New AI software could accelerate drug development

New AI software could accelerate drug development

Drug discovery and development in pharmacological research - including risk assessment of active substances in the early phase of drug development - still relies largely on animal experiments. In addition to the ethical issues, animal studies are very expensive and time-consuming. They also typically require ongoing supervision and evaluation by highly qualified staff. The development of automated assessment methods that can be used instead of standard animal testing would thus have a wide range of benefits for drug discovery.

The pursuit of these alternative methods is the focus of the “Embryonet-AI” project, for which Patrick Müller has just been awarded a Proof of Concept grant from the European Research Council (ERC) worth 150,000 euros. Müller is a professor of developmental biology at the University of Konstanz and a member of the Konstanz Cluster of Excellence - Collective Behavior. His project builds on insights he and his team gained in the ERC-funded Ace-of-Space project (“Analysis, Control and Engineering of Spatiotemporal Pattern Formation”). The goal of Müller's new project is to further develop the AI-assisted image analysis software Embryonet, which automatically detects defects that arise during the development of animal embryos.

Embryonet offers a fast, cost-effective and highly accurate assessment of the influence of a substance on the development of biological systems. Negative effects such as visible developmental defects are automatically recognized and linked to the corresponding signaling pathway. Embryonet even surpasses human experts in accuracy. “We see great potential for applying the software to drug development, especially in the early phase of identifying potentially suitable substances – for carrying out risk assessments and studying the mechanisms of how fluctuated drugs work,” says Müller.

Not just for embryos

Patrick Müller and his team first presented Embryonet in a 2023 study using zebrafish embryos published in the journal Nature Methods. The software has since been expanded to include organoids. "Organoids are artificial tissues that are produced in a laboratory using human stem cells. Their structures resemble small organs such as the liver, kidney or brain - and can be used as models for these organs in drug research," explains Müller.

As part of the Proof of Concept Grant, Müller and his team will further improve the AI ​​models on which Embryonet is based in order to increase its accuracy and, above all, its functions. At the same time, the team wants to create an online platform to make Embryonet available to users worldwide. To achieve this goal, Müller and his team will work hand in hand with other researchers, industry partners and key regulators to ensure that the online platform meets the needs of its future users and meets regulatory requirements. The overall goal is to develop Embryonet into a market-ready product.

The idea: Because Embryonet is fully automated, pharmaceutical companies could fully integrate the platform into their research pipelines. For example, you could use Embryonet to simultaneously test hundreds of substances in a high-throughput process for their effects on or risks to specific organs or developmental processes - without completing long studies with large numbers of test animals for each individual substance. Embryonet also provides information about the mechanisms of how potential new drugs work. “In the long term, Embryonet could then replace a large number of animal experiments in drug research and accelerate conventional processes through automation while significantly reducing costs,” concludes Patrick Müller.

Sources: