grid-based dominance mapping

To address the lack of efficient, accessible tools for quantitative spatial analysis of cellular organization in AI-segmented histopathological images, this study introduces SASHIMI—the first comprehensive single-cell spatial analytics platform specifically designed for AI segmentation outputs. SASHIMI integrates 27 spatial statistical and topological features, including proximity metrics, grid-based similarity measures, spatial autocorrelation indices, and persistent homology descriptors, and enables reproducible, real-time analysis via a web-based interactive visualization interface. Validated on cohorts of oral potentially malignant disorders and non-small cell lung cancer, SASHIMI identified multiple spatial biomarkers significantly associated with overall survival, demonstrating its utility in prognostic modeling. This work bridges a critical methodological gap in AI-driven spatial histomics, advancing standardization and clinical translation of tumor microenvironment quantification.

To address the challenge of multi-class cell counting in immunohistochemistry (IHC) images—complicated by staining overlap, biomarker expression heterogeneity, and morphological diversity—we propose a knowledge distillation framework integrating multiple foundation models. Our method introduces a rank-aware teacher selection mechanism that dynamically evaluates and aggregates teacher capabilities via global-local patch ranking; and a vision-language alignment fine-tuning strategy that leverages structured text prompts to generate semantic anchors, jointly encoding class identity and density information. Built upon regression-based density map estimation, the framework enables end-to-end prediction of multi-class cell densities. Evaluated across 12 IHC biomarkers and 5 tissue types, it significantly outperforms state-of-the-art methods, achieving exceptional agreement with pathologist counts (ICC > 0.95). Moreover, it demonstrates strong generalizability on H&E-stained images.

Existing single-cell large language models (LLMs) struggle to effectively integrate spatial coordinates with cell–cell interaction information, resulting in inadequate spatial semantic modeling and insufficient capture of biological relationships. To address this, we propose Spatial2Sentence—a multi-sentence framework tailored for imaging mass cytometry (IMC) data. Our method introduces a novel spatial–expression dual positive/negative sampling paradigm that jointly encodes single-cell expression profiles and spatial proximity into natural language sequences. It is the first to semantically represent spatial coordinates as part of a “cellular language” and explicitly model bidirectional interactions between spatial and functional modalities. The framework integrates multi-task learning, distance-matrix-guided sample construction, and LLM-driven cross-modal textual encoding. Evaluated on a diabetic IMC dataset, Spatial2Sentence achieves absolute improvements of 5.98% in cell-type classification accuracy and 4.18% in clinical state prediction accuracy, while significantly enhancing model interpretability and biological relevance.

Existing approaches struggle to effectively quantify interactions among entities in multispecies spatial data. This work introduces, for the first time, the metric space invariant known as “magnitude” into this domain, proposing a global and local feature vector method that simultaneously captures spatial configuration and scale. Grounded in magnitude theory for finite metric spaces, the method extracts structural features from both synthetic and real tissue microarray data. Applied to tumor microenvironment analysis, it successfully identifies radial distribution patterns correlated with clinical outcomes and reveals the discriminative roles of B/T cell interactions and CD4⁺ T cell–CD163⁺ macrophage associations in determining immune response types in colorectal cancer.

To address the limitations in microscopy cell counting—namely, model complexity and the entanglement of localization and counting tasks, which jointly hinder accuracy and efficiency—this paper proposes a decoupled dual-network framework. The framework separates counting and localization: a lightweight Counter network extracts global features to generate a coarse density map and outputs an accurate total cell count; a Locator network, conditioned on both the original image and the coarse map, reconstructs a high-resolution density map for precise single-cell localization. To alleviate optimization difficulties inherent in direct high-resolution density map regression, we introduce a novel cross-regional global message-passing module. The architecture employs a compact two-branch CNN with intermediate-layer feature fusion and conditional density map reconstruction. Evaluated on four standard benchmarks, our method achieves state-of-the-art performance, significantly reducing average counting error. The source code is publicly available.

This study addresses how spatial biologists can guide and validate complex tissue data analysis tasks executed by AI agents. Building upon the Claude Science agent, the authors employ contextual inquiry, formative pilots, and observational experiments to propose four key design directions: execution control, familiar views, source information transparency, and cross-environment accessible verification. The work reveals the epistemic mechanisms through which scientists rely on visual evidence to evaluate AI-generated results. Furthermore, it constructs a comprehensive empirical model of the analytical workflow encompassing both interactive control and verification. Ultimately, this research contributes a systematic design framework for human-AI collaborative scientific discovery, offering actionable insights into integrating intelligent agents within rigorous biological research practices.

This study addresses the limitation of existing image assessment models that output only scalar scores without defect localization or interpretability. We propose a unified image assessment framework utilizing a text-native grid representation as its interface to jointly predict quality scores, localize defective regions, and generate interpretable descriptions within a single forward pass. Methodologically, we integrate supervised fine-tuning with Group Relative Policy Optimization (GRPO) reinforcement learning—leveraging Dice and format-based rewards—to achieve post-training optimization under heterogeneous spatial supervision, alongside introducing a parameter-free parser for structured prediction conversion. Experimental results demonstrate that our model attains an overall scoring SRCC of 0.601, outperforming the Gemini baseline, while achieving superior defect localization performance over both general-purpose and specialized models across most benchmarks.

This work addresses the challenge that in single-cell perturbation data, cell populations under different perturbations exhibit substantial overlap, rendering conventional single-cell classification accuracy an unreliable metric of model performance. To overcome this limitation, the authors propose the Classifier Discrimination Score (CDS), which constructs a perturbation-level profile by aggregating classifier output probability distributions across entire cell populations and replaces single-cell predictions with population-level ranking. Remarkably, CDS recovers near-perfect perturbation identification from weak classifiers without requiring retraining. The method is compatible with diverse architectures—including linear models, MLPs, and Transformers—and demonstrates significant gains in identification accuracy on the Tahoe-100M and Virtual Cell Challenge datasets, with particularly pronounced advantages in low-cell-count regimes.

This study addresses the high computational cost of large-scale spatial point pattern clustering inference, which hinders its application to high-throughput spatial proteomics data. The authors propose an efficient testing framework based on adaptive spatial tiling: by extracting non-overlapping local tiles that satisfy constraints on both point count and geometric shape, and combining Ripley’s K-function with asymptotic normal approximation and evidence aggregation across multiple tiles, the method enables scalable clustering inference and rapid p-value computation. While preserving statistical power, the approach achieves substantial gains in computational efficiency. It successfully detects spatial clustering of plasma cells and their co-localization with macrophages in both simulated data and real human gut spatial proteomics datasets, demonstrating strong scalability and practical utility.

This work addresses the challenge of efficiently exploring and interpreting the high-dimensional combinatorial space of gene perturbations generated by AI-based virtual cell models and their complex transcriptional responses across diverse cell types. To this end, we propose a visual analytics system that, for the first time, integrates clustered overviews, compact glyph-based encodings, and coordinated multi-view interactions to enable systematic comparison and interpretable exploration of perturbation strategies. By incorporating AI-generated predictions and validating through real-world case studies and expert interviews, we demonstrate that our approach substantially enhances researchers’ understanding of perturbation effects and improves decision-making efficiency in drug discovery, effectively bridging the cognitive gap between computational models and biomedical experts.