Bioinformatics analysis for the identification of Differentially Expressed Genes in Alzheimer’s disease and development of Machine Learning models for data interpretation

Alzheimer’s disease (AD) is a multifactorial neurodegenerative disease characterized by complex molecular mechanisms. The advent of Next Generation Sequencing (NGS) techniques, the refinement of bioinformatics analysis, and the use of predictive tools such as machine learning (ML) are collaborating to shed light on the complex molecular processes underlying the development of this pathology. In this context, a pipeline has been developed for identifying genes differentially expressed between individuals with AD and healthy controls using transcriptomic data stored in the AD Knowledge Portal and obtained through RNA-seq technology. The genes identified as differentially expressed were subsequently subjected to Gene Ontology (GO) enrichment analysis and pathway analysis to identify significant alterations in specific biological processes and molecular functions. Machine learning currently represents one of the most promising tools for extracting relevant information and recognizing patterns in biologically significant data. This study employed various machine learning models with the goal of predicting the AD phenotype based on the count of reads on the genes, highlighting the strengths and limitations of using machine learning in the handling of biological data