提出hSNMF方法，提升空间转录组数据的聚类效果与生物一致性。
hSNMF: Hybrid Spatially Regularized NMF for Image-Derived Spatial Transcriptomics
- 融合空间邻近与转录组相似性，通过混合邻接图增强聚类。
- 在胆管癌数据上实现聚类紧凑性（CHAOS<0.004）与分离度（Silhouette>0.12）显著提升。
- 适合研究肿瘤微环境、空间异质性的生物学家和计算科学家。
高分辨率空间转录组平台（如Xenium）生成单细胞图像，同时保留分子与空间信息，但其极高维度给表示学习与聚类带来挑战。本研究基于Xenium平台获取的肿瘤微阵列（TMA）组织图像，将其转换为细胞-基因矩阵用于计算分析。我们评估并扩展了非负矩阵分解（NMF）方法，引入两种空间正则化变体：首先提出空间NMF（SNMF），通过在空间邻域内扩散每个细胞的NMF因子向量，强制局部空间平滑；其次提出混合空间NMF（hSNMF），在空间正则化NMF后，利用可调混合参数alpha的混合邻接图（结合接触半径图与转录组相似性）进行Leiden聚类。在胆管癌数据集上，SNMF与hSNMF显著提升空间紧凑性（CHAOS < 0.004，Moran's I > 0.96）、聚类分离度（轮廓系数 > 0.12，DBI < 1.8）及生物学一致性（CMC与富集分析）。代码与实现见：https://github.com/ishtyaqmahmud/hSNMF
原文摘要 · Abstract (English)
High-resolution spatial transcriptomics platforms, such as Xenium, generate single-cell images that capture both molecular and spatial context, but their extremely high dimensionality poses major challenges for representation learning and clustering. In this study, we analyze data from the Xenium platform, which captures high-resolution images of tumor microarray (TMA) tissues and converts them into cell-by-gene matrices suitable for computational analysis. We benchmark and extend nonnegative matrix factorization (NMF) for spatial transcriptomics by introducing two spatially regularized variants. First, we propose Spatial NMF (SNMF), a lightweight baseline that enforces local spatial smoothness by diffusing each cell's NMF factor vector over its spatial neighborhood. Second, we introduce Hybrid Spatial NMF (hSNMF), which performs spatially regularized NMF followed by Leiden clustering on a hybrid adjacency that integrates spatial proximity (via a contact-radius graph) and transcriptomic similarity through a tunable mixing parameter alpha. Evaluated on a cholangiocarcinoma dataset, SNMF and hSNMF achieve markedly improved spatial compactness (CHAOS < 0.004, Moran's I > 0.96), greater cluster separability (Silhouette > 0.12, DBI < 1.8), and higher biological coherence (CMC and enrichment) compared to other spatial baselines. Availability and implementation: https://github.com/ishtyaqmahmud/hSNMF
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。