Abstract
This PhD thesis explores the transformative impact of machine learning, specifically su-pervised learning, on various fields of biology, with a focus on plant science. In the firstpart of this work, a comprehensive overview of several supervised machine learning mod-els is presented, serving as a foundational entry point into the realm of these methods.The second part delves into the applications of these models within the context of plantscience.The applications part of the thesis addresses the enigma of missing heritability. Thisphenomenon illuminated by the first GWAS pertains to unexplained phenotypic variationsthat transcend simple genomic modifications. Genetic interactions between different locihas emerged as a partial explanation. However, current GWAS statistical models sufferfrom scalability issues, high sensibility to false discovery rate (FDR). To address thesechallenges, the thesis introduces Next-Gen GWAS (NGG), a novel modeling approachcapable of evaluating over 60 billions single nucleotide polymorphisms within hours. Themethod is benchmarked against state of the art GWAS models and applied to Arabidop-sis thaliana yielding 2D epistatic maps at gene resolution. Results demonstrate NGG’sefficacy in retrieving missing heritability through epistatic interactions, thereby enhanc-ing phenotype prediction capabilities. Additionally, the thesis investigates the regulatorymechanisms that govern gene expression, with a focus on transcription factor interactions(TF). TF are known to play an important role in gene expression regulation, and theirinteractions are known to shape genomic transcriptional responses. The thesis proposesa machine learning approach using CART Trees to predict influent TF in a scRNA-seqdataset from Arabidopsis thaliana roots. This new methodology offers a robust and inter-pretable means of predicting TFs but is currently highly limited by validation data. Thegoal of this thesis is mainly to underscores the profound influence of supervised machinelearning on experimental science, showcasing its contributions to deciphering complexphenomena such as missing heritability and intricate gene regulatory mechanisms.