idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
An interdisciplinary research team from Leipzig University and the Saxon AI centre ScaDS.AI has developed a novel approach that integrates artificial intelligence (AI) methods with biophysical modelling. This innovative strategy can be applied to the development of new therapeutics, such as antibodies and vaccines, including those for pandemic preparedness. The research project, conducted in collaboration with Vanderbilt University in Nashville, US, is the result of extensive preliminary work in computer-aided drug development. The study has now been published in the journal Science Advances.
The scientists believe that the current research landscape in the field of computational protein design is akin to a gold rush, with many new methods being published without experimental validation. This often leads to inaccurate assessments of the performance of AI models. “We urgently need standards for the description and availability of such models,” says Professor Clara Schoeder, research group leader at the Institute for Drug Discovery. “Our research makes an important contribution to this goal.” The current findings show that AI methods are particularly good at suggesting sequences that do not disrupt the folding of proteins. However, they struggle when it comes to accurately assessing the effects of individual amino acid changes on folding. “Our findings make it clear that no AI model or biophysical method is ideally suited to all design problems,” explains Humboldt Professor Jens Meiler, one of the project’s lead scientists and Director of the Institute for Drug Discovery. “In the future, we will have to carefully consider which model to use for which purpose. Our work is a first step towards greater comparability between the different methods.”
The Rosetta biophysical software suite, which has been used in protein research for many years, provides a framework for integrating different AI methods. Rosetta is used by more than 100 laboratories worldwide and allows researchers to efficiently combine different approaches, such as large language models (e.g. ESM-2) and the ProteinMPNN model, with biophysical methods. This combination allows researchers to compare and analyse the different behaviours of the design approaches. “With this development, we can quickly and easily combine AI models with classical methods and use them side by side,” explains Professor Meiler. “This greatly simplifies our work and allows us to take full advantage of all the infrastructure that has been developed in Rosetta over the last 20 years.”
This does not mean that the research project is finished. The research groups led by Professor Meiler and Professor Schoeder will continue to refine and experimentally evaluate the developed algorithms, particularly with regard to vaccine design for pandemic preparedness. We are investigating which methods reliably suggest amino acid changes that could lead to vaccine candidates,” says Professor Clara Schoeder. Despite the progress made through the use of AI, the so-called scoring problem remains a challenge. This refers to the difficulty of predicting the effect of a single amino acid substitution. In collaboration with the Center for Scalable Data Analytics and Artificial Intelligence, ScaDS.AI, the research team is optimistic that the combination of AI and biophysical methods will not only increase the efficiency of protein design.
ScaDS.AI is a research centre for data science, artificial intelligence and big data with locations in Leipzig and Dresden. As one of five new AI centres in Germany, ScaDS.AI has been funded since 2019 as part of the German government’s AI strategy and is supported by the Federal Ministry of Education and Research and the Free State of Saxony.
Prof Clara T. Schoeder
E-Mail: clara.schoeder@medizin.uni-leipzig.de
Telefon:+49 341 97 - 25730
Self-supervised machine learning methods for protein design improve sampling, but not the identification of high-fitness variants, DOI 10.1126/sciadv.adr7338
https://www.science.org/doi/10.1126/sciadv.adr7338
https://www.uniklinikum-leipzig.de/einrichtungen/pharmazie/en
https://scads.ai/
Prof Clara T. Schoeder heads a working group in the current research project.
Anton Stolle
Universität Leipzig
Humboldt Professor Dr Jens Meiler conducts research at Leipzig University and at Vanderbilt Universi ...
Christian Hüller
Universität Leipzig
Merkmale dieser Pressemitteilung:
Journalisten, Studierende, Wissenschaftler
Ernährung / Gesundheit / Pflege, Medizin, Wirtschaft
überregional
Forschungsergebnisse, Forschungsprojekte
Englisch
Prof Clara T. Schoeder heads a working group in the current research project.
Anton Stolle
Universität Leipzig
Humboldt Professor Dr Jens Meiler conducts research at Leipzig University and at Vanderbilt Universi ...
Christian Hüller
Universität Leipzig
Sie können Suchbegriffe mit und, oder und / oder nicht verknüpfen, z. B. Philo nicht logie.
Verknüpfungen können Sie mit Klammern voneinander trennen, z. B. (Philo nicht logie) oder (Psycho und logie).
Zusammenhängende Worte werden als Wortgruppe gesucht, wenn Sie sie in Anführungsstriche setzen, z. B. „Bundesrepublik Deutschland“.
Die Erweiterte Suche können Sie auch nutzen, ohne Suchbegriffe einzugeben. Sie orientiert sich dann an den Kriterien, die Sie ausgewählt haben (z. B. nach dem Land oder dem Sachgebiet).
Haben Sie in einer Kategorie kein Kriterium ausgewählt, wird die gesamte Kategorie durchsucht (z.B. alle Sachgebiete oder alle Länder).
