spatial proteomics orchestration

This study addresses the challenges of deciphering cellular heterogeneity, tissue spatial architecture, and dynamic biological processes—including development, neuronal activity, and tumor evolution—from spatial multi-omics data. We propose a systematic analytical framework integrating spatial transcriptomics, spatial proteomics, deep learning, graph neural networks (GNNs), and multimodal fusion algorithms. Our approach overcomes key limitations of conventional methods in modeling cell–cell spatial neighborhood relationships and spatiotemporal regulatory networks. It enables high-resolution characterization of spatial cellular patterning during organogenesis and identification of critical molecular features and regulatory circuits within the tumor microenvironment. The framework significantly advances understanding of spatial–molecular coordination in complex biological systems. By providing a scalable, integrative computational paradigm and open analytical tools, it facilitates mechanistic investigation of human diseases and accelerates discovery of precision medicine targets.

Current AI agents lack standardized evaluation for extracting biological insights from real-world spatial omics data. Method: We introduce SpatialBench—the first benchmark for spatial biology—comprising 146 verifiable questions across five experimental platforms and seven analytical task types. We propose the first systematic evaluation paradigm for spatial biology agents, emphasizing task-platform coupling and identifying Harness—a unified framework integrating tool orchestration, prompt engineering, control-flow logic, and execution environment—as the primary determinant of agent performance. Our implementation leverages multimodal large language models, custom toolchains, deterministic automated scoring, and realistic data workflow modeling. Results: State-of-the-art models achieve only 20–38% accuracy on SpatialBench; however, targeted Harness optimization yields substantial performance gains. SpatialBench establishes a reproducible, transparent, and diagnosable standard for evaluating and iteratively improving spatial biology agents.

Spatial transcriptomics remains costly and low-throughput, while hematoxylin and eosin (H&E) staining lacks molecular resolution, hindering precise biological discovery and clinical prediction. To address these limitations, this work proposes STORM, a multimodal foundation model that establishes the first cross-platform, scalable framework for spatial multimodal integration. STORM leverages a hierarchical neural network to jointly encode morphological, gene expression, and spatial contextual information from 1.2 million paired spatial transcriptomics and H&E image patches across 18 organs. The model unifies tissue morphology with molecular representations, significantly outperforming existing methods in gene expression prediction across 11 cancer types. Furthermore, STORM enhances performance in immunotherapy response and prognostic assessment across 23 independent cohorts comprising 7,245 patients, demonstrating compatibility with multiple platforms including Visium, Xenium, Visium HD, and CosMx.

Two-dimensional tissue sections struggle to reliably capture the spatial characteristics of local cellular interactions and rare cell populations within three-dimensional tissue architecture, while dense volumetric imaging remains prohibitively expensive. This study systematically evaluates, for the first time, the bias introduced by 2D sampling on local spatial statistics and proposes a geometry-aware sparse 3D reconstruction framework. By integrating phenotypic similarity with spatial proximity to associate cells across serial sections and incorporating cell type–specific shape priors, the method reconstructs high-fidelity single-cell 3D coordinates. Validated on both public imaging mass cytometry and in-house CODEX datasets, the approach significantly enhances the reliability of spatial analysis under limited imaging budgets, outperforming conventional 2D analyses. It enables structure-level 3D spatial resolution and provides quantitative guidance for experimental design regarding section spacing, coverage, and redundancy.

This study addresses the challenge of integrating local microenvironments with global pseudotemporal trajectories in spatial transcriptomics, which involves multimodal registration across samples and regions as well as deciphering complex spatiotemporal expression patterns. To this end, the authors propose a multi-region analytical paradigm that jointly models local neighborhoods and global developmental trajectories. They develop an integrated visual analytics system featuring novel glyphs and a computational framework to enable efficient, interactive exploration of spatial transcriptomic data alongside reference cell atlases and simulated temporal dynamics. In case studies involving pathologists and oncologists, as well as external evaluations, the system effectively facilitated the identification of cellular state transitions and the discovery of spatiotemporal gene expression dynamics.

This work addresses the pervasive challenges in bioinformatics tooling—such as fragmentation, complex dependencies, inconsistent documentation, and irreproducible environments—that severely hinder method reuse and adaptation. To overcome these limitations, the authors propose PoSyMed, an open modular platform that integrates biomedical workflows through formalized tool descriptions, containerized execution, a persistent workflow engine, and a conversational interface. Innovatively, a large language model is incorporated as a semantic assistant within a typed, validated, and human-supervised framework to support tool discovery, pipeline construction, and parameter configuration. This design significantly enhances analytical transparency and reproducibility. The platform’s efficacy is demonstrated in representative biomedical use cases, and it has been released as open-source software.

Current foundation models in computational pathology struggle to accurately link histological morphology with genomic alterations due to the absence of spatially resolved molecular supervision, thereby limiting their ability to infer molecular phenotypes directly from H&E-stained slides. To address this, this work proposes STAMP, a novel framework that introduces, for the first time, a spatial transcriptomics–guided molecular alignment mechanism. By integrating pathway-informed representation alignment with parameter-efficient fine-tuning, STAMP endows the model with intrinsic molecular awareness. The study also constructs HumanST-1k, a large-scale multi-organ dataset comprising 1.8 million paired H&E and spatial transcriptomics samples, which substantially enhances the model’s accuracy and clinical applicability in predicting molecular features without requiring additional sequencing.

Current spatial proteomics analysis workflows are fragmented and rely heavily on expert-driven manual integration of heterogeneous tools, limiting scalability and reproducibility. This work proposes the first autonomous reasoning agent tailored for this domain, leveraging a large language model–driven architecture that combines expert-curated biological skills with specialized computational tools to automatically translate natural language queries into end-to-end analytical pipelines—spanning from multiplexed imaging to phenotypic discovery. The approach achieves full pipeline automation without task-specific fine-tuning and introduces SP-Bench, a comprehensive benchmark comprising 102 tasks across 18 categories. Experimental results demonstrate that the proposed method significantly outperforms existing open-source biomedical agents on both SP-Bench and downstream tasks, establishing state-of-the-art performance.