Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images

• URL: http://arxiv.org/abs/2603.19766v1
• Date: Fri, 20 Mar 2026 08:52:39 GMT
• Title: Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
• Abstract summary: HINGE (HIstology-coNditioned GEneration) retrofits a pre-trained sc-FM into a conditional expression generator.<n> Evaluated on three ST datasets, ours outperforms state-of-the-art baselines on mean Pearson correlation.
• Score: 5.072469295071516
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spatial transcriptomics (ST) enables spot-level in situ expression profiling, but its high cost and limited throughput motivate predicting expression directly from HE-stained histology. Recent advances explore using score- or flow-based generative models to estimate the conditional distribution of gene expression from histology, offering a flexible alternative to deterministic regression approaches. However, most existing generative approaches omit explicit modeling of gene-gene dependencies, undermining biological coherence. Single-cell foundation models (sc-FMs), pre-trained across diverse cell populations, capture these critical gene relationships that histology alone cannot reveal. Yet, applying expression-only sc-FMs to histology-conditioned expression modeling is nontrivial due to the absence of a visual pathway, a mismatch between their pre-training and conditional ST objectives, and the scarcity of mixed-cell ST supervision. To address these challenges, we propose HINGE (HIstology-coNditioned GEneration), which retrofits a pre-trained sc-FM into a conditional expression generator while mostly preserving its learned gene relationships. We achieve this by introducing SoftAdaLN, a lightweight, identity-initialized modulation that injects layer-wise visual context into the backbone, coupled with an expression-space masked diffusion objective and a warm-start curriculum to ensure objective alignment and training stability. Evaluated on three ST datasets, ours outperforms state-of-the-art baselines on mean Pearson correlation and yields more accurate spatial marker expression patterns and higher pairwise co-expression consistency, establishing a practical route to adapt pre-trained sc-FMs for histology-conditioned spatial expression generation.

Related papers

• Program-space Diffusion for Morphology-to-Transcriptomics Prediction [0.0]
  We reformulate morphology-to-transcriptomics prediction as conditional generation in program space.<n>We extract a low-dimensional set of programs capturing coordinated expression variation in the training data.<n>We train a conditional diffusion model to generate program activations from histology.
  arXiv  Detail & Related papers  (2026-08-14T14:20:40Z)
• Understanding Synergistic Interactions among Pathology Foundation Models via Adaptive Fusion [49.550545038402184]
  Pathology foundation models (PFMs) provide strong tile-level representations via self-supervised pre-training on large-scale pathology images.<n>We present AdaFusion, a lightweight adaptive fusion framework that integrates complementary signals from multiple frozen PFMs.<n>AdaFusion consistently outperforms individual PFMs and other fusion baselines, while providing interpretable tissue visualisation.
  arXiv  Detail & Related papers  (2026-08-02T16:44:45Z)
• DriftST: One-Step Generative Inference of Spatial Transcriptomics from H\&E Histology [11.977375064177354]
  Inferring expression directly from Hematoxylin and Eosin stained histology offers a cost-effective alternative.<n>We propose DriftST, a unified framework for inferring spatially resolved gene expression from H&E images.<n> operating on a generic gene-panel representation, DriftST applies directly to both spot-level and cell-level data in one framework.
  arXiv  Detail & Related papers  (2026-07-06T07:22:58Z)
• FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction [21.300129464820984]
  Current models overlook essential biological structures like gene coordination and spatial distribution.<n>We introduce textbfFLAG, a diffusion-based framework that redefines this task as structured distribution modeling.<n>Our experiments demonstrate that FLAG is highly competitive in traditional accuracy.
  arXiv  Detail & Related papers  (2026-05-18T08:43:18Z)
• Central-to-Local Adaptive Generative Diffusion Framework for Improving Gene Expression Prediction in Data-Limited Spatial Transcriptomics [2.3129926848389633]
  Spatial Transcriptomics (ST) provides spatially resolved gene expression profiles within intact tissue architecture.<n>We present a Central-to-Local adaptive generative diffusion framework for ST (C2L-ST) that integrates large-scale morphological priors with limited molecular guidance.<n>C2L-ST provides a scalable and data-efficient framework for molecular-level data augmentation.
  arXiv  Detail & Related papers  (2026-03-27T02:32:00Z)
• Towards Spatial Transcriptomics-driven Pathology Foundation Models [32.70436266943553]
  We introduce a vision-omics self-supervised learning framework that infuses localized molecular information into pathology vision encoders.<n>We instantiate SEAL by training on over 700,000 paired gene expression spot-tissue region examples spanning tumor and normal samples from 14 organs.<n> SEAL encoders exhibit robust domain generalization on out-of-distribution and enable new cross-modal capabilities such as gene-to-image retrieval.
  arXiv  Detail & Related papers  (2026-02-15T15:06:45Z)
• MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology [2.4068264948068276]
  We introduce MoLF, a generative model for pan-cancer histogenomic prediction.<n>By dynamically routing inputs to specialized sub-networks, MoLF effectively decouples the optimization of diverse tissue patterns.<n>MoLF exhibits zero-shot generalization to cross-species data, suggesting it captures fundamental, conserved histo-molecular mechanisms.
  arXiv  Detail & Related papers  (2026-02-02T16:23:31Z)
• C3-Diff: Super-resolving Spatial Transcriptomics via Cross-modal Cross-content Contrastive Diffusion Modelling [5.986183062217602]
  This study presents a cross-modal cross-content contrastive diffusion framework, called C3-Diff, for ST enhancement with histology images as guidance.<n>To overcome the problem of low sequencing sensitivity in ST maps, we perform nosing-based information augmentation on the surface of feature unit hypersphere.<n>We propose a dynamic cross-modal imputation-based training strategy to mitigate ST data scarcity.
  arXiv  Detail & Related papers  (2025-11-04T13:12:25Z)
• GenAR: Next-Scale Autoregressive Generation for Spatial Gene Expression Prediction [15.143858141542532]
  GenAR is a multi-scale autoregressive framework that refines predictions from coarse to fine.<n>We introduce GenAR, a multi-scale autoregressive framework that refines predictions from coarse to fine.<n>GenAR achieves principled state-of-the-art performance, offering potential implications for precision medicine and cost-effective molecular profiling.
  arXiv  Detail & Related papers  (2025-10-05T18:28:21Z)
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation [85.58520120011269]
  We propose Composable Score-based Graph Diffusion model (CSGD), which extends score matching to discrete graphs via concrete scores.<n>We show that CSGD achieves state-of-the-art performance with a 15.3% average improvement in controllability over prior methods.<n>Our findings highlight the practical advantages of score-based modeling for discrete graph generation and its capacity for flexible, multi-property molecular design.
  arXiv  Detail & Related papers  (2025-09-11T13:37:56Z)
• AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models [49.550545038402184]
  We propose AdaFusion, a novel prompt-guided inference framework.<n>Our method compresses and aligns tile-level features from diverse models.<n>AdaFusion consistently surpasses individual PFMs across both classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-07T07:09:31Z)
• Modeling Gene Expression Distributional Shifts for Unseen Genetic Perturbations [44.619690829431214]
  We train a neural network to predict distributional responses in gene expression following genetic perturbations.<n>Our model predicts gene-level histograms conditioned on perturbations and outperforms baselines in capturing higher-order statistics.
  arXiv  Detail & Related papers  (2025-07-01T06:04:28Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• 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)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Efficient and Scalable Fine-Tune of Language Models for Genome Understanding [49.606093223945734]
  We present textscLingo: textscLanguage prefix ftextscIne-tuning for textscGentextscOmes. Unlike DNA foundation models, textscLingo strategically leverages natural language foundation models' contextual cues. textscLingo further accommodates numerous downstream fine-tune tasks by an adaptive rank sampling method.
  arXiv  Detail & Related papers  (2024-02-12T21:40:45Z)

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.