Spatial omics

Spatial omics Models

Spatial omics foundation models operate on measurements that retain their physical coordinates within a tissue — spatial transcriptomics, histology-to-expression prediction, and models of the tumor and tissue microenvironment. Unlike dissociated single-cell data, spatial models learn how neighboring cells influence one another and how gene expression is organized across tissue architecture. By preserving the where alongside the what, they are revealing the structural logic of development, immunity, and disease at cellular resolution.

8 models in this category

Notable Models

Top-rated spatial omics models from our evaluations

TARIO-2

Noetik

Released June 1, 2026

Multimodal tumor foundation model trained on paired H&E histology and spatial transcriptomics to infer whole-transcriptome and tumor-microenvironment signal from routine H&E alone.

PathologySpatial omics

STMDiT

ETH Zurich +1 other

Released May 29, 2026

A diffusion transformer that synthesizes H&E histopathology image patches conditioned jointly on spatial transcriptomics gene expression and morphological embeddings.

PathologySpatial omics

TMEformer

Sichuan University

Released May 20, 2026

A spatial-transcriptomics foundation model for the tumor microenvironment that produces TME-aware embeddings and enables in silico perturbation from a fixed pretrained checkpoint.

Spatial omics

SpaRank

Guangxi University

Released May 13, 2026

A transferable spatial-transcriptomics deconvolution model whose rank-based spot encoding lets one pretrained model generalize across tissues, disease states, and platforms without retraining.

Spatial omics

A multi-organ foundation model aligning histology image features with spatial-transcriptomics gene expression across 13 organs for zero-shot virtual ST and survival prediction.

PathologySpatial omics

Phoenix

Helmholtz Munich +1 other

Released April 29, 2026

Latent flow-matching foundation model that predicts pan-cancer spatially-resolved single-cell gene expression directly from routine H&E histology slides.

PathologySpatial omics