Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching

Tinglin Huang, Tianyu Liu, Mehrtash Babadi, Wengong Jin, Zhitao Ying
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25550-25565, 2025.

Abstract

Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental facilities. Prior works sought to predict ST from whole-slide histology images to accelerate this process, but they suffer from two major limitations. First, they do not explicitly model cell-cell interaction as they factorize the joint distribution of whole-slide ST data and predict the gene expression of each spot independently. Second, their encoders struggle with memory constraints due to the large number of spots (often exceeding 10,000) in typical ST datasets. Herein, we propose STFlow, a flow matching generative model that considers cell-cell interaction by modeling the joint distribution of gene expression of an entire slide. It also employs an efficient slide-level encoder with local spatial attention, enabling whole-slide processing without excessive memory overhead. On the recently curated HEST-1k and STImage-1K4M benchmarks, STFlow substantially outperforms state-of-the-art baselines and achieves over 18% relative improvements over the pathology foundation models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-huang25t, title = {Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching}, author = {Huang, Tinglin and Liu, Tianyu and Babadi, Mehrtash and Jin, Wengong and Ying, Zhitao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {25550--25565}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/huang25t/huang25t.pdf}, url = {https://proceedings.mlr.press/v267/huang25t.html}, abstract = {Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental facilities. Prior works sought to predict ST from whole-slide histology images to accelerate this process, but they suffer from two major limitations. First, they do not explicitly model cell-cell interaction as they factorize the joint distribution of whole-slide ST data and predict the gene expression of each spot independently. Second, their encoders struggle with memory constraints due to the large number of spots (often exceeding 10,000) in typical ST datasets. Herein, we propose STFlow, a flow matching generative model that considers cell-cell interaction by modeling the joint distribution of gene expression of an entire slide. It also employs an efficient slide-level encoder with local spatial attention, enabling whole-slide processing without excessive memory overhead. On the recently curated HEST-1k and STImage-1K4M benchmarks, STFlow substantially outperforms state-of-the-art baselines and achieves over 18% relative improvements over the pathology foundation models.} }
Endnote
%0 Conference Paper %T Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching %A Tinglin Huang %A Tianyu Liu %A Mehrtash Babadi %A Wengong Jin %A Zhitao Ying %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-huang25t %I PMLR %P 25550--25565 %U https://proceedings.mlr.press/v267/huang25t.html %V 267 %X Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental facilities. Prior works sought to predict ST from whole-slide histology images to accelerate this process, but they suffer from two major limitations. First, they do not explicitly model cell-cell interaction as they factorize the joint distribution of whole-slide ST data and predict the gene expression of each spot independently. Second, their encoders struggle with memory constraints due to the large number of spots (often exceeding 10,000) in typical ST datasets. Herein, we propose STFlow, a flow matching generative model that considers cell-cell interaction by modeling the joint distribution of gene expression of an entire slide. It also employs an efficient slide-level encoder with local spatial attention, enabling whole-slide processing without excessive memory overhead. On the recently curated HEST-1k and STImage-1K4M benchmarks, STFlow substantially outperforms state-of-the-art baselines and achieves over 18% relative improvements over the pathology foundation models.
APA
Huang, T., Liu, T., Babadi, M., Jin, W. & Ying, Z.. (2025). Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:25550-25565 Available from https://proceedings.mlr.press/v267/huang25t.html.

Related Material