- recipe prokbert
ProkBERT is a genomic language model specifically designed for microbiome applications. It leverages the power of machine learning to decipher complex microbial interactions, predict functionalities, and uncover novel patterns in extensive datasets. The ProkBERT model family, built on transfer learning and self-supervised methodologies, capitalizes on the abundant genomic data available.
- Homepage:
- Documentation:
- License:
MIT / MIT
- Recipe:
- Links:
- package prokbert¶
- versions:
0.0.44-0,0.0.40-0- depends biopython:
- depends datasets:
>=2.0.1- depends h5py:
>=3.7.0- depends pandas:
>=2.0.0- depends python:
>=3.10- depends pytorch:
- depends scikit-learn:
>=1.2.2- depends scipy:
>=1.10.0- depends tables:
>=3.8.0- depends torchvision:
- depends transformers:
>=4.23- requirements:
Installation
You need a conda-compatible package manager (currently either micromamba, mamba, or conda) and the Bioconda channel already activated (see set-up-channels).
While any of above package managers is fine, it is currently recommended to use either micromamba or mamba (see here for installation instructions). We will show all commands using mamba below, but the arguments are the same for the two others.
Given that you already have a conda environment in which you want to have this package, install with:
mamba install prokbert and update with:: mamba update prokbert
To create a new environment, run:
mamba create --name myenvname prokbert
with
myenvnamebeing a reasonable name for the environment (see e.g. the mamba docs for details and further options).Alternatively, use the docker container:
docker pull quay.io/biocontainers/prokbert:<tag> (see `prokbert/tags`_ for valid values for ``<tag>``)
Download stats¶
Link to this page¶
Render an 
badge with the following MarkDown:
[](http://bioconda.github.io/recipes/prokbert/README.html)
