Full metadata record
DC FieldValueLanguage
dc.contributor.authorVillalobos, Rodney V.-
dc.description.abstractFaced with uncertain data and an unpredictable return on computational tool investment, researchers are opting for laboratory studies over in silico (computer based) studies. This study addressed the lack of efficiency in identifying motifs (biologically significant amino sequences) in deoxyribonucleic acid (DNA) sequences via naive Bayesian text classification. DNA is a nucleic acid that carries genetic information in cells. A naive Bayesian text classifier is a machine-learning tool that uses automated means of determining metadata and has been used to identify e-mail worms, viruses, and spam. This quantitative study utilized a naive Bayesian text classification algorithm as the primary data collection technique. The data were analyzed using the independent t test and the chi-square goodness of fit test to address the research questions. Based on the tests conducted, naive Bayesian text classification is not effective in identifying and classifying motifs. The results do suggest that secondary and tertiary motifs can be found in DNA sequences using machine learning. Given these 2 conclusions, the study adds to the area of research by furthering ways to help researchers handle large amounts of data that may point to more effective drugs, faster development of these drugs to the marketplace, and improvement to the care and cure of diseases.
dc.publisherWalden University
dc.relation.ispartofseriesDoctor of Philosophy
dc.titleIdentification of secondary and tertiary motifs in DNA sequences through naive Bayesian text classification
Appears in Collections
CL – ProQuest

  • 3247593.PDF
    • Size : 321,31 kB

    • Format : Adobe PDF

    • Views : 
    • Downloads :