Welcome to DeSide’s documentation!

The usage of DeSide as a Python package is described in this documentation.


What is DeSide?

DeSide is a deep-learning and single-cell-based deconvolution method for solid tumors. It enables the inference of cellular proportions of different cell types from bulk RNA-seq data. DeSide was developed by Xin Xiong and Yerong Liu under the guidance and collaboration of the Li(X) Lab at the Institute for Synthetic Biology Research (iSynBio), Chinese Academy of Sciences, and the Tian Lab at Hong Kong Baptist University (HKBU).

Contents

Our manuscript consists of the following four parts (see figure below):

  • DNN Model

  • Single Cell Dataset Integration

  • Cell Proportion Generation

  • Bulk Tumor Synthesis

Overview of DeSide

Please check Usage for more details of each part.

Indices and tables