SNR-ST-Mix: 基于样本特异性邻域回归混合增强的空间转录组学深度神经网络插补
SNR-ST-Mix: Sample-specific Neighborhood Regression Mixup for Augmented Spatial Transcriptomics Imputation with Deep Neural Network
- Northwestern University（西北大学）
- Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对空间转录组数据噪声大、分辨率低的问题，提出SNR-ST-Mix数据增强框架，通过空间邻域约束和表达相似性加权混合生成生物合理的合成样本，提升深度神经网络插补性能。
AI中文摘要：
目的：空间转录组学（ST）能够在组织背景下测量基因表达。然而，这些测量通常噪声大、分辨率低且采样稀疏，限制了精细空间结构的恢复。深度神经网络已成为从组织学进行表达插补的强大工具，但其性能仍受限于有限的样本量和缺乏生物学信息的增强。大多数现有的学习增强策略是为分类任务而非回归任务设计的，忽略了空间和转录组关系，导致生物上不合理的插值，阻碍了预测性能。方法：为解决这些限制，我们提出SNR-ST-Mix，一种专门为ST数据设计的几何和表达感知数据增强框架。它将混合限制在点的k个最近空间邻域内，并基于表达相似性自适应加权插值系数，生成保留局部生物结构同时确保空间平滑性的增强样本。这种双重条件化产生合成样本，扩展了有效训练流形，促进了泛化，并在样本特异性训练下增强了预测稳定性。结果：使用各种组织类型的大量实验表明，SNR-ST-Mix在不需要架构更改或额外计算的情况下，始终优于传统增强方法。结论：SNR-ST-Mix为空间转录组学回归任务提供了一种有效且生物学原理的增强策略。通过显式利用空间几何和转录组相似性，它扩展了有效训练流形，并在不增加模型复杂度的情况下提高了预测性能。
英文摘要：
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.
