CosMAP：用于组学和系谱数据降维的对比流形近似与投影
CosMAP: Contrastive Manifold Approximation and Projection for Dimensionality Reduction of Omics and Genealogical Data
- Institut national de la recherche scientifique (INRS)（国家科学研究院）
- Centre Armand-Frappier Santé Biotechnologie (INRS-AFSB)（阿尔芒-弗拉皮尔健康生物技术中心）
- Unité mixte de recherche en santé durable (UMR INRS–UQAC)（可持续健康联合研究单位）
- Université du Québec à Chicoutimi (UQAC)（希库蒂米魁北克大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对组学和系谱数据的高维稀疏等特性，提出基于UMAP扩展的CosMAP降维方法，经多类数据集验证，可生成更连贯嵌入与清晰全局结构，为复杂数据探索提供稳健框架。
AI中文摘要：
组学数据集，尤其是单细胞RNA测序数据，具有高维、稀疏、含噪且零值主导的特点，难以生成忠实的低维表示。现有降维方法可能扭曲局部邻域、全局结构或有意义群体的内聚性，在系谱数据中也存在类似局限。我们提出对比流形近似与投影（Contrastive Manifold Approximation and Projection，CosMAP），这是一种基于图的无监督降维方法，用于生成忠实且可解释的嵌入。CosMAP扩展了UMAP的基于图的框架，将余弦相似度邻域与温度归一化的对比亲和力相结合，通过吸引-排斥目标在嵌入空间中优化；还采用两阶段优化策略：首先学习中间高维表示，再用其重构邻域图并初始化最终低维嵌入。我们在MNIST和USPS手写数字数据集、小鼠视网膜与皮层单细胞RNA测序数据集，以及源自BALSAC-CARTaGENE的大型系谱亲属关系数据集上评估CosMAP。与最先进的降维方法相比，CosMAP生成更连贯的可视化表示，提升邻域保留效果，为数字类别、生物细胞群体和区域系谱模式提供更清晰的全局结构。这些结果表明，CosMAP为复杂、稀疏、高维数据的探索性分析提供了稳健框架，其实现代码公开于指定网址。
英文摘要：
Omics datasets, particularly single-cell RNA sequencing data, are high-dimensional, sparse, noisy, and dominated by zero values, making faithful low-dimensional representation challenging. Existing dimensionality-reduction methods may distort local neighbourhoods, global organization, or the cohesion of meaningful populations, with similar limitations arising in genealogical data. We introduce Contrastive Manifold Approximation and Projection (CosMAP), a graph-based unsupervised dimensionality-reduction method for producing faithful and interpretable embeddings. CosMAP extends the graph-based framework of UMAP by combining cosine-similarity neighbourhoods with temperature-normalized contrastive affinities, which are optimized in the embedding space using an attractive--repulsive objective. It further employs a two-phase refinement strategy: an intermediate higher-dimensional representation is first learned and then used to reconstruct the neighbourhood graph and initialize the final low-dimensional embedding. We evaluate CosMAP on MNIST and USPS handwritten-digit datasets, mouse retina and cortex single-cell RNA-sequencing datasets, and a large genealogical kinship dataset derived from BALSAC-CARTaGENE. Compared with state-of-the-art dimensionality-reduction methods, CosMAP produces more coherent visual representations, improves neighbourhood preservation, and provides clearer global organization of digit classes, biological cell populations, and regional genealogical patterns. These results indicate that CosMAP offers a robust framework for exploratory analysis of complex, sparse, high-dimensional data. The implementation is publicly available at https://github.com/FenosoaRandrianjatovo/CosMAP-dr.
