<p>Artificial Intelligence driven approaches, especially  based on deep learning algorithms, provided an alternative perspective in summarizing the common features in large-scale and complex datasets and aided the human professions in discovering novel features in cross-domain research. In this dissertation, the author proposed his research of developing AI-driven algorithms to reveal the real relation of complex medical data. The author started to identify the abnormal structures from the radiology images. When the abnormal structure was detected, the author built a model to explore the domain layers or cell phenotype of the specific tissues. Finally, the author evaluated cell-cell communication for the downstream tasks.</p> <p><br></p> <p>In his first research, the author applied IResNet, a two-stage prediction-interpretation Convolution Neural Network, to assist clinicians in the early diagnosis of Autism Spectrum Disorders (ASD). IresNet first predicted the input sMRI scan to one of the two categories: (1) ASD group or (2) Normal Control group, and interpret the prediction using a \textit{post-hoc} approach and visualized the abnormal structures on top of the raw inputs. The proposed method can be applied to other neural diseases such as Alzheimer's Disease. </p> <p><br></p> <p>When the abnormal structure was detected, the author proposed a method to reveal the latent relation at the tissue level. Thus the author proposed SiGra, an unsupervised learning paradigm to identify the domain layers and cellular phenotype in a particular tissue slide based on the corresponding gene expression matrix and the morphology representations. SiGra outperformed other benchmarking algorithms in three different tissue slides from three commercialized single-cell platforms.</p> <p><br></p> <p>At last, the author measured the potential interactions between two cells. The proposed spaCI, measured the correlation of a Ligand-Receptor interaction in the high-dimension latent space and predicted the interactive $L-R$ pair for downstream analysis. </p> <p><br></p> <p>In summary, the author presented three end-to-end AI-driven frameworks to facilitate clinicians and pathologists in better understanding the latent connections of complex diseases and tissues. </p>

Ce projet de recherche porte sur l’étude de la régulation des systèmes cannabinoïdes et vanilloïdes chez Caenorhabditis elegans (C. elegans), dans le but d’évaluer les effets antinociceptifs du tétrahydrocannabinol (THC) et du cannabidiol (CBD). C. elegans est un modèle largement utilisé pour étudier la nociception, visant principalement à caractériser les réponses nociceptives induites par le THC et le CBD, ainsi qu’à identifier les mécanismes et les cibles moléculaires impliqués. Les résultats des études sur l’utilisation du cannabis dans le traitement de la douleur chronique chez les mammifères sont controversés. Cette recherche vise à étudier l’effet du CBD et du THC sur la réponse nociceptive chez C. elegans et à approfondir la compréhension des mécanismes pharmacologiques sous-jacents. La méthodologie consiste à quantifier l’effet antinociceptif du CBD et du THC chez C. elegans par la méthode de la thermotaxie. Les nématodes sauvages (N2) étaient exposés à des concentrations croissantes de phytocannabinoïdes pour évaluer la relation concentration-effet. D’autres tests étaient effectués sur des souches mutantes exprimant des récepteurs cannabinoïdes et vanilloïdes afin d’identifier préalablement leurs cibles. Enfin, les analyses protéomiques et bioinformatiques seront effectuées pour identifier les voies de signalisation et les processus biologiques induits par l’interaction entre les phytocannabinoïdes et leurs cibles. Cette étude démontre l’activité antinociceptive du CBD et du THC chez C. elegans avec des effets rémanents pour THC, en ciblant respectivement le vanilloïde pour le CBD et le cannabinoïde pour les systèmes THC. Les analyses protéomiques et bio-informatiques mettent en évidence des différences significatives dans leurs voies de signalisation et leurs processus biologiques. / The objective of this research project was to focus on studying the regulation of cannabinoid and vanilloid systems in Caenorhabditis elegans (C. elegans) to evaluate the anti-nociceptive effects of tetrahydrocannabinol (THC) and cannabidiol (CBD). C. elegans is a widely used model for studying nociception, with the main objective being to characterize nociceptive responses induced by THC and CBD, as well as identify the underlying molecular mechanisms and targets involved. Recent studies on the use of cannabis for the treatment of chronic pain in mammals have shown controversial results. This research aims to investigate the effect of CBD and THC on the nociceptive response in C. elegans and understand the underlying pharmacological mechanisms. The methodology consisted in quantifying the antinociceptive effect of CBD and THC in C. elegans using the thermotaxis method. WT(N2) were exposed to decreasing concentrations of phytocannabinoids to evaluate the dose and effect relationship. Further tests performed on mutant expressing cannabinoid and vanilloid receptors allowed preliminarily identification of their targets. Finally, proteomic and bioinformatics analyses were used to identify the signaling pathways and biological processes induced by these phytocannabinoids. The result of this study confirmed the antinociceptive effect of CBD and THC in C. elegans, with a remanent effect of THC. This effect is mediated by the vanilloid system for CBD and the cannabinoid system for THC, respectively. Also, proteomics and bioinformatics analyses revealed significant differences in signaling pathways and biological processes.