Supervised machine learning approach to molecular dynamics forecast of SARS-CoV-2 spike glycoproteins at varying temperatures

Abstract

Molecular dynamics (MD) simulations are a widely used technique in modeling complex nanoscale interactions of atoms and molecules. These simulations can provide detailed insight into how molecules behave under certain environmental conditions. This work explores a machine learning (ML) solution to predicting long-term properties of SARS-CoV-2 spike glycoproteins (S-protein) through the analysis of its nanosecond backbone RMSD (root-mean-square deviation) MD simulation data at varying temperatures. The simulation data were denoised with fast Fourier transforms. The performance of the models was measured by evaluating their mean squared error (MSE) accuracy scores in recurrent forecasts for long-term predictions. The models evaluated include k-nearest neighbors (kNN) regression models, as well as GRU (gated recurrent unit) neural networks and LSTM (long short-term memory) autoencoder models. Results demonstrated that the kNN model achieved the greatest accuracy in forecasts with MSE scores over around 0.01 nm less than those of the GRU model and the LSTM autoencoder. Furthermore, it demonstrated that the kNN model accuracy increases with data size but can still forecast relatively well when trained on small amounts of data, having achieved MSE scores of around 0.02 nm when trained on 10,000 ns of simulation data. This study provides valuable information on the feasibility of accelerating the MD simulation process through training and predicting supervised ML models, which is particularly applicable in time-sensitive studies. Graphic abstract SARS-CoV-2 spike glycoprotein molecular dynamics simulation. Extraction and denoising of backbone RMSD data. Evaluation of k-nearest neighbors regression, GRU neural network, and LSTM autoencoder models in recurrent forecasting for long-term property predictions.

Methodology-Centered Review of Molecular Modeling, Simulation, and Prediction of SARS-CoV-2

“…The recently reported transcriptomics data of upper airway tissue with acute respiratory illnesses is integrated with some machine learning algorithms such as the k-NN algorithm to identify effective qualitative biomarkers and quantitative rules for the distinction of SARS-CoV-2 infection from other infectious diseases. 737 Furthermore, with the implementation of the k-NN algorithm, as well as the GRU (gated recurrent unit) neural networks and LSTM (long short-term memory) autoencoder models by Liang et al, 738 the analysis of the nanosecond backbone root-mean-square deviation (RMSD) of the S protein assisted in the prediction of the long-term properties of SARS-CoV-2 S proteins. In the study of SARS-CoV-2, a common method for discovering evolution patterns and transmission pathways is to cluster mutations.…”

Do Machine-Learning Atomic Descriptors and Order Parameters Tell the Same Story? The Case of Liquid Water

“…The past decade has seen a tremendous spurt in both the development and application of machine-learning (ML) approaches to study molecular systems. − ML has become a mainstream component of atomistic modeling, in particular, for the construction of interaction potentials, ,, and for the analysis of molecular dynamics simulations. − Establishing an understanding of the underlying physical and chemical principles that make ML useful and accurate and, in short, avoid its black box usage remains an open challenge.…”

Long Short-Term Memory to Predict 3D Amino Acids Positions in GPCR Molecular Dynamics

“…Other authors applies LSTM directly onto the low dimensional molecular trajectories and predicts the rare events in the sequential data [20]. Liang et al (2019) [21] apply LSTMs to trajectories forecasting of spike glycoproteins (S-protein) on the SARS-CoV-2 dynamics. Ludwig et al (2022) have worked with special LSTM, bi-directional, to increase the 3D spacial resolution of MD trajectories within a post-processing step.…”