INRscrecon: Enhancing 3D Spatial Transcriptomics Reconstruction through Implicit Neural Representations

ICLR 2025 Conference Submission239 Authors

13 Sept 2024 (modified: 26 Nov 2024)ICLR 2025 Conference SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Spatial Transcriptomics reconstruction, Implicit Neural Representations, alignment
Abstract: Single-cell spatial transcriptomics (scST) technologies have revolutionized our understanding of the complex three-dimensional cellular landscapes of tissues. However, the accuracy of spatial expression profiles is often compromised by missing or distorted experimental data. To address this challenge, we introduce INRscrecon, a novel framework that leverages Implicit Neural Representations (INRs) known for their continuous signal encoding capabilities. INRscrecon accurately predicts and corrects spatial expressions, enhancing the clarity of 3D tissue reconstructions. Our study demonstrates the efficacy of INRscrecon across various datasets and dimensions, highlighting its potential to restore spatial expression with high precision. The findings suggest broader applications for INR-based methodologies in spatial transcriptomics, paving the way for more accurate and detailed analysis of cellular interactions within tissues. Future research may expand on the incorporation of INR techniques in spatial transcriptomics to further enhance analytical capabilities.
Supplementary Material: pdf
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 239
Loading