NucleoFind

Nucleic acid electron density interpretation remains a difficult problem for computer programs to deal with. Programs tend to rely on exhaustive searches to recognise characteristic features. NucleoFind is a deep-learning-based approach to interpreting and segmenting electron density. Using a crystallographic map, the positions of the phosphate group, sugar ring and nitrogenous base group are able to be predicted with high accuracy.

Model Details

Model Description

NucleoFind is based on a 3D-UNet architecture.

  • Developed by: Jordan Dialpuri, Jon Agirre, Kathryn Cowtan and Paul Bond, York Structural Biology Laboratory, University of York
  • Funded by BBSRC and The Royal Society
  • Model type: Multiclass
  • Language(s) (NLP): Python
  • License: LGPL-3

Model Card Authors

Jordan Dialpuri

Model Card Contact

Jordan Dialpuri - jordan.dialpuri (at) york.ac.uk

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .