analiza aiqbench
SNR-ST-Mix introduces a specialized data augmentation framework for spatial transcriptomics that addresses the limitations of standard mixup techniques in regression tasks. By constraining interpolation to spatial neighbors and weighting by expression similarity, the method preserves local biological structure while improving generalization without requiring architectural changes. This approach effectively expands the training manifold for deep neural networks handling noisy, low-resolution gene expression data.
SNR-ST-Mix: Sample-specific Neighborhood Regression Mixup for Augmented Spatial Transcriptomics Imputation with Deep Neural Network
arXiv:2606.08712v1 Announce Type: new Abstract: Purpose: Spatial transcriptomics (ST) enables gene expression measurements within the tissue context. However, these measurements are often noisy, low-resolution, and sparsely sampled, which limits the recovery of fine spatial structure. Deep neural networks have become powerful tools for expression imputation from histology, but their performance remains constrained by limited sample sizes and a lack of biologically informed augmentation. Most of the existing augmentation strategies for learning are designed for classification tasks rather than regression, which neglect spatial and transcriptomic relationships, leading to biologically implausible interpolations that hinder prediction performance. Approach: To address these limitations, we propose SNR-ST-Mix, a geometry- and expression-aware data augmentation framework designed specifically for ST data. It constrains mixing to a spot's k-nearest spatial neighbors and adaptively weights interpolation coefficients based on expression similarity, generating augmented samples that preserve local biological structure while ensuring spatial smoothness. This dual conditioning yields synthetic examples that expand the effective training manifold, promote generalization, and enhance prediction stability under sample-specific training. Results: Extensive experiments with various tissue types demonstrate that SNR-ST-Mix consistently outperforms conventional augmentation methods without requiring architectural changes or additional computation. Conclusions: SNR-ST-Mix provides an effective and biologically principled augmentation strategy for spatial transcriptomics regression tasks. By explicitly leveraging spatial geometry and transcriptomic similarity, it expands the effective training manifold and improves predictive performance without increasing model complexity.
Abstract:Purpose: Spatial transcriptomics (ST) enables gene expression measurements within the tissue context. However, these measurements are often noisy, low-resolution, and sparsely sampled, which limits the recovery of fine spatial structure. Deep neural networks have become powerful tools for expression imputation from histology, but their performance remains constrained by limited sample sizes and a lack of biologically informed augmentation. Most of the existing augmentation strategies for learning are designed for classification tasks rather than regression, which neglect spatial and transcriptomic relationships, leading to biologically implausible interpolations that hinder prediction performance. Approach: To address these limitations, we propose SNR-ST-Mix, a geometry- and expression-aware data augmentation framework designed specifically for ST data. It constrains mixing to a spot's k-nearest spatial neighbors and adaptively weights interpolation coefficients based on expression similarity, generating augmented samples that preserve local biological structure while ensuring spatial smoothness. This dual conditioning yields synthetic examples that expand the effective training manifold, promote generalization, and enhance prediction stability under sample-specific training. Results: Extensive experiments with various tissue types demonstrate that SNR-ST-Mix consistently outperforms conventional augmentation methods without requiring architectural changes or additional computation. Conclusions: SNR-ST-Mix provides an effective and biologically principled augmentation strategy for spatial transcriptomics regression tasks. By explicitly leveraging spatial geometry and transcriptomic similarity, it expands the effective training manifold and improves predictive performance without increasing model complexity.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2606.08712 [cs.LG]
(or arXiv:2606.08712v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.08712 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 322 cuvinte
Subiecte conexe
inversedMixup: Data Augmentation via Inverting Mixed Embeddings
arXiv · 10 iun. 2026
Spatial Transcriptomics as Images for Large-Scale Pretraining
arXiv · 4 iun. 2026
LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration
arXiv · 21 iul. 2026
Exploring self-distilled reasoning for supervised fine-tuning with Amazon Nova
AWS · 21 iul. 2026