Snip: A package for data handling and model training using Single Nucleotide polymorphism data
A package for data handling and model training using Single Nucleotide polymorphism data. Implemented in Python and PyTorch.
🔧 Installation
To get started using this package install it using pip by running the following line in your terminal:
pip install git+https://github.com/KennethEnevoldsen/snipFor more detailed instructions on installing see the installation instructions.
Development Setup
To set up the project for development:
conda create -n snip python=3.9
conda activate snip
conda install poetry
peotry install👩💻 Getting started
Convert
To convert .bed files to .zarr simply run from your terminal:
snip convert sample.bed sample.zarror equivalently:
python -m snip convert sample.bed sample.zarrLearn more
To see a list of possible commands:
snip --helpTo find out more about each command:
snip convert --helpSlurm
This project uses slurm.
Slurm quick guide
**To run a job:** ```bash sbatch {filename}.sh -A NLPPred ``` Where `A` stands for account and `NLPPred` is the account. **Check the status of submitted queue:** ``` squeue -u {username} ``` **See available nodes:** ``` gnodes ``` **SSH to node:** ```bash ssh {node id} ``` **Run an interactive window:** ``` srun --pty -c 4 --mem=16g bash -A NLPPred ``` Using 4 cores and 16GB memory. For more on slurm please check out [this site](https://docs.rc.fas.harvard.edu/kb/convenient-slurm-commands).
💬 Where to ask questions
| Type | |
|---|---|
| 🚨 Bug Reports | GitHub Issue Tracker |
| 🎁 Feature Requests & Ideas | GitHub Issue Tracker |
| 👩💻 Usage Questions | GitHub Discussions |
| 🗯 General Discussion | GitHub Discussions |