Loading
Nathan J. LeRoy, Guangtao Zheng, Oleksandr Khoroshevskyi, Donald R Campbell, Aidong Zhang, Nathan C. Sheffield
IntroductionChromatin accessibility profiling is an important tool for understanding gene regulation and cellular function. While public repositories house nearly 10,000 scATAC-seq experiments, unifying this data for meaningful analysis remains challenging. Existing tools struggle with the scale and complexity of scATAC-seq datasets, limiting tasks like clustering, cell-type annotation, and reference mapping. A promising solution is using foundation models adapted to specific tasks via transfer learning. While transfer learning has been applied to scRNA-seq, its potential for scATAC-seq remains underexplored. MethodsWe introduce Atacformer, a transformer-based foundation model for scATAC-seq data analysis. Unlike other models that only produce cell-level representations, Atacformer generates embeddings for individual cis-regulatory elements. Pre-trained on a large atlas of scATAC-seq experiments, Atacformer learns robust representations of genomic regulatory regions for downstream use. After pretraining, the model is fine-tuned for cell-type prediction and batch correction. We also integrated Atacformer with RNA-seq data to build a Contrastive RNA-ATAC Fine Tuning (CRAFT) model capable of cross-modal alignment and RNA imputation from ATAC data. ResultsAtacformer matches or exceeds leading scATAC-seq clustering tools in adjusted rand index and runtime, with fine-tuned models achieving top performance across datasets. It processes raw fragment files end-to-end 80% faster than existing tools while preserving biological structure. Fine-tuned on bulk BED files, it recovers cell type and assay labels with >80% accuracy. We show how the Atacformer architecture produces contextualized embeddings of individual genomic regions, which we use to identify unannotated, cell-type-specific promoter elements directly from chromatin accessibility data.
Peer review in progress...
Loading...
CD4⁺ T cells confer transplantable rejuvenation via Rivers of telomeres
Lanna, A.; Valvo, S.; Dustin, M.; Rinaldi, F.
Using a GPT-5-driven autonomous lab to optimize the cost and titer of cell-free protein synthesis
Smith, A. A.; Wong, E. L.; Donovan, R. C.; Chapman, B. A.; Harry, R.; Tirandazi, P.; Kanigowska, P.; Gendreau, E. A.; Dahl, R. H.; Jastrzebski, M.; Cortez, J. E.; Bremner, C. J.; Hemuda, J. C. M.; Dooner, J.; Graves, I.; Karandikar, R.; Lionetti, C.; Christopher, K.; Consiglio, A. L.; Tran, A.; McCusker, W.; Nguyen, D. X.; Nunes da Silva, I. B.; Bautista-Ayala, A. R.; McNerney, M. P.; Atkins, S.; McDuffie, M.; Serber, W.; Barber, B. P.; Thanongsinh, T.; Nesson, A.; Lama, B.; Nichols, B.; LaFrance, C.; Nyima, T.; Byrn, A.; Thornhill, R.; Cai, B.; Ayala-Valdez, L.; Wong, A.; Che, A. J.; Thavaraj
A Single-Cell and Spatial 3D Multi-omic Atlas of Developing Human Basal Ganglia and Inhibitory Neurons
Heffel, M. G.; Xu, H.; Pastor-Alonso, O.; Li, X.; Baig, M. S.; Irfan Ghoor, R.; Li, R.; Kern, C.; Kum, J.; Zhang, Y.; Paino, J.; Tsai, M. J.; Tai, C.-Y.; Tucker, G.; Zhao, Z.; Hou, A.; von Behren, Z.; Bhade, M.; Li, S.; Sandoval, K.; Scholes, J.; Codrea, F.; Calimlim, J.; Liao, E. K.; Leung, G.; Kim, J.; Eskin, E.; Flint, J.; Cotter, J. A.; Pasaniuc, B.; Bintu, B.; Zhu, Q.; Mukamel, E. A.; Ernst, J.; Paredes, M. F.; Luo, C.
Prediction of transformative breakthroughs in biomedical research
Davis, M. T.; Busse, B. L.; Arabi, S.; Meyer, P.; Hoppe, T. A.; Meseroll, R. A.; Hutchins, B. I.; Willis, K. A.; Santangelo, G. M.