OWOLABI, JESUJOBA MARY (2021) PREDICTION OF INSECTICIDE RESISTANT GENES IN ANOPHELES GAMBIAE USING A SEMI-SUPERVISED MACHINE LEARNING APPROACH. Masters thesis, Covenant University Ota..
![[img]](http://eprints.covenantuniversity.edu.ng/style/images/fileicons/application_pdf.png) |
PDF
Download (430kB) |
Abstract
Insecticides are used to manage insects that harm crops, livestock, and humans, as well as to eliminate pests that spread harmful infectious diseases. However, widespread use of insecticides, especially pesticides, has resulted in the reappearance of pest species that are totally resistant to more than two types of prescribed insecticides, resulting in an increase in global mortality rates. Insecticide resistance is defined as a heritable alteration in a pest population's sensitivity to insecticides, as evidenced by a repeated failure to achieve the expected degree of control when applied according to the level of recommended dosage. Experimental approaches have been extensively utilized in identifying resistance among many malaria vectors including Anopheles gambiae. However, these techniques used such as expression profiling and transcriptome analyses tends to be species specific, costly and timeconsuming. Thus, computational technique for discovering resistant genes that is independent of species and cost-effective would aid in the advancement of insecticide resistance gene research. To this end, this research aims to identify other potential resistant genes with a selftrained semi-supervised approach using five probabilistic machine learning models such as Random Forest, Decision Tree, XGBoost, Gradient Boosting Machine and Logistic Regression. A total of 63 insecticide resistant genes were predicted across five models based on a consensus based voting scheme. With highly significant predictions, new insecticides can be formulated to counteract the activities of this predicted genes as functional analysis has shown their relationship to the already identified experimentally validated genes.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Anopheles gambiae, Insecticide resistance, self-training, semi-supervised learning, biological interpretation |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | Mrs Patricia Nwokealisi |
| Date Deposited: | 17 May 2022 11:55 |
| Last Modified: | 17 May 2022 11:55 |
| URI: | http://eprints.covenantuniversity.edu.ng/id/eprint/15843 |
Actions (login required)
 |
View Item |
