ICA LEARNING APPROACH FOR PREDICTING OF RNA-SEQ MALARIA VECTOR DATA CLASSIFICATION USING SVM KERNEL ALGORITHMS

Parasites of malaria follow vague difference in sections in life as they expand across various stratospheres of mosquito vectors. There are transcriptomes of several thousand human parasites. Ribonucleic acid sequencing (RNA-Seq) is a prevalent gene expression technique haven led to a better understanding of genetic requests. RNA-Seq measures gene expression transcripts. Data from the RNA-Seq require methodological developments in machine learning techniques. Scientists have suggested many addressed learning for the study of biological evidence. Independent Component Analysis (ICA) algorithm is utilized in this analysis to collect latent components from a high-dimensional RNA-Seq malaria vector dataset and analyse its classification output utilizing classification algorithms for Support Vector Machine (SVM) Kernel. The effectiveness of this assay is tested on an RNA-Seq sample of mosquito Anopheles gambiae. The findings of the analysis hit important performance thresholds with a classification accuracy of 92% and 87% individually.