This repository contains the implementation of the paper available on OpenReview.
To get started, follow these steps:
-
Clone the repository:
git clone https://github.com/jichunxie/xMINT_manu_support cd xMINT_manu_support
-
Create a Conda environment with Python 3.8:
conda create -n xmint_env python=3.8 conda activate xmint_env
-
Install the required packages using the
requirements.txt
file:pip install -r requirements.txt
You will need paired Xenium datasets from the same tissue to get started.
For each dataset, the input data should include:
- Xenium Output Bundle: The data generated by Xenium.
- Post-Xenium H&E Image: An OME-TIFF file of the H&E stained image corresponding to the Xenium output.
Unzip the Xenium Output Bundle folder and place the H&E image into the output folder.
Our paper utilized the following datasets:
- FFPE Human Breast with Pre-designed Panel 1 Standard
- Human Tonsil Data: Xenium Human Multi-Tissue and Cancer Panel 1 Standard
To run the pipeline, follow these steps:
-
Run the preprocessing script:
python preprocess_to_sequence.py
-
Run the main xMINT script:
python xmint_main.py
Before running these scripts, ensure you update the sample names and other customized parameters as needed.