SpatialAgent: An autonomous AI agent for spatial biology
SpatialAgent: автономный AI-агент для пространственной биологии
2025-04-06
SCID: 54.1/myjsp2xz
Discuss with AI
AI-driven discoverySpatialAgentadaptive reasoningautonomous AI agentdynamic tool executionexperimental designhuman brainhuman hearthypothesis generationlarge language modelsmouse colon colitis modelmultimodal data analysisspatial biologytwo million cells dataset
Figures from the paper
Abstract (AI)
Advances in AI are transforming scientific discovery, yet spatial biology, a field that deciphers the molecular organization within tissues, remains constrained by labor-intensive workflows. Here, we present SpatialAgent, an autonomous AI agent for spatial biology research. SpatialAgent couples large language models with a Plan-Act-Conclude architecture, dynamic tool and skill retrieval, multimodal interpretation, and verification modules that audit generated claims. It supports the full discovery loop, from gene-panel design and multimodal annotation to trajectory inference, cell-cell communication analysis, imputation, and hypothesis generation. Across human and mouse brain, heart, tonsil, colon, and prostate datasets, SpatialAgent outperformed established computational baselines and matched or surpassed expert scientists in key tasks. In open-ended case studies, it recovered known tissue organization and generated spatially grounded hypotheses. In a prospective mouse prostate cancer Xenium study, it designed a compact 100-gene add-on panel that profiled 4.2 million cells across 21 samples, improved cell-type and malignant-state prediction, and captured spatially structured tumor and microenvironment programs. SpatialAgent establishes a framework for autonomous and collaborative discovery in spatial biology.
Key Findings
1
It integrates large language models with dynamic tool execution and adaptive reasoning to perform experimental design, multimodal data analysis, and hypothesis generation.
2
SpatialAgent enables a paradigm combining autonomy with human collaboration for AI-driven discovery in spatial biology.
3
SpatialAgent is a fully autonomous AI agent designed specifically for spatial-biology research, covering the entire research pipeline.
4
SpatialAgent’s performance surpassed the best computational methods and matched or outperformed human scientists across key tasks.
5
Tested on datasets totaling two million cells from human brain, heart, and a mouse colon colitis model, SpatialAgent scaled across tissues and species.
Research Object
SpatialAgent, an autonomous AI agent designed for spatial biology research
Research Subject
The agent's end-to-end performance and capabilities across the spatial-biology research pipeline, including experimental design, multimodal data analysis, hypothesis generation, and scaling across tissues and species
Publication Details
Publication Date
2025-04-06
Journal
Publisher
ISSN
Cited by
64
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
Scikit-learn: Machine Learning in Python2012
PyTorch: An Imperative Style, High-Performance Deep Learning Library2019
Inference and analysis of cell-cell communication using CellChat2021
Autonomous biomedical research with an artificial intelligence agent2026
Empowering biomedical discovery with AI agents2024
Accelerating scientific discovery with Co-Scientist2026
An agentic system for rare disease diagnosis with traceable reasoning2026
Towards end-to-end automation of AI research2026