Welcome to stSCI’s documentation!

Overview

Spatial transcriptomics (ST) data reveals the locations of transcriptomes, offering crucial perspectives but at a compromised quality. Integrating ST data with single-cell transcriptomics (SC) data has proven to be an effective strategy for enhancing the quality of ST data, as demonstrated by previous research. We introduce stSCI (ST-SC Integration), a novel computational method that seamlessly fuses SC and ST data into a unified embedding space by incorporating a newly designed fusion module. Utilizing several simulated and real datasets, stSCI demonstrates its performance in batch correction across the two omics data, in clustering, and deconvolution of ST data, as well as in reconstructing spatial coordinates for SC data. Additionally, stSCI shows its potential for annotating ST data using only marker genes and cell types derived from SC data. Moreover, experiment result shows that stSCI performing well with both sequencing-based and imaging-based ST data, highlighting its capability as a powerful tool for comprehensive biological system analysis.

Contents

• Installation
  • Software Dependencies
  • Setup by Docker (Recommended)
  • Manually setup
• Parameter introduction
  • stSCI.train
  • stSCI.eval
• Clustering for DLPFC dataset
  • Data preprocessing
  • Model training
  • Evaluation
• Clustering for multiple mouse embryo dataset
  • Data preprocessing
  • Model training
  • Visualization
• Deconvolution for the simulated mouse embryo data
  • Data preprocessing
  • Model training
  • Evaluation
• Deconvolution for human lymph nodes
  • Data preprocessing
  • Model training
  • Evaluation
• Label annotating for human breast cancer dataset
  • Data preprocessing
  • Model training
  • Generate the correlation matrix
• Reconstructing spatial coordination for mouse brain cortex
  • Data preprocessing
  • Model training
  • Visualization
• Integrating SC and ST data in human liver dataset
  • Data preprocessing
  • Model training
  • UMAP visualization