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

TL;DR: SUICA = Spatial Transcriptomics + Implicit Neural Representations → Restored Authenticity + Enriched Bio-conservation

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.

Lay Summary: Spatial Transcriptomics (ST) is a technology that allows scientists to understanding how genes are expressed across different regions of tissues is crucial for studying biological processes and diseases. However, analyzing this kind of data is challenging because it is both very large and highly complex. To address this, we developed a new computational tool called SUICA, which uses advanced deep learning techniques to model gene expression in a more continuous and compact way. Overall, SUICA not only improves the quality of spatial gene expression maps but also enhances the biological insights that researchers can gain from these datasets, opening new possibilities for studying tissue biology and disease mechanisms.

Link To Code: https://github.com/Szym29/SUICA

Primary Area: Applications->Health / Medicine

Keywords: Spatial Transcriptomics, Implicit Neural Representations

Submission Number: 1814