用稀疏自编码器解开神经网络中的概念混淆，实现细胞图像与基因数据的精准对齐。
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
- 通过稀疏自编码器解析高维生物数据中的概念重叠问题
- 恢复潜在空间几何结构，使图像表征更准确
- 无需空间转录组数据即可重建神经病理层级路径
人工智能正在改变我们解决生物学挑战的能力。在高维生物数据导致的维度瓶颈下，神经网络将不同概念压缩到低维空间，形成所谓的超位置现象。尽管这一现象普遍被认为影响可解释性，但其对潜在空间几何结构的破坏作用仍被严重忽视。本文利用在超过10万张患者来源的帕金森病及健康神经元多路复用图像上训练的稀疏自编码器（SAEs），成功解析了超位置问题。该方法通过转向可解释的潜在表示分析，规避了特征归因的数学非唯一性。理论与实证均表明，超位置会污染表征度量空间，而SAEs能有效恢复几何保真度。将这些几何净化后的表示作为单细胞状态向量，我们直接移植单细胞RNA测序（scRNA-seq）分析方法至图像域。最后，提出GW-map，采用格罗莫夫-沃瑟斯坦最优传输技术，从零开始将图像表示与真实scRNA-seq数据对齐。该方法重建了如钙离子-AIS支架等层次化神经病理通路，无需参考空间转录组数据，为空间生物学构建了可扩展的基础。代码已开源：https://github.com/jijihihi/Bio_superposition
原文摘要 · Abstract (English)
Artificial intelligence is transforming our capability to solve biological challenges. In dimensionality bottleneck regimes exacerbated by high-dimensional biological data, neural networks force distinct concepts into the lower dimensions known as superposition. Although this superposition is widely known to hinder interpretability, its impact on corrupting the geometry of latent spaces remains critically overlooked. Here, we utilized sparse autoencoders (SAEs) trained on over 100,000 multiplexed images of patient-derived Parkinson's disease and healthy neurons to resolve superposition. This approach bypasses the mathematical non-uniqueness of feature attribution by shifting to interpretable latent representation analysis. We theoretically and empirically demonstrate that superposition contaminates representational metric spaces, and thereby SAEs successfully recover geometric fidelity. By treating these geometrically purified representations as single-cell state vectors, we adapted single-cell RNA sequencing (scRNA-seq) data analysis methodologies directly to the image domain. Finally, we introduce GW-map, utilizing Gromov-Wasserstein optimal transport to align these image representations with authentic scRNA-seq data de novo. This coupling reconstructs hierarchical neuronal pathology pathways such as Calcium-AIS scaffold, without reference spatial transcriptomics, establishing a scalable foundation for spatial biology. Code is available at https://github.com/jijihihi/Bio\_superposition
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。