Foundation Models in Health Research
Foundation models are advanced artificial intelligence systems designed to process vast amounts of data and to complete a range of downstream tasks. Being trained on extensive datasets these models are now revolutionizing biomedical research, accelerating discovery and translation. At the Computational Health Center we and our partners leverage these cutting-edge models to decode the complexities of human biology, aiming to pave the way for innovative treatments and a deeper understanding of health and disease.
Foundation models are advanced artificial intelligence systems designed to process vast amounts of data and to complete a range of downstream tasks. Being trained on extensive datasets these models are now revolutionizing biomedical research, accelerating discovery and translation. At the Computational Health Center we and our partners leverage these cutting-edge models to decode the complexities of human biology, aiming to pave the way for innovative treatments and a deeper understanding of health and disease.
On this page, you find highlights, publications and resources of our scientists and more.
↳ Read our newest foundation model-dedicated story about DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology here!
↳ Read an interview with Dr. Eric Schulz, Director of the Institute of Human-Centered AI at Helmholtz Munich, about Machine Psychology and how Foundation Models will revolutionize human health here!
↳ Read an interview with Anna Schaar, PhD student at Helmholtz Munich, about Nicheformer: a foundation model for single-cell and spatial omics here!
↳ Read an interview with Roberto Olayo Alarcon, PhD student at Helmholtz Munich, about
MolE: Pre-trained molecular representations enable antimicrobial discovery here!
Stéphane d'Ascoli, Sören Becker, Alexander Mathis, Philippe Schwaller, Niki Kilbertus. 2023.
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers. arXiv
Marcel Binz, Stephan Alaniz, Adina Roskies, Balazs Aczel, Carl T. Bergstrom, Colin Allen, Daniel Schad, Dirk Wulff, Jevin D. West, Qiong Zhang, Richard M. Shiffrin, Samuel J. Gershman, Ven Popov, Emily M. Bender, Marco Marelli, Matthew M. Botvinick, Zeynep Akata, Eric Schulz. 2023.
How should the advent of large language models affect the practice of science?. arXiv
Sergey Vilov, Matthias Heinig. 2024.
Investigating the performance of foundation models on human 3’UTR sequences. bioRxiv
Roberto Olayo-Alarcon, Martin K. Amstalden, Annamaria Zannoni, Medina Bajramovic, Cynthia M. Sharma, Ana Rita Brochado, Mina Rezaei, Christian L. Müller. 2024.
Pre-trained molecular representations enable antimicrobial discovery. bioRxiv
Manuel Tran, Paul Schmidle, Sophia J. Wagner, Valentin Koch, Valerio Lupperger, Annette Feuchtinger, Alexander Böhner, Robert Kaczmarczyk, Tilo Biedermann, Kilian Eyerich, Stephan A. Braun, Tingying Peng, Carsten Marr. 2024.
Generating highly accurate pathology reports from gigapixel whole slide images with HistoGPT. medRxiv
Alexander Karollus, Johannes Hingerl, Dennis Gankin, Martin Grosshauser, Kristian Klemon & Julien Gagneur. 2024
Species-aware DNA language models capture regulatory elements and their evolution. Genome Biology
Anna C. Schaar, Alejandro Tejada-Lapuerta, Giovanni Palla, Robert Gutgesell, Lennard Halle, Mariia Minaeva, Larsen Vornholz, Leander Dony, Francesca Drummer, Mojtaba Bahrami, Fabian J. Theis. 2024.
Nicheformer: a foundation model for single-cell and spatial omics. bioRxiv
Mohammad Lotfollahi, Yuhan Hao, Fabian J. Theis, Rahul Satija. 2024
The future of rapid and automated single-cell data analysis using reference mapping. Cell