Show simple item record

dc.contributor.advisorPerkins, Andy D.en_US
dc.contributor.authorThrash, Charles Adamen_US
dc.date.accessioned2019-07-15T16:24:57Zen_US
dc.date.available2019-07-15T16:24:57Zen_US
dc.date.issued2019
dc.identifier.urihttps://hdl.handle.net/11668/14514en_US
dc.description.abstractA key use of high throughput sequencing technology is the sequencing and assembly of full genome sequences. These genome assemblies are commonly assessed using statistics relating to contiguity of the assembly. Measures of contiguity are not strongly correlated with information about the biological completion or correctness of the assembly, and a commonly reported metric, N50, can be misleading. Over the past ten years, multiple research groups have rejected the overuse of N50 and sought to develop more informative metrics. This research seeks to create a ranking method that includes biologically relevant information about the genome, such as completeness and correctness of the genome. Approximately eight hundred genomes were initially selected, and information about their completeness, contiguity, and correctness was gathered using publicly available tools. Using this information, these genomes were scored by subject matter experts. This rating system was explored using supervised machine learning techniques. A number of classifiers and regressors were tested using cross validation. Two metrics were explored in this research. First, a metric that describes the distance to the ideal genome was created as a way to explore the incorporation of human subject matter expert knowledge into the genome assembly assessment process. Second, random forest regression was found to be the method of supervised learning with the highest scores. A model created by an optimized random forest regressor was saved, and a tool was created to load the saved model and rank genomes provided by the end user. These metrics both serve as ways to incorporate human subject matter expert knowledge into genome assembly assessment.en_US
dc.description.sponsorshipThis work was supported in part by Mississippi State University's tuition remission program for employees of the University and in part through USDA Agricultural Research Service Agreements 58-6066-6-046 and 58-6066-6-059 and USDA National Institute of Food and Agriculture Multi-State Hatch project 17810.en_US
dc.language.isoen_USen_US
dc.publisherMississippi State Universityen_US
dc.subjectgenome assemblyen_US
dc.subjectquality assessmenten_US
dc.subjectmachine learningen_US
dc.titleA Machine Learning Approach to Genome Assessmenten_US
dc.typeDissertationen_US
dc.publisher.departmentDepartment of Computer Science and Engineeringen_US
dc.publisher.collegeJames Worth Bagley College of Engineeringen_US
dc.publisher.researchcenterInstitute for Genomics, Biocomputing & Biotechnologyen_US
dc.publisher.officeOffice of the Graduate Schoolen_US
dc.source.institutionMississippi State Universityen_US
dc.subject.degreeDoctor of Philosophyen_US
dc.subject.majorComputer Scienceen_US
dc.contributor.committeeHoffmann, Federico G.en_US
dc.contributor.committeeArchibald, Christopheren_US
dc.contributor.committeeIannucci, Stefanoen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record