|
|
--- |
|
|
license: lgpl-3.0 |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- chemistry |
|
|
- biology |
|
|
--- |
|
|
|
|
|
# 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 |
