Stay in touch
Prime news from our network.
Stay in touch
Prime news from our network.
The study, which was conducted in collaboration with Vanderbilt University (USA) and published in Science Advances, shows that AI models are particularly good at suggesting sequences, but often struggle to accurately predict the effects of individual amino acid changes. „Our research helps to use AI methods more specifically and effectively in protein design“, explains Prof Dr Clara Schoeder from the Institute of Drug Discovery. The researchers are using the established Rosetta software, which makes it possible to combine various AI models with classic biophysical methods. In the long term, this should lead to better standards in computer-aided drug development. The research groups led by Prof. Dr Jens Meiler and Prof. Dr Schoeder are now working on further optimising the algorithms in order to identify reliable vaccine candidates.
Press release from "Universitätsklinikum Leipzig" from 14 February 2025
The above texts, or parts thereof, were automatically translated from the original language text using a translation system (DeepL API).
Despite careful machine processing, translation errors cannot be ruled out.