Missing value Imputation for Spatially resolved Transcriptomics (MIST)

Reference

Wang, L., Maletic-Savatic, M. & Liu, Z. Region-specific denoising identifies spatial co-expression patterns and intra-tissue heterogeneity in spatially resolved transcriptomics data. Nat Commun 13, 6912 (2022). https://doi.org/10.1038/s41467-022-34567-0

Install

We recommend using a conda environment to automatically install all required dependencies. Conda installation guide can be found at https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html. After installing conda, run the following command to install a ReST environment:

conda env create -f environment.yml

Or, users could manually install all required dependencies as below:

• pandas=0.25.3
• numpy=1.18.5
• matplotlib=3.3.4
• statsmodels=0.12.0
• scipy=1.6.1
• tqdm=4.56.0
• imageio
• alphashape
• descartes
• joblib
• gseapy

Input data format

1. For 10X Visium, Space Ranger Folder with the following contents:

• [Folder]/spatial/tissue_positions_list.csv
• [Folder]/filtered_feature_bc_matrix.h5

2. adata:

• processed AnnData object with count, spot and gene meta data frame

3. General spatial transcriptomics data:

• counts - gene expression data frame in Pandas.DataFrame format.
• coordinates - spot meta data frame, with x, y columns denoting coordinates.
• gene_df - gene meta data frame.

Running MIST

Please read Tutorial 1 - MIST region detection, functional annotation and imputation (Melanoma).ipynb for instructions.