{"id":49200,"date":"2025-09-01T14:57:37","date_gmt":"2025-09-01T12:57:37","guid":{"rendered":"https:\/\/www.uni.lu\/en\/?post_type=news&p=49200"},"modified":"2025-09-02T15:39:31","modified_gmt":"2025-09-02T13:39:31","slug":"ai-model-unlocks-simulations-of-large-biomolecules-with-quantum-accuracy","status":"publish","type":"news","link":"https:\/\/www.uni.lu\/en\/news\/ai-model-unlocks-simulations-of-large-biomolecules-with-quantum-accuracy\/","title":{"rendered":"AI model unlocks simulations of large biomolecules with quantum accuracy"},"content":{"rendered":"\n
\n

An international team of researchers from the 糖心Vlog, Technische Universit\u00e4t Berlin (TU Berlin), the Berlin Institute for the Foundations of Learning and Data (BIFOLD), and Google DeepMind has developed a new machine learning model capable of simulating a wide variety of molecular systems \u2013 for example, large and complex biological molecules \u2013 with quantum-mechanical accuracy.<\/p>\n\n\n\n

The new method, called SO3LR, combines the latest developments in neural network design with physical laws and was trained on a specially curated dataset of four million different molecular structures. This enables the model to be applied not only to large biomolecules like proteins, sugars, or cell membranes, but also to a broad spectrum of other molecules without the need for retraining. This universal applicability of SO3LR paves the way for accelerated drug discovery and a deeper understanding of molecular biology.<\/p>\n\n\n\n

An interdisciplinary and international endeavour, the project was conceived by Uni.lu doctoral candidate Adil Kabylda and his PhD supervisor Prof. Alexandre Tkatchenko. As project lead, Adil developed and trained the model, then designed, performed, and analysed the simulations. This work, supported by an FNR AFR Individual PhD Fellowship, constitutes the final chapter of his PhD thesis, which is dedicated to atomistic-level (bio)molecular modelling.<\/p>\n\n\n\n

Findings are now published in the prestigious Journal of the American Chemical Society (JACS):<\/p>\n\n\n\n