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
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.