PCA Model For RNA-Seq Malaria Vector Data Classification Using KNN And Decision Tree Algorithm

Malaria parasites adopt unresolved discrepancy of life segments as they grow through various mosquito vector stratospheres. Transcriptomes of thousands of individual parasites exists. Ribonucleic acid sequencing (RNA-seq) is a widespread method for gene expression which has resulted into improved understandings of genetical queries. RNA-seq compute transcripts of gene expressions. RNA-seq data necessitates analytical improvements of machine learning techniques. Several learning approached have been proposed by researchers for analyzing biological data. In this study, PCA feature extraction algorithm is used to fetch latent components out of a high dimensional malaria vector RNA-seq dataset, and evaluates it classification performance using KNN and Decision Tree classification algorithms. The effectiveness of this experiment is validated on a mosquito anopheles gambiae RNA-Seq dataset. The experiment result achieved a relevant performance metrics with a classification accuracy of 86.7% and 83.3% respectively.