Cheminformatics

Alex Wiltschko explains efforts to predict smell from molecular structure and to give computers a useful representation of odors. He discusses graph neural networks, the difficulty of collecting olfactory data, and how learned embeddings connect chemistry to perception and potential practical applications.

EMBL-EBI seeks a scientific developer for the Open Targets Safety 2.0 project. The role builds machine-learning and data-processing pipelines that extract drug side-effect evidence from publications, clinical trials and drug labels, map it to biomedical ontologies, and integrate results with ChEMBL and the Open Targets Platform. The researcher will help curate training data, collaborate with pharmaceutical partners and communicate methods and results. This is a full-time hybrid role based in Hinxton, UK. The advert gives a closing date of 11 October 2026 at 23:59 CET.

This webinar uses research on Chagas disease to explain how predicted protein structures can support drug discovery when experimental structures are unavailable. In the example study, AlphaFold models of Trypanosoma cruzi proteins supported a virtual screen of roughly 30,000 compounds; subsequent experiments identified antiparasitic activity in two approved drugs. The session introduces AlphaFold confidence measures and ways to obtain models, then follows a screening workflow through binding-pocket prediction, chemical-library selection, docking, and interpretation of results. It discusses difficulties encountered when docking against predicted structures and considerations for adapting the workflow to other targets. The material is intended for doctoral students, early-career researchers, and other drug-discovery professionals.

Lead computational chemistry contributions to drug programmes from early discovery towards candidate selection. Combine structure-based and ligand-based design with AI predictions, work closely with machine-learning scientists and experimental teams, and guide external research activities. The role includes scientific leadership and mentoring. The employer’s exact vacancy is currently accepting applications without a stated fixed deadline.

Build machine-learning and computational-chemistry software supporting molecular property prediction, virtual screening, reaction optimisation and drug design. Work spans production pipelines and methods such as molecular dynamics, docking, free-energy calculations and retrosynthesis, in collaboration with discovery scientists. The advertised salary range is USD 200,000–241,500. Applications are currently available; no fixed deadline is stated.

Alex Wiltschko explains efforts to predict smell from molecular structure and to give computers a useful representation of odors. He discusses graph neural networks, the difficulty of collecting olfactory data, and how learned embeddings connect chemistry to perception and potential practical applications.