STAGATE
论文阅读记录STAGATE 标题：Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder 作者：University of Chinese Academy of Sciences 发表会议/期刊：Nature Communications 年份：2022 链接：STAGATE 主要内容简介 Motivation: 邻域相似性是预定义的，无法自适应学习。 方法与创新点 总体框架： 方法概述： Construction of SNN (Construction of cell type-aware SNN (optional)) Graph attention auto-encoder Encoder Decoder (迭代和encoder相似) graph attention layer -graph...
Spatial-MGCN and MAFN details supplement
论文阅读记录Spatial-MGCN 标题：Spatial-MGCN: a novel multi-view graph convolutional network for identifying spatial domains with attention mechanism 作者：Hunan University 发表会议/期刊：Briefings in Bioinformatics 年份：2023 链接：Spatial-MGCN 主要内容简介 Motivation：While increasingly computational methods have been developed for spatial domain detection, most of them cannot adaptively learn the complex relationship between gene expression and spatial information, leading to sub-optimal...
STMGraph
论文阅读记录STMGraph 标题：STMGraph: spatial-context-aware of transcriptomes via a dual-remasked dynamic graph attention model 作者：Fujian Agriculture and Forestry University 发表会议/期刊：Briefings in Bioinformatics 年份：2025 链接：STMGraph 主要内容简介 Motivation：the current ST integration algorithm ignores for ST dropouts, which impedes the spatial-aware of ST features, resulting in challenges in the accuracy and robustness of microenvironmental heterogeneity detecting, spatial domain clustering, and...
基于代码理解MAFN
论文阅读记录1. 基本信息 论文题目：Multi-View Adaptive Fusion Network for Spatially Resolved Transcriptomics Data Clustering 作者/机构：China University of Geosciences 会议/期刊：IEEE TRANSACTIONS 年份：DECEMBER 2024 论文链接：MAFN_IEEE 2. 方法总览 总体框架： 关键技术路线： spatial graph G1(euclidean distance & r), feature graph G2(cosine similarity & kNN) Inter-View Complementary Features Learning (GCN) Intra-View Discriminative Features Learning(GCN + Lc –> (S-I)^2) Cross-View Attention Module (CAM) Gene...
Deep Fusion Clustering Network
📖 论文阅读记录1. 基本信息 论文题目：Deep Fusion Clustering Network 作者/机构：National University of Defense Technology 会议/期刊：AAAI 年份：2021 2. 研究背景 研究领域：深度聚类 主要问题： 缺乏动态融合机制来选择性整合和精炼图结构与节点属性的信息以达成共识表示学习； 未能从双方提取信息以生成鲁棒的目标分布（即“真实”软标签）。 相关工作： 属性图聚类 目标分布生成 3. 核心贡献 ✨ 创新点：通过SAIF模块实现AE与IGAE的特征深度融合 4. 方法 SAIF总体框架： 标号： Fusion-based Autoencoders Structure and Attribute Information Fusion Joint loss and Optimization 5. 实验 数据集： ...
单细胞算法典型任务
📖 论文阅读记录TASK
