Host: The Japanese Society of Toxicology
Name : The 49th Annual Meeting of the Japanese Society of Toxicology
Date : June 30, 2022 - July 02, 2022
With a recent advancement of high-throughput experimental technologies, large-scale and multidimensional omics data are now available. Especially, transcriptomics data under administration of compounds as well as large-scale molecular interaction networks are useful resources for system toxicology and drug discovery. AI, especially deep learning based analysis tools, are keys to automatically extract biologically meaningful information embedded in complex omics data, especially those associated with toxicological mechanisms. In this presentation, we are planning to present our AI-driven analysis methods for omics data, especially those based on deep learning technologies, and their applications to system toxicology and drug discovery (and discuss future technical challenges), including (i) deep convolutional neural network based method analyze Percellome data to classifies genes activate/suppressed by administration of compounds and (ii) a deep autoencoder based computational pipeline to analyze a large-scale protein interaction network to prioritize potential drug target genes [1].
Reference:
[1] Tsuji S, Hase T, Yachie-Kinoshita A, et al. Artificial intelligence-based computational framework for drug-target prioritization and inference of novel repositionable drugs for Alzheimer's disease. Alzheimers Res Ther. 2021 13:92.
