
dash.identifier.vireohttp://etds.lib.harvard.edu/college/admin/view/250
dash.author.emailchristinehzhang@gmail.com


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record