Adjustment of p-value expression to ontology using machine learning for genetic prediction, prioritization, interaction, and its validation in glomerular disease

Boutaina Ettetuani; Rajaa Chahboune; Ahmed Moussa

doi:10.3389/fgene.2023.1215232

Adjustment of p-value expression to ontology using machine learning for genetic prediction, prioritization, interaction, and its validation in glomerular disease

Front Genet. 2023 Oct 12:14:1215232. doi: 10.3389/fgene.2023.1215232. eCollection 2023.

Authors

Boutaina Ettetuani¹, Rajaa Chahboune², Ahmed Moussa¹

Affiliations

¹ Systems and Data Engineering Team, National School of Applied Sciences, Abdelmalek Essaadi University, Tétouan, Morocco.
² Life and Health Sciences Team, Faculty of Medicine and Pharmacy, Abdelmalek Essaadi University, Tétouan, Morocco.

Abstract

The results of gene expression analysis based on p-value can be extracted and sorted by their absolute statistical significance and then applied to multiple similarity scores of their gene ontology (GO) terms to promote the combination and adjustment of these scores as essential predictive tasks for understanding biological/clinical pathways. The latter allows the possibility to assess whether certain aspects of gene function may be associated with other varieties of genes, to evaluate regulation, and to link them into networks that prioritize candidate genes for classification by applying machine learning techniques. We then detect significant genetic interactions based on our algorithm to validate the results. Finally, based on specifically selected tissues according to their normalized gene expression and frequencies of occurrence from their different biological and clinical inputs, a reported classification of genes under the subject category has validated the abstract (glomerular diseases) as a case study.

Keywords: ETL; gene expression; gene ontology; glomerular diseases; machine learning.