Adam R. Boxall

A bstract: Molecular assays such as spatial transcriptomics facilitate fine-grained identification of cell types for analyzing tumor microenvironments. However, they are expensive to acquire in routine clinical practice compared to hematoxylin and eosin (H&E) images. With molecular guidance, such images can distinguish cell lineages, yet often fail to resolve closely related subtypes. To overcome this, we introduce CellBridge , a multi-modal contrastive learning framework pretrained on 16M cells with paired H&E and spatial profiles, for transferring molecular information into morphological representations. CellBridge further incorporates a Cell-Ontology-aware conformal prediction module that assigns labels at different levels of specificity: leaf-level cell types when morphology alone provides sufficient evidence, and broader ancestor categories when distinguishing among more specific cell types would require molecular information. Across in-domain and out-of-domain benchmarks, CellBridge outperforms leading pathology foundation models in macro F1 by up to 16 percentage points, with the largest gains on the most fine-grained label spaces. It consistently achieves smaller prediction sets, while reducing class-wise coverage gaps. We envision CellBridge as a step toward extracting cellular information that currently requires costly molecular assays from routinely acquired pathology images, while explicitly identifying where such assays remain necessary. Our code is available at https://github.com/Lotfollahilab/cellbridge .

Spatial transcriptomics maps gene expression at cellular resolution, revealing how cells organize into multicellular niches. Yet computational analyses remain dataset-specific, without a transferable representation of tissue organization that generalizes across datasets, tasks and tissues or predicts how tissues behave under perturbation. We present TERRA, a foundation model pretrained on 112 million human cells profiled by spatial transcriptomics. From a single pretrained backbone, TERRA yields embeddings at the scale of cells, the genes they express and the neighborhoods in which they reside, and supports spatial in silico perturbation, all applied zero-shot to unseen tissues. At the cell level, in newly generated spatial data for developing pancreas, TERRA identified an islet-associated capillary state which we posit represents a developmental precursor of the mature islet microvasculature. At the gene level, in untreated kidney sections, in silico knockout of immune-checkpoint targets predicted a gene program of immune-checkpoint-blockade-associated nephrotoxicity, which we validated in treatment-exposed tissue and recovered in blood. At the neighborhood level, TERRA mapped macrophages across tissues to identify recurring cross-organ niches, which we term archetypes, including a tumor-boundary niche associated with poor prognosis in kidney cancer. Together, TERRA captures the spatial and multicellular logic of human tissue and predicts, in silico, its response to perturbation, providing a multi-scale framework for tissue biology, therapeutic development and clinical application.

Tissue microenvironments reprogram local cellular states in disease, yet current computational spatial methods remain descriptive and do not simulate tissue perturbation. We present MintFlow, a generative AI algorithm that learns how the tissue microenvironment influences cell states and predicts how tissue perturbations can reprogram them. Applied to three human diseases, MintFlow uncovered distinct pathogenic spatial reprogramming in inflammatory and tumor microenvironments. In atopic dermatitis, MintFlow identified a novel, spatially-imprinted, type 2 ( IL13 ⁺ ITGAE ⁺ ) epidermal T resident memory cell population (type 2 T _RM ), and decoded signaling pathways within the perivascular lymphoid niche. In melanoma, MintFlow identified fibrotic stroma resembling keloid scar tissue. In kidney cancer, MintFlow resolved immunosuppressed CD8 ⁺ T cell states within tertiary lymphoid structures. Furthermore, MintFlow enabled in silico perturbations of disease-relevant cell states and tissue environments. Regulatory T cell modulation in atopic dermatitis was predicted to suppress the pro-inflammatory tissue environment, supporting manipulation of these cells as a therapeutic target. In kidney cancer, in silico T cell replacement recapitulated immune checkpoint blockade, while spatially targeted macrophage depletion reverted immunosuppressed T cell states. The corresponding gene programs correlated with survival in large kidney cancer patient cohorts. Together, these findings position MintFlow as a tool for unbiased disease mechanism prediction and in silico perturbation, accelerating translational hypothesis generation and guiding therapeutic strategies.

Spatial omics enable the characterization of colocalized cell communities that coordinate specific functions within tissues. These communities, or niches, are shaped by interactions between neighboring cells, yet existing computational methods rarely leverage such interactions for their identification and characterization. To address this gap, here we introduce NicheCompass, a graph deep-learning method that models cellular communication to learn interpretable cell embeddings that encode signaling events, enabling the identification of niches and their underlying processes. Unlike existing methods, NicheCompass quantitatively characterizes niches based on communication pathways and consistently outperforms alternatives. We show its versatility by mapping tissue architecture during mouse embryonic development and delineating tumor niches in human cancers, including a spatial reference mapping application. Finally, we extend its capabilities to spatial multi-omics, demonstrate cross-technology integration with datasets from different sequencing platforms and construct a whole mouse brain spatial atlas comprising 8.4 million cells, highlighting NicheCompass’ scalability. Overall, NicheCompass provides a scalable framework for identifying and analyzing niches through signaling events.

Effect of necrosome protein expression in TCL cell lines on tolinapant-induced cell death. A, Western blots of parental BW5147, RIPK3−/− BW5147 and MLKL−/− BW5147 cell lysates (untreated). B, Cytotox-NIR signal captured by real-time microscopy (IncuCyte), detecting membrane permeabilization during lytic cell death after treatment of parental BW5147, RIPK3−/− BW5147 and MLKL−/− BW5147 cells with tolinapant in the absence or presence of zVAD. C, Western blots of Karpas-299 cells transduced with control gRNA (KARPAS-299-CTR gRNA) or with RIPK3 gRNA (KARPAS-299-RIPK3 gRNA) constructs treated with tolinapant ± zVAD for 0, 2, or 6 hours. D, Real-time microscopy (IncuCyte) measurement of membrane permeabilization by measuring Cytotox-NIR signal after treatment of KARPAS-299-CTR gRNA or KARPAS-299-RIPK3 gRNA cells with tolinapant. E, Western blots of EL4-PAR and CASP8 KO EL4 (EL4-C8KO) cell lysates after 24-hour treatment with tolinapant. F, Real-time microscopy (IncuCyte) measurement of membrane permeabilization by measuring Cytotox-NIR signal after treatment of EL4-PAR or EL4-C8KO cells with tolinapant.

Figure S1. Additional Western blots showing different CRISPR clones generated from each construct. (Refers to Figure 1)

Uncropped Western blots from Figure 2A

Figure S9. Analysis of tumor and plasma samples from EL4-Parental and EL4-C8KO syngeneic model PD studies (Refers to Figure 6)

Measurement of gene expression changes in TCL cell lines after treatment with decitabine in vitro. A, Western blots of human (H9 and Karpas-299) and mouse (BW5147 and CT26) cell lysates prepared after treatment with decitabine for 4 days (human) or 2 days (mouse). Dotted lines indicate a cropped blot for presentation purposes. B, Bisulfite pyrosequencing data from four human TCL cell lines, showing basal (untreated) levels RIPK3 promoter methylation (top left), decitabine concentration-dependent decrease of RIPK3 methylation in all cell lines after 4 days treatment (top right), time dependent of RIPK3 promoter demethylation in Karpas-299 cells (bottom left), LINE-1 demethylation as control (at day 4, bottom right) for all four cell lines. Relative levels if cDNA expression measured by qPCR prepared from Karpas-299 (C) and H9 (D) cells treated for 4 days with a various concentration of decitabine. Each gene was normalized to 18S housekeeping gene as a control. * Indicates an estimation of relative expression since this gene was not detected in DMSO control (DMSO control CT set to 40).

Figure S4. Changes in DNA methylation levels after decitabine (DAC) treatment of human TCL cell lines. (Refers to Figure 2)