Gerhard Ecker is Professor of Pharmacoinformatics and Head of the Pharmacoinformatics Research Group at the Department of Pharmaceutical Sciences, University of Vienna. Gerhard received his doctorate in natural sciences from the University of Vienna and performed his post-doctoral training at the group of J. Seydel in Borstel (Germany). His research focuses on computational drug design with special emphasis on drug-transporter interaction and in silico safety assessment. He participated in 5 EU-funded projects related to toxicology and coordinated the Open PHACTS project, which created an Open Pharmacological Space by semantic integration of public databases. His recent contributions focus on the application of deep learning and AI for target profiling and prediction of drug-drug interactions. Gerhard served 2009 – 2011 as President of the European Federation for Medicinal Chemistry, and from 2018 – 2022 as Dean at the Faculty of Life Sciences.
OpenTox Summer School 2026
In silico Hazard Assessment – from Target Prediction to QSAR and Deep Learning
Hazard assessment usually starts with a chemical structure with little or no biological data avilable. In this case, in silico target prediction allows to derive a first list of potential interactors. If for these proteins a substantial amount of biological data is available, machine learning models such as QSAR are widely used to quantify biological activity. While traditional QSAR models rely mainly on 2D chemical structures and are typically developed for single targets, structure-based methods such as molecular docking and molecular dynamics simulations provide mechanistic insight into compound-target interactions in 3D space. Furthermore, large public data sources such as ToxCAST and ChEMBL allow to apply deep learning approaches, such as our multitask deep neural network for simultaneous prediction of 78 off-targets. However, many current approaches still neglect the broader biological context. Therefore, we developed models for prediction of hepatotoxicity incorporating compound-target and compound-pathway fingerprints. This both improved predictive performance and allowed the identification of novel potential molecular initiating events, thereby supporting mechanism-based toxicity prediction within the 3R framework.