scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository
7 affiliations
- 1Arc Institute, Palo Alto, CA, USA
- 2Arc Institute, Palo Alto, CA, USA; University of California, Berkeley, Berkeley, CA, USA
- 3Arc Institute, Palo Alto, CA, USA; University of Pennsylvania, Philadelphia, PA, USA
- 4Arc Institute, Palo Alto, CA, USA; Department of Biochemistry, Stanford University School of Medicine, Stanford, CA, USA
- 5Arc Institute, Palo Alto, CA, USA; University of California, Berkeley, Berkeley, CA, USA; Department of Pathology, Stanford University School of Medicine, Stanford, CA, USA
- 6Arc Institute, Palo Alto, CA, USA; Department of Biochemistry and Biophysics, University of California, San Francisco, San Francisco, CA, USA. Electronic address: [email protected]
- 7Arc Institute, Palo Alto, CA, USA. Electronic address: [email protected]
Abstract
Single-cell RNA sequencing has transformed cell biology by enabling precise transcriptomic measurements of individual cells. The Sequence Read Archive (SRA) is the largest public repository of sequencing reads, yet much of it remains underutilized due to unstandardized metadata. Here, we introduce scBaseCount, a database that leverages an AI agent to automate discovery and metadata extraction and standardize data processing. Built by mining all 10x Genomics datasets, scBaseCount is the largest public repository of single-cell gene expression data, comprising over 502 million cells across 27 organisms and 75 tissues. It offers an unbiased view of the data landscape within the SRA and enables the training of more performant computational models through access to broader phenotypic diversity. Uniform processing enables measurement of both intronic and exonic reads and non-coding gene expression and improves alignment across experiments. Moreover, scBaseCount provides a blueprint for how AI can be leveraged to autonomously curate biological data repositories.
Related
- CellMarker 3.0: an updated resource of manually curated and computationally predicted cell markers in human/mouse and interactive web tools for single-cell and spatial transcriptomics analysis
- A Newly Curated Single Cell Sequencing Atlas Predicts Efferocytic-dependent Crosstalk in Hearts
- Towards a holistic epidemiology of Streptococcus agalactiae using the BakRep repository
- AptViralDB: A repository of experimentally validated antiviral aptamers
- APDB: A Large-Scale Repository of Predicted 2D and 3D Aptamer Structures.
BibTeX
@article{youngblut2026scbasecount,
title = {{scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository}},
author = {Nicholas D. Youngblut and Christopher Carpenter and Arshia Nayebnazar and Abhinav Adduri and Rohan Shah and Chiara Ricci-Tam and Jaanak Prashar and Rajesh Ilango and Noam Teyssier and Silvana Konermann and Patrick D. Hsu and Alexander Dobin and Dave P. Burke and Hani Goodarzi and Yusuf Roohani},
journal = {Cell},
year = {2026},
month = sep,
doi = {10.1016/j.cell.2026.08.025},
url = {https://doi.org/10.1016/j.cell.2026.08.025},
note = {CC BY},
}
RIS
TY - JOUR
TI - scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository
AU - Nicholas D. Youngblut
AU - Christopher Carpenter
AU - Arshia Nayebnazar
AU - Abhinav Adduri
AU - Rohan Shah
AU - Chiara Ricci-Tam
AU - Jaanak Prashar
AU - Rajesh Ilango
AU - Noam Teyssier
AU - Silvana Konermann
AU - Patrick D. Hsu
AU - Alexander Dobin
AU - Dave P. Burke
AU - Hani Goodarzi
AU - Yusuf Roohani
PY - 2026
DA - 2026/09/01
JO - Cell
DO - 10.1016/j.cell.2026.08.025
UR - https://doi.org/10.1016/j.cell.2026.08.025
AB - Single-cell RNA sequencing has transformed cell biology by enabling precise transcriptomic measurements of individual cells. The Sequence Read Archive (SRA) is the largest public repository of sequencing reads, yet much of it remains underutilized due to unstandardized metadata. Here, we introduce scBaseCount, a database that leverages an AI agent to automate discovery and metadata extraction and standardize data processing. Built by mining all 10x Genomics datasets, scBaseCount is the largest public repository of single-cell gene expression data, comprising over 502 million cells across 27 organisms and 75 tissues. It offers an unbiased view of the data landscape within the SRA and enables the training of more performant computational models through access to broader phenotypic diversity. Uniform processing enables measurement of both intronic and exonic reads and non-coding gene expression and improves alignment across experiments. Moreover, scBaseCount provides a blueprint for how AI can be leveraged to autonomously curate biological data repositories.
SN - 0092-8674
SN - 1097-4172
ER -