A vision foundation model for single-cell biology via spatial gene cartography

• URL: http://arxiv.org/abs/2607.14163v1
• Date: Wed, 15 Jul 2026 01:03:17 GMT
• Title: A vision foundation model for single-cell biology via spatial gene cartography
• Abstract summary: scVision is a vision foundation model that renders each cell as a continuous image.<n>It places genes at fixed positions on a single shared, pan-tissue layout so that co-expressed genes become spatial neighbours.<n> scVision is the most accurate cell-type annotator and recovers gene programs without supervision.
• Score: 36.59425810402625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens. This discards the relationships among genes and often the magnitude of their expression. We present scVision, a vision foundation model that instead renders each cell as a continuous image. Using optimal transport, it places genes at fixed positions on a single shared, pan-tissue layout so that co-expressed genes become spatial neighbours, turning a transcriptome into an image in which gene programs appear as local texture. We pretrain a vision transformer by masked image modelling on 72 million human cells and use the frozen encoder with no fine-tuning. In zero-shot evaluations on six independent, held-out studies, scVision is the most accurate cell-type annotator and recovers gene programs without supervision, ahead of existing foundation models and classical baselines; on multi-study integration it matches the strongest token-based model while conserving the most biological structure, without ever seeing a batch label. Permuting the gene layout with the network fixed sharply lowers accuracy, more than removing the vision transformer itself, showing that biologically meaningful position, not the network, carries the signal. By preserving expression magnitude and gene relationships, scVision reframes single-cell representation learning as a vision problem, connecting it to the mature methods of computer vision.

Related papers

• VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression [12.854881472840363]
  We present a multimodal foundation model that predicts single-cell expression from H&E images using paired Xenium data.<n>VICE generalizes to heldout patients, slides, and partially overlapping gene panels from Xenium, and it consistently outperforms prior single-cell expression prediction methods on seven metrics.
  arXiv  Detail & Related papers  (2026-08-08T23:36:00Z)
• BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells [64.21963170814706]
  BioM-JEPA predicts aggregate representations of graph-connected gene blocks.<n>A student network infers each target-block representation from the remaining genes in a cell.<n>Across CellBench tasks, BioM-JEPA embeddings retained expression, pathway and neighbourhood information.
  arXiv  Detail & Related papers  (2026-08-06T11:58:29Z)
• Beyond Gene Reconstruction: Learning Cell Representations through Complementary Transcriptomic Views [8.738986684868424]
  We propose a contrastive pretraining framework that learns cell representations through complementary transcriptomic views.<n>We introduce specific adaptations along three dimensions --- co-expression-guided gene partitioning, expression-aware contrast-set construction, and competence-gated contrastive onset.
  arXiv  Detail & Related papers  (2026-08-02T04:35:45Z)
• Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics [9.067087306213525]
  We use partial gene expression to guide the prediction process alongside histology images.<n>We employ a Masked Autoencoder (MAE) to utilize a small fraction of gene expression as genetic anchors for inferring whole-slide gene expression profiles.<n>Our framework consistently surpasses existing methods in both histology-only prediction and spatial imputation.
  arXiv  Detail & Related papers  (2026-06-19T06:47:55Z)
• MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging [31.990445585569688]
  MorphGen is a state-of-the-art diffusion-based generative model for fluorescent microscopy.<n>It generates the complete set of fluorescent channels jointly, preserving per-organelle structures.<n>MorphGen attains an FID score over 35% lower than the prior state-of-the-art MorphoDiff.
  arXiv  Detail & Related papers  (2025-10-01T13:34:29Z)
• SPATIA: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes [39.45743286683448]
  We introduce SPATIA, a multi-scale generative and predictive model for spatial transcriptomics.<n> SPATIA learns cell-level embeddings by fusing image-derived morphological tokens and transcriptomic vector tokens.<n>We benchmark SPATIA against 13 existing models across 12 individual tasks.
  arXiv  Detail & Related papers  (2025-07-07T06:54:02Z)
• HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data [25.915980581662023]
  We introduce HEIST, a hierarchical graph foundation model for spatial transcriptomics and transformer.<n>HEIST is pretrained on 22.3M cells from 124 tissues across 15 organs using spatially-aware contrastive and masked autoencoding objectives.
  arXiv  Detail & Related papers  (2025-06-11T12:29:01Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology [57.25098075813054]
  We propose a new framework for gene discovery entitled Un Phenotype Ensembles. It builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations.
  arXiv  Detail & Related papers  (2023-01-07T18:36:44Z)
• ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond [76.35955924137986]
  We propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context. We obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 accuracy on ImageNet real validation set.
  arXiv  Detail & Related papers  (2022-02-21T10:40:05Z)
• Neural Cellular Automata Manifold [84.08170531451006]
  We show that the neural network architecture of the Neural Cellular Automata can be encapsulated in a larger NN. This allows us to propose a new model that encodes a manifold of NCA, each of them capable of generating a distinct image. In biological terms, our approach would play the role of the transcription factors, modulating the mapping of genes into specific proteins that drive cellular differentiation.
  arXiv  Detail & Related papers  (2020-06-22T11:41:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.