Novel feature selection, scalable feature extraction, and clustering algorithms for plant genome sequences

Abstract

Feature selection, extraction, and clustering techniques play crucial roles in various fields such as healthcare, bioinformatics, finance, and environment monitoring etc. Despite their potential to address significant issues like the time-consuming nature of alignment-based methodologies, their application in plant genomics remains limited. To overcome these challenges, researchers are delving into machine learning and parallel computing techniques. Clustering emerges as a promising approach, aiding in organizing and categorizing genomic sequences to uncover patterns and functional elements. However, the large-scale and high-dimensional nature of data in plant genomics complicates the clustering process and reduces accuracy.