Rxivist logo

Selene: a PyTorch-based deep learning library for biological sequence-level data

By Kathleen M Chen, Evan M. Cofer, Jian Zhou, Olga G Troyanskaya

Posted 10 Oct 2018
bioRxiv DOI: 10.1101/438291 (published DOI: 10.1038/s41592-019-0360-8)

To enable the application of deep learning in biology, we present Selene (https://selene.flatironinstitute.org/), a PyTorch-based deep learning library for fast and easy development, training, and application of deep learning model architectures for any biological sequences. We demonstrate how Selene allows researchers to easily train a published architecture on new data, develop and evaluate a new architecture, and use a trained model to answer biological questions of interest.

Download data

  • Downloaded 4,408 times
  • Download rankings, all-time:
    • Site-wide: 3,350
    • In bioinformatics: 267
  • Year to date:
    • Site-wide: 14,692
  • Since beginning of last month:
    • Site-wide: 32,879

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide