A Bayesian Approach to Protein Model Quality Assessment
Abstract
Given multiple possible models b<sub>1</sub>, b<sub>2</sub>, ... b<sub>n</sub> for a protein structure, a common sub-task in in-silico Protein Structure Prediction is ranking these models according to their quality. Extant approaches use MLE estimates of parameters r<sub>i</sub> to obtain point estimates of the Model Quality. We describe a Bayesian alternative to assessing the quality of these models that builds an MRF over the parameters of each model and performs approximate inference to integrate over them. Hyperparameters w are learnt by optimizing a list-wise loss function over training data. Our results indicate that our Bayesian approach can significantly outperform MLE estimates and that optimizing the hyper-parameters can further improve results.
Cite
Text
Kamisetty and Langmead. "A Bayesian Approach to Protein Model Quality Assessment." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553437Markdown
[Kamisetty and Langmead. "A Bayesian Approach to Protein Model Quality Assessment." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/kamisetty2009icml-bayesian/) doi:10.1145/1553374.1553437BibTeX
@inproceedings{kamisetty2009icml-bayesian,
title = {{A Bayesian Approach to Protein Model Quality Assessment}},
author = {Kamisetty, Hetunandan and Langmead, Christopher James},
booktitle = {International Conference on Machine Learning},
year = {2009},
pages = {481-488},
doi = {10.1145/1553374.1553437},
url = {https://mlanthology.org/icml/2009/kamisetty2009icml-bayesian/}
}