📥 Installation
DAPT (Descriptor-based Adaptive Perturbation Transformer) is a Python-based deep learning framework. You can install the required dependencies using standard package managers or directly from the source code.
⚠️ Prerequisites
Before installing DAPT, please ensure your system meets the following requirements:
- Python Version: Python 3.8 or higher is required.
- Hardware: A CUDA-enabled GPU is highly recommended for efficient Graph Neural Network (GNN) message passing and large batch predictions.
- System RAM: High system memory is necessary to handle
AnnDataobjects containing over 100,000 cells. - Environment Manager: We strongly recommend using
condato manage environments and prevent dependency conflicts. - Python package installer: pip is required to install all the necessary python packages on your environment.
📦 Dependencies
- torch
- numpy
- pandas
- scikit-learn
- torch_geometric
- math
- seaborn
- matplotlib
- json
- yaml
- pickle
- streamlit
⬇️ Installation Steps
Follow these steps to set up the DAPT environment on your local machine.