arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.17699cs.AIcs.LGq-bio.GN
收藏

理解基因表达到图像的学习:空间结构与信息保真度

Understanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity

University of Electronic Science and Technology of China(电子科技大学);Xiamen University(厦门大学);Yuelushan Laboratory(岳麓山实验室)

Xiaoqing Lian, Pei Liu, Jiahui Tan, Quan Zou, Chen Lin, Xiangxiang Zeng

AI总结:

该研究针对基因表达到图像(GE2I)学习,揭示了空间平滑度与基因级保真度的权衡,明确了基因到像素分配方式对预测性能的影响,为相关应用提供了实用指导。

摘要:

单细胞RNA测序(scRNA-seq)可实现细胞层面的生物异质性分析,但从高维、无序的基因表达谱中学习有效表征仍具挑战性。基因表达到图像(GE2I)提供了一种有效学习策略,其通过将基因值排列在像素网格上以适配卷积神经网络,但其潜在机制尚不明确。我们在保持网络和训练流程固定的情况下,针对全转录组数据研究GE2I。研究结果揭示了空间平滑度与基因级保真度之间的权衡:结构化映射会产生平滑的低频模式,支持更快的早期优化;而将多个基因分配到同一像素会掩盖表达差异,可能降低预测性能。这种权衡解释了当需表征大量基因时,随机映射为何能与结构化布局相媲美。即使图像平滑度下降,一对一的基因到像素分配也能在测试的所有视觉骨干网络上提升预测效果。我们进一步发现,预训练和数据增强的益处取决于骨干网络和映射方式。这些发现为像素分配以及将视觉先验迁移至基因表达数据提供了实用指导。

英文摘要:

Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene expression profiles remains challenging. Gene Expression-to-Image (GE2I) offers an effective learning strategy by arranging gene values on pixel grids for convolutional neural networks, but its underlying mechanisms remain unclear. We study GE2I on full-transcriptome data while keeping the network and training procedure fixed. Our results reveal a trade-off between spatial smoothness and gene-level fidelity. Structured mappings produce smooth, low-frequency patterns that support faster early optimization, whereas assigning multiple genes to the same pixel obscures expression differences and can reduce predictive performance. This trade-off explains why random mappings can compete with structured layouts when many genes are represented. One-to-one gene-to-pixel assignment improves prediction across the tested visual backbones even when image smoothness decreases. We further find that the benefits of pretraining and augmentation depend on the backbone and mapping. These findings provide practical guidance for pixel allocation and the transfer of vision priors to gene expression data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑