Root Cause Analysis of Hydrogen Bond Separation in Spatio-Temporal Molecular Dynamics using Causal Models

2025/08/17 by Rahmat Adesunkanmi, Adesunkanmi, Rahmat K., Ashfaq Khokhar +5
Chemistry · Physics and Astronomy · #Advanced Chemical Physics Studies #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Molecular spectroscopy and chirality #Quantitative Methods (q-bio.QM) #Spectroscopy and Quantum Chemical Studies

paper · pdf · doi:10.48550/arxiv.2508.12500

openalex publication_date 2025/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Molecular dynamics simulations (MDS) face challenges, including resource-heavy computations and the need to manually scan outputs to detect "interesting events," such as the formation and persistence of hydrogen bonds between atoms of different molecules. A critical research gap lies in identifying the underlying causes of hydrogen bond formation and separation -understanding which interactions or prior events contribute to their emergence over time. With this challenge in mind, we propose leveraging spatio-temporal data analytics and machine learning models to enhance the detection of these phenomena. In this paper, our approach is inspired by causal modeling and aims to identify the root cause variables of hydrogen bond formation and separation events. Specifically, we treat the separation of hydrogen bonds as an "intervention" occurring and represent the causal structure of the bonding and separation events in the MDS as graphical causal models. These causal models are built using a variational autoencoder-inspired architecture that enables us to infer causal relationships across samples with diverse underlying causal graphs while leveraging shared dynamic information. We further include a step to infer the root causes of changes in the joint distribution of the causal models. By constructing causal models that capture shifts in the conditional distributions of molecular interactions during bond formation or separation, this framework provides a novel perspective on root cause analysis in molecular dynamic systems. We validate the efficacy of our model empirically on the atomic trajectories that used MDS for chiral separation, demonstrating that we can predict many steps in the future and also find the variables driving the observed changes in the system.

Citations

• MLPST: MLP is All You Need for Spatio-Temporal Prediction
• Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey
• Expectation Distance-based Distributional Clustering for Noise-Robustness
• Toward Causal Representation Learning
• DoWhy: An End-to-End Library for Causal Inference
• Causal structure based root cause analysis of outliers
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• Neural Message Passing for Quantum Chemistry
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Gated Graph Sequence Neural Networks
• Structural-RNN: Deep Learning on Spatio-Temporal Graphs
• Adam: A Method for Stochastic Optimization
• Multilayer perceptrons for classification and regression
• The Graph Neural Network Model

Related

• Integration of Machine Learning in the Characterization of Hydrogen Bonding Analysis: A Comparative Study
• Simulating and investigating various dynamic aspects of the \rmH₂\rmO-related hydrogen bond model
• Shift-Robust Molecular Relational Learning with Causal Substructure
• Machine Learning in Molecular Dynamics Simulations of Biomolecular Systems
• Ab Initio Molecular Dynamics Simulations for Organic Chemists─It is About Time!