SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics

Qingtian Zhu, Yumin Zheng, Yuling Sang, Yifan Zhan, Ziyan Zhu, Jun Ding, Yinqiang Zheng
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80448-80462, 2025.

Abstract

Spatial Transcriptomics (ST) is a method that captures gene expression profiles aligned with spatial coordinates. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can enhance both the spatial density and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms under varying degradations, SUICA outperforms both conventional INR variants and SOTA methods regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhu25af, title = {{SUICA}: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics}, author = {Zhu, Qingtian and Zheng, Yumin and Sang, Yuling and Zhan, Yifan and Zhu, Ziyan and Ding, Jun and Zheng, Yinqiang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {80448--80462}, 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/zhu25af/zhu25af.pdf}, url = {https://proceedings.mlr.press/v267/zhu25af.html}, abstract = {Spatial Transcriptomics (ST) is a method that captures gene expression profiles aligned with spatial coordinates. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can enhance both the spatial density and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms under varying degradations, SUICA outperforms both conventional INR variants and SOTA methods regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis.} }
Endnote
%0 Conference Paper %T SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics %A Qingtian Zhu %A Yumin Zheng %A Yuling Sang %A Yifan Zhan %A Ziyan Zhu %A Jun Ding %A Yinqiang Zheng %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-zhu25af %I PMLR %P 80448--80462 %U https://proceedings.mlr.press/v267/zhu25af.html %V 267 %X Spatial Transcriptomics (ST) is a method that captures gene expression profiles aligned with spatial coordinates. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can enhance both the spatial density and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms under varying degradations, SUICA outperforms both conventional INR variants and SOTA methods regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis.
APA
Zhu, Q., Zheng, Y., Sang, Y., Zhan, Y., Zhu, Z., Ding, J. & Zheng, Y.. (2025). SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:80448-80462 Available from https://proceedings.mlr.press/v267/zhu25af.html.

Related Material