Peer-Reviewed Publication
Nature2025;637(8047):965-973.January 1, 2025Journal Article
A foundation model of transcription across human cell types.
Xi Fu1,2, Shentong Mo3,4, Alejandro Buendia5, Anouchka P Laurent6, Anqi Shao7, Maria Del Mar Alvarez-Torres5, Tianji Yu5, Jimin Tan8, Jiayu Su5, Romella Sagatelian5, Adolfo A Ferrando6,9, Alberto Ciccia10, Yanyan Lan11,12, David M Owens7,13, Teresa Palomero6,13, Eric P Xing14,15, Raul Rabadan16,17
1Program of Mathematical Genomics, Department of Systems Biology, Columbia University, New York, NY, USA. xf2217@cumc.columbia.edu.
2Department of Biomedical Informatics, Columbia University, New York, NY, USA. xf2217@cumc.columbia.edu.
3Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.
4Department of Machine Learning, Carnegie Mellon University, Pittsburgh, PA, USA.
5Program of Mathematical Genomics, Department of Systems Biology, Columbia University, New York, NY, USA.
6Institute for Cancer Genetics, Columbia University, New York, NY, USA.
7Department of Dermatology, Columbia University, New York, NY, USA.
8Institute for Systems Genetics, New York University Grossman School of Medicine, New York, NY, USA.
9Regeneron Genetics Center, Regeneron, Tarrytown, NY, USA.
10Department of Genetics and Development, Columbia University, New York, NY, USA.
11Institute for AI Industry Research, Tsinghua University, Beijing, China.
12Beijing Frontier Research Center for Biological Structure, Tsinghua University, Beijing, China.
13Department of Pathology and Cell Biology, Columbia University, New York, NY, USA.
14Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE. epxing@cs.cmu.edu.
15Department of Machine Learning, Carnegie Mellon University, Pittsburgh, PA, USA. epxing@cs.cmu.edu.
16Program of Mathematical Genomics, Department of Systems Biology, Columbia University, New York, NY, USA. rr2579@cumc.columbia.edu.
17Department of Biomedical Informatics, Columbia University, New York, NY, USA. rr2579@cumc.columbia.edu.
Abstract
Transcriptional regulation, which involves a complex interplay between regulatory sequences and proteins, directs all biological processes. Computational models of transcription lack generalizability to accurately extrapolate to unseen cell types and conditions. Here we introduce GET (general expression transformer), an interpretable foundation model designed to uncover regulatory grammars across…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans