FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
On the map: Diffusion models → Medical imaging and segmentation
Abstract (arXiv)
Predicting spatial gene expression from routine H&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essential biological structures like gene coordination and spatial distribution. To preserve these relationships, we introduce FLAG, a diffusion-based framework that redefines this task as structured distribution modeling. At the same time, we identify the critical Gene Dimension Curse, where joint modeling gene expression and their spatial interactions fail in high-dimensional spaces, and FLAG solves this challenge by integrating a spatial graph encoder for topological consistency and utilizing Gene Foundation Model (GFM) alignment for gene-gene fidelity in the generation process. To rigorously assess model performance, we propose a set of novel structural evaluation metrics, including Gene Structural Correlation (GSC) and Spatial Structural Correlation (SSC). Our experiments demonstrate that FLAG is highly competitive in traditional accuracy (PCC/MSE) while achieving significantly enhanced structural fidelity in capturing both gene-gene and gene-spatial relationships. The code is available at https://github.com/darkflash03/FLAG.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 20 of its 51 references that are in the map. First posted on arXiv 18 May 2026.
Builds on
20 of 51 references.
Closest ancestors · 3
Same direction, newest first
- 2025Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching25 May
- 2025Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images26 Jan
- 2024SpaDiT: Diffusion Transformer for Spatial Gene Expression Prediction using scRNA-seq18 Jul
Other references · 17
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
- 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
- 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
- 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 283
- 2023Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Imagescited by 134
- 2024HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysiscited by 107
- 2025Latent Diffusion Model without Variational Autoencodercited by 88
- 2023Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learningcited by 79
5 more
- 2024Accurate Spatial Gene Expression Prediction by integrating Multi-resolution featurescited by 52
- 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 45
- 2024MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Imagescited by 17
- 2023SEPAL: Spatial Gene Expression Prediction from Local Graphscited by 13
- 2025Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learningcited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Correlation-Guided Flow Matching with Annealed Masking for Spatial Transcriptomics Generation
- 2026What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
- 2026Program-space Diffusion for Morphology-to-Transcriptomics Prediction
- 2025Latent Gene Diffusion for Spatial Transcriptomics Completion
- 2025SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes
- 2026Concept-based explanation of gene expression prediction from H&E images
- 2026Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
- 2025Controllable diffusion-based generation for multi-channel biological data