AI3SD Video: Data-driven molecular design in computational toxicology

Abstract

Timely drug discovery and toxicology approaches have seen a rise in strategies which use data as a basis for decisions at various stages. Such approaches include (automated) data integration and curation efforts, predictive machine learning approaches, as well as structure-based molecular design strategies that make use of the wealth of publicly available data sources and data types. In this talk, various computational workflows which have been developed in my lab for addressing research questions related to toxicology will be presented. In one project, ligand- and structure-based methods have been combined in an effective data-driven manner to decipher the molecular basis of ligand recognition and selectivity for hepatic Organic Anion Transporting Polypeptides (OATPs). In the framework of this successful project, novel highly potent inhibitors of these SLC uptake transporters have been identified by an AI-driven virtual screening approach. At the other end of the spectrum, we are using target-agnostic information if the underlying mechanism of toxicity is insufficiently understood. Such approaches allow to leverage in vivo data for building predictive machine learning models but they also make the incorporation of in vitro bioactivity data possible. Another example will illustrate how data integration strategies can be used to consolidate Adverse Outcome Pathway (AOP) hypotheses, which are effective tools in toxicology and risk assessment to capture mechanistic knowledge of critical toxicological effects that span over different layers of biological organization.

More information

Identifiers

ORCID for Jeremy G. Frey: orcid.org/0000-0003-0842-4302

ORCID for Samantha Kanza: orcid.org/0000-0002-4831-9489

ORCID for Mahesan Niranjan: orcid.org/0000-0001-7021-140X

Catalogue record

Export record

Altmetrics