SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
For biomedical researchers, SP-Mind automates fragmented spatial proteomics workflows, improving scalability and reproducibility.
SP-Mind is the first autonomous AI agent that unifies spatial proteomics analysis from raw imaging to phenotype discovery, achieving state-of-the-art performance on the new SP-Bench benchmark (102 tasks, 18 categories) compared to existing open-source biomedical agents.
Spatial proteomics enables single-cell-resolution characterization of protein expression within tissue architecture, playing a critical role in understanding tumor microenvironments and guiding precision medicine. However, current analysis workflows remain fragmented, requiring expert manual orchestration of heterogeneous tools and limiting research scalability and reproducibility. We present SP-Mind, the first autonomous AI agent designed to unify the spatial proteomics analysis pipeline, from raw multiplexed tissue imaging to downstream phenotype discovery. Equipped with expert-curated biological analysis skills and specialized computational tools, SP-Mind converts natural-language queries into end-to-end analytical workflows without task-specific fine-tuning. To rigorously evaluate its capabilities, we introduce SP-Bench, a comprehensive benchmark spanning diverse tissue types, comprising 102 tasks across 18 distinct categories. Through extensive evaluation on SP-Bench and established downstream tasks, SP-Mind achieves state-of-the-art performance compared to existing open-source biomedical agent baselines.