For more details, please refer to our paper [Spatial transcriptomics reveals distinct cellular niches of resistance to immune checkpoint blockade in melanoma].
This repository contains the code for NIMO. Leveraging single-cell spatially resolved transcriptomics data, NIMO models local cellular neighbourhoods to identify recurring spatial patterns (niches) and predict patient response to immune checkpoint blockade.
Note: A GPU is strongly recommended for the deep learning component.
- Clone repository:
git clone https://github.com/xhelenfu/NIMO.git- Create virtual environment:
conda create --name nimo python=3.12- Activate virtual environment:
conda activate nimo- Install dependencies:
cd nimo
pip install -r requirements.txtInstallation is expected to be completed within a few minutes.
Please check out Training and validation for key steps in using NIMO.
If NIMO has assisted you with your work, please kindly cite our paper.