Skip to main content
Logo of Goethe university

AI in Drug Discovery: Goethe University is Part of the International Open Science Initiative LIGAND-AI

International research initiative generates open-source data on ligand binding to proteins, laying the foundation for AI-supported drug discovery

High-throughput analysis: A pipetting robot prepares samples for protein analysis in a pharmaceutical laboratory at Goethe University.

High-throughput analysis: A pipetting robot prepares samples for protein analysis in a pharmaceutical laboratory at Goethe University.

Uwe Dettmar

Artificial intelligence could significantly improve drug discovery – but there is a lack of publicly available data for training AI models. The international consortium LIGAND-AI, with partners from science and industry, will generate large-scale, high-quality, publicly accessible data describing how small molecules interact with human proteins. This data will then be used to develop and train AI models in drug discovery. The Innovative Health Initiative is funding LIGAND-AI with more than £55 million. Goethe University is leading the medical chemistry part of the project.

FRANKFURT. The early phase of drug discovery is a lengthy and costly process with an uncertain outcome. Particularly in the case of poorly researched target structures, identifying the first validated binding partners – also known as ‘hits’ – is often time-consuming, error-prone and difficult. The partners in the international LIGAND-AI consortium are convinced that AI models can significantly accelerate this process. Until now, however, the necessary experimental data to train such learning systems has been lacking.

The LIGAND-AI project, led by the pharmaceutical company Pfizer and the non-profit organisation Structural Genomics Consortium (SGC), aims to change this: as part of the project, thousands of interactions between small molecules and proteins relevant to various diseases, including rare neurological and oncological diseases, are being characterised. The data generated will be made available to the AI community in a publicly accessible database called AIRCHECK.

Scientists at the SGC-Frankfurt research hub at Goethe University play a central role in LIGAND-AI in generating data and lead the project's medicinal chemistry division with the aim of rapidly developing the identified binding partners into potent inhibitors.

Stefan Knapp, Professor of Pharmaceutical Chemistry at Goethe University and Chief Scientific Officer of SGC Frankfurt, is convinced: ‘By linking the data obtained from experimental observations with AI models, we are creating a powerful lever for pharmacological research. In addition, in line with our open access strategy, the database will be available to researchers worldwide.’

About LIGAND-AI: The project partners of LIGAND-AI are: Structural Genomics Consortium, European Molecular Biology Laboratory (EMBL), Goethe University Frankfurt, Universidade Estadual de Campinas, University College London, University Health Network, Vall d'Hebron Institute of Oncology (VHIO), Abcam Limited, AstraZeneca UK Limited, Chemspace LLC, Enamine Germany GmbH, IBM Research Israel – Science and Technology LTD, Novo Nordisk, Nuvisan ICB GmbH, Pfizer Inc, The Hospital for Sick Children in Toronto, Thermo Fisher Scientific GmbH and Vernalis (R&D) Limited.

LIGAND-AI is a flagship project of the Target 2035 initiative. It is supported by the Innovative Health Initiative Joint Undertaking (IHI JU) under grant agreement No. 101252959. The JU is funded by the European Union's Horizon Europe research and innovation programme, as well as by COCIR, EFPIA, EuropaBio, MedTech Europe, Vaccines Europe, Enamine and The Hospital for Sick Children. However, the views and opinions expressed are solely those of the authors and do not necessarily reflect those of the organisations mentioned. None of the parties mentioned can be held responsible for this.

Note: This text was translated using AI

Editor: Dr. Markus Bernards, Science Editor, PR & Communications Office, Theodor-W.-Adorno-Platz 1, 60323 Frankfurt, Tel: +49 (0) 69 798-12498, [email protected]

AI in Drug Discovery | Goethe University