NeuralTSNE: A Python Package for the Dimensionality Reduction of Molecular Dynamics Data Using Neural Networks

2025/05/22 by Patryk Tajs, Tajs, Patryk, Mateusz Skarupski +3 · 1 voice · 1 citation
Materials Science · Physics and Astronomy · #Chemical Physics (physics.chem-ph) #FOS: Physical sciences #Machine Learning in Materials Science #Quantum many-body systems #Spectroscopy and Quantum Chemical Studies #physics.chem-ph

paper · pdf · doi:10.48550/arxiv.2505.16476

openalex publication_date 2025/05/22 · arxiv published 2025/05/22 · arxiv updated 2025/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Unsupervised machine learning has recently gained much attention in the field of molecular dynamics (MD). Particularly, dimensionality reduction techniques have been regularly employed to analyze large volumes of high-dimensional MD data to gain insight into hidden information encoded in MD trajectories. Among many such techniques, t-distributed stochastic neighbor embedding (t-SNE) is particularly popular. A parametric version of t-SNE that employs neural networks is less commonly known, yet it has demonstrated superior performance in dimensionality reduction compared to the standard implementation. Here, we present a Python package called NeuralTSNE with our implementation of parametric t-SNE. The implementation is done using the PyTorch library and the PyTorch Lightning framework and can be imported as a module or used from the command line. We show that NeuralTSNE offers an easy-to-use tool for the analysis of MD data.

Citations

• Machine Learning of Slow Collective Variables and Enhanced Sampling via Spatial Techniques
• PLUMED Tutorials: a collaborative, community-driven learning ecosystem
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Enhancing Important Fluctuations: Rare Events and Metadynamics from a Conceptual Viewpoint
• PLUMED 2: New feathers for an old bird
• Slow Feature Analysis: Unsupervised Learning of Invariances

Cited by

• Constructing Generalized Sample Transition Probabilities with Biased Simulations

Discussions

• Together with my students, we have implemented a PyTorch Lightning package for dimensionality reduction with a parametric version of tSNE. More methods soon! Paper: arxiv.org/abs/2505.16476 Code: gith [bsky, 4 points, 0 comments]

Related

• Acceleration of Molecular Simulations by Parametric Time-Lagged tSNE Metadynamics
• Artificial Intelligence for Direct Prediction of Molecular Dynamics across Chemical Space
• Enhanced Sampling with Machine Learning: A Review
• How simple can you go? An off-the-shelf transformer approach to molecular dynamics
• Enhanced Sampling with Machine Learning