Installation
GPMelt implementation is based on the Python (Van Rossum and Drake 2009) package GPyTorch (Gardner et al. 2018), and the full workflow has been encapsulated in a Nextflow (Di Tommaso et al. 2017) pipeline. This setup ensures simple installation, supports parallel computation, and offers a portable solution for deployment on both local computers and high-performance computing (HPC) clusters.
1 Installing Nextflow and Docker
Before we start, make sure Nextflow and Docker (or any containerization tool compatible with Docker containers) is installed either locally on your machine, or set up on the HPC cluster that you are planning to use.
2 GPMelt repository
GPMelt implementation is found on the following gitlab repository.
- Clone the repository:
git clone https://git.embl.de/grp-savitski/gpmelt.git- Navigate to the Nextflow directory:
cd NextflowThis directory contains the Nextflow pipeline GPMelt_workflow.nf (and the sub-pipelines: .nffiles ), the config files (.config) and the python code (in the bin directory). The dummy_data folder contains example datasets.