Weighted-Persistent-Homology-based Machine Learning for RNA Flexibility Analysis

Abstract

With the great significance of biomolecular flexibility in biomolecular dynamics and function analysis, various experimental methods and theoretical models are developed. Experimentally, Debye-Waller factor, also known as B-factor, measures atomic mean-square displacement and is usually considered as an important measurement for flexibilities. Theoretically, elastic network models, Gaussian network model, flexibility-rigidity model, and other computational models, have been proposed for flexility analysis by shedding light on the biomolecular inner topological structures. Recently, a topology-based machine learning model is proposed. By using the features from persistent homology, this model achieves remarkable high accuracy in protein B-factor prediction. Motivated by its success, we propose weighted-persistent-homology (WPH)-based machine learning (WPHML) models for RNA flexibility analysis. Our WPH is a newly-proposed model, which incorporate physical, chemical and biological information into topological measurements using a weight function. In particular, we use local persistent homology (LPH), which is not to consider the topology of a whole RNA structure, but to focus on the topological information of local regions. Our WPHML model is validated on a well-established RNA dataset, and numerical experiments show that our model can achieve a Pearson correlation coefficient up to 0.5822. The comparison with the previous sequence-information-based learning models shows that a consistent increase of accuracy by at least 10% is achieved in our current model.