Structure-Function Dynamics Hybrid Modeling: RNA Degradation

TL;DR

This paper introduces a hybrid modeling approach combining mechanistic and machine learning techniques to predict RNA degradation, bridging atomistic details with macroscopic biological processes.

Contribution

The study develops a novel multi-scale hybrid model that integrates molecular dynamics and machine learning for RNA degradation prediction.

Findings

The hybrid model effectively predicts RNA lifetime.

It demonstrates promising performance in multi-scale bioprocess modeling.

The approach advances understanding of RNA structure-function relationships.

Abstract

RNA structure and functional dynamics play fundamental roles in controlling biological systems. Molecular dynamics simulation, which can characterize interactions at an atomistic level, can advance the understanding on new drug discovery, manufacturing, and delivery mechanisms. However, it is computationally unattainable to support the development of a digital twin for enzymatic reaction network mechanism learning, and end-to-end bioprocess design and control. Thus, we create a hybrid ("mechanistic + machine learning") model characterizing the interdependence of RNA structure and functional dynamics from atomistic to macroscopic levels. To assess the proposed modeling strategy, in this paper, we consider RNA degradation which is a critical process in cellular biology that affects gene expression. The empirical study on RNA lifetime prediction demonstrates the promising performance of the proposed multi-scale bioprocess hybrid modeling strategy.