Protein Structure-Function Relationship: A Kernel-PCA Approach for Reaction Coordinate Identification
By: Parisa Mollaei, Amir Barati Farimani
Potential Business Impact:
Finds how proteins work by looking at their moves.
In this study, we propose a Kernel-PCA model designed to capture structure-function relationships in a protein. This model also enables ranking of reaction coordinates according to their impact on protein properties. By leveraging machine learning techniques, including Kernel and principal component analysis (PCA), our model uncovers meaningful patterns in high-dimensional protein data obtained from molecular dynamics (MD) simulations. The effectiveness of our model in accurately identifying reaction coordinates has been demonstrated through its application to a G protein-coupled receptor. Furthermore, this model utilizes a network-based approach to uncover correlations in the dynamic behavior of residues associated with a specific protein property. These findings underscore the potential of our model as a powerful tool for protein structure-function analysis and visualization.
Similar Papers
Localized Functional Principal Component Analysis Based on Covariance Structure
Methodology
Finds patterns in data that only exist in parts.
KinForm: Kinetics Informed Feature Optimised Representation Models for Enzyme $k_{cat}$ and $K_{M}$ Prediction
Quantitative Methods
Helps predict how fast tiny body helpers work.
Controllable protein design through Feynman-Kac steering
Machine Learning (CS)
Designs proteins that stick to targets better.