SpatialAgent: An Autonomous AI Agent for Spatial Biology

SpatialAgent is an autonomous LLM-driven agent that spans the full spatial biology research workflow — experimental design, multimodal spatial transcriptomics/scRNA-seq analysis, and hypothesis generation — using 72 specialized tools and 17 guided skill templates. It runs in autonomous or co-pilot mode and matched or outperformed human scientists on benchmark tasks across ~2 million cells from brain, heart, and colitis-model tissue.

SpatialAgent combines LLMs with dynamic tool execution for end-to-end spatial biology research.

72 specialized tools spanning database queries, literature mining, spatial analytics, and genomic analysis
17 skill templates for guided workflows
Autonomous mode (full task execution) and co-pilot mode (interactive refinement)
Benchmarked on ~2M cells across human brain, heart, and mouse colitis model, matching or beating expert performance

Described in the bioRxiv preprint (April 2025); code and tutorials at Genentech/SpatialAgent.