论文阅读记录

GraphST

  • 标题：Spatially informed clustering, integration,and deconvolution of spatial transcriptomics with GraphST
  • 作者：National University of Singapore (NUS)
  • 发表会议/期刊：Nature Communications
  • 年份：2023
  • 链接：GraphST

主要内容简介

  • Motivation:
    1. 反卷积未利用空间信息
    2. 多样本整合未利用空间信息

方法与创新点

  • 总体框架：

    Generalization

  • 方法概述：

    1. graph self-supervised contrastive learning framework：

      • data augmentation
      • GNN-based encoder for representation learning

      Generalization

      • self-supervised contrastive learning for representation refinement

      Generalization
      Generalization
      Generalization

    2. Vertical and horizontal integration of multiple tissues via implicit batch effect correction(By PASTE)

    3. Spatially informed contrastive learning for scRNA-seq and ST data integration

      Generalization
      Generalization

      1. Spot-targeted annotation transfer
      2. Domain-targeted annotation transfer

      Generalization
      Generalization

任务

  1. Spatial clustering
  2. Multi-sample integration
  3. ST and scRNA-seq integration

完结撒花