Abstract
Spatial and single-cell transcriptomics are transformative in deciphering cellular dynamics. Trajectory inference (TI) is critical as the fundamental paradigm for reconstructing cell developmental paths. However, existing methods require extensive manual intervention and proficiency in heterogeneous tools, posing a significant barrier to efficient TI analysis. To bridge this gap, we propose SpaCellAgent, an autonomous large language model (LLM) multi-agent framework that automates end-to-end spatiotemporal analysis and narrative generation.
SpaCellAgent utilizes a multi-agent architecture for strategic workflow planning, a dynamic tool-orchestration engine for adaptive algorithm selection, and a self-evolution module that iteratively refines performance through feedback. We evaluate SpaCellAgent on six heterogeneous datasets encompassing complex temporal developmental trajectories, diverse sequencing platforms, and spatially-resolved tissue architectures. SpaCellAgent consistently demonstrates over 40\% improvement in analytical efficiency while maintaining expert-aligned performance.
By converting natural language specifications into optimized analytical workflows and fully automating the pipeline, SpaCellAgent democratizes advanced spatiotemporal modeling and establishes a scalable, agent-driven paradigm for computational biology. The code and materials are available at GitHub.
Blogger's Review: The introduction of SpaCellAgent greatly simplifies the analysis of cellular developmental trajectories. Its automation and self-evolution mechanisms significantly reduce reliance on technical expertise, enabling bioinformatic researchers to conduct data analysis and interpretation more efficiently. The design of its multi-agent architecture and dynamic tool selection engine undoubtedly provides new insights and directions for future computational biology research.