# Protein Structure-Function Relationship: A Kernel-PCA Approach for Reaction Coordinate Identification

arXiv: https://arxiv.org/abs/2503.19186 · HTML: https://mlsanity.com/paper/2503.19186/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 59 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [TorchMD: A deep learning framework for molecular simulations](https://mlsanity.com/paper/2012.12106/) (2020)
- [Machine Learning Coarse-Grained Potentials of Protein Thermodynamics](https://mlsanity.com/paper/2212.07492/) (2022)
- [PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction](https://mlsanity.com/paper/2309.03099/) (2023)
- [Multi-Peptide: Multimodality Leveraged Language-Graph Learning of Peptide Properties](https://mlsanity.com/paper/2407.03380/) (2024)

## Built on by (most cited first, 1 of 1)

- [Curveball Steering: The Right Direction To Steer Isn't Always Linear](https://mlsanity.com/paper/2603.09313/) (2026)

## Abstract (arXiv)

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.