scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository.

scBaseCount is the largest public repository of single-cell gene expression data, containing over 502 million cells from 27 organisms and 75 tissues, standardized through AI automation.

• Why it matters: Standardized metadata and data processing are crucial for maximizing the utility of the vast SRA dataset, enabling more accurate analyses and model training across diverse biological contexts.
• What they did: An AI agent was used to discover, extract metadata, and standardize processing of all 10x Genomics datasets, creating a comprehensive, uniform database that captures both coding and non-coding gene expression.
• The result: This resource enhances the ability to analyze phenotypic diversity, improves cross-experiment alignment, and demonstrates AI’s potential to autonomously curate large-scale biological data repositories.