Welcome to SEDR’s documentation!

SEDR – Unsupervised spatially embedded deep representation of spatial transcriptomics.

• Installation
• Tutorial 1: 10X Visium data
• Tutorial 2. Imputation
• Tutorial 3. Use SEDR to do batch integration.
• Tutorial 4: Use SEDR to process Stereo-seq data

Overview

We present SEDR, an unsupervised spatially embedded deep representation of both transcript and spatial information. The SEDR pipeline uses a deep autoencoder coupled with a masked self-supervised learning mechanism to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder.

Citation

Huazhu Fu, Hang Xu, Kelvin Chong, Mengwei Li, Hong Kai Lee, Kok Siong Ang, Ao Chen, Ling Shao, Longqi Liu, and Jinmiao Chen, “Unsupervised Spatial Embedded Deep Representation of Spatial Transcriptomics”, bioRxiv (2021).