biobb-pytorch 5.2.2

biobb_pytorch is the Biobb module collection to create and train ML & DL models.

biobb_pytorch

Introduction

biobb_pytorch is the Biobb module collection to create and train ML & DL models using the popular PyTorch Python library. Biobb (BioExcel building blocks) packages are Python building blocks that create new layer of compatibility and interoperability over popular bioinformatics tools. The latest documentation of this package can be found in our readthedocs site: latest API documentation.

Version

v5.2.2 2025.2

Installation

Using PIP:

Important: PIP only installs the package. All the dependencies must be installed separately. To perform a complete installation, please use ANACONDA, DOCKER or SINGULARITY.

• Installation:

    pip install "biobb_pytorch>=5.2.2"
  

• Usage: Python API documentation

Using ANACONDA:

• Installation:

    conda install -c bioconda "biobb_pytorch>=5.2.2"
  

• Usage: With conda installation BioBBs can be used with the Python API documentation and the Command Line documentation

Using DOCKER:

• Installation:

    docker pull quay.io/biocontainers/biobb_pytorch:5.2.2--pyhad2cae4_0
  

• Usage:

    docker run quay.io/biocontainers/biobb_pytorch:5.2.2--pyhad2cae4_0 <command>
  

Using SINGULARITY:

MacOS users: it's strongly recommended to avoid Singularity and use Docker as containerization system.

• Installation:

    singularity pull --name biobb_pytorch.sif https://depot.galaxyproject.org/singularity/biobb_pytorch:5.2.2--pyhad2cae4_0
  

• Usage:

    singularity exec biobb_pytorch.sif <command>
  

The command list and specification can be found at the Command Line documentation.

Copyright & Licensing

This software has been developed in the MMB group at the BSC & IRB for the European BioExcel, funded by the European Commission (EU Horizon Europe 101093290, EU H2020 823830, EU H2020 675728).

• (c) 2015-2026 Barcelona Supercomputing Center
• (c) 2015-2026 Institute for Research in Biomedicine

Licensed under the Apache License 2.0, see the file LICENSE for details.