Traditional drug testing methods rely heavily on animal models, which are time-consuming, expensive, and ethically problematic. EmbryoNet-AI, on the other hand, offers a faster, more accurate, and more comprehensive solution for assessing the effects of substances on biological development, thereby improving the efficiency of early-stage drug development.

The EmbryoNet AI platform aims to improve the detection of drug effects and toxicities in fish embryos, but also in organoids. Phenotypic analyses are automated using contemporary deep learning. This platform enables faster, more accurate assessment of effects and reduces dependence on animal models.

EmbryoNet has already successfully identified new active substances, elucidated their mechanisms of action, and thus provided valuable insights for therapeutic development. The project is funded by the European Research Council. Prof. Müller is also co-founder of the corresponding start-up EmbryoNet AI Technologies, which was awarded the Start-up Prize by the German Federal Ministry for Economic Affairs and Climate Action in March this year.

Sources and further information:
https://embryonet.de/
https://www.biologie.uni-konstanz.de/mueller/patrick-mueller/
https://www.uni-konstanz.de/universitaet/aktuelles-und-medien/aktuelle-meldungen/aktuelles-1/bmwk-gruendungspreis-fuer-embryonet-ai-technologies/
https://cordis.europa.eu/project/id/101213895
https://www.gesundheitsindustrie-bw.de/fachbeitrag/aktuell/embryonet-ai-identifiziert-selbststaendig-entwicklungsstoerungen

Čapek, D., Safroshkin, M., Morales-Navarrete, H. et al. EmbryoNet: using deep learning to link embryonic phenotypes to signaling pathways. Nat Methods 20, 815–823 (2023).
https://doi.org/10.1038/s41592-023-01873-4