mlsanityData to 14 Oct 2026

Deeptime: a Python library for machine learning dynamical models from time series data

arXiv 2110.15013 ↗First posted 28 Oct 2021math.DS cs.LG math-phcited by 38

Not on the map. Why?

Abstract (arXiv)

Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 26 of its 142 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

26 of 142 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
  5. 2021Modern Koopman Theory for Dynamical Systemscited by 276
  6. 2017Learning Koopman Invariant Subspaces for Dynamic Mode Decompositioncited by 158
  7. 2017Linearly-Recurrent Autoencoder Networks for Learning Dynamicscited by 145
  8. 2017Sparse identification of nonlinear dynamics for model predictive control in the low-data limitcited by 140
  9. 2017VAMPnets: Deep learning of molecular kineticscited by 136
  10. 2014Dynamic mode decomposition with controlcited by 129
  11. 2017Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systemscited by 127
  12. 2019sktime: A Unified Interface for Machine Learning with Time Seriescited by 102
14 more
  1. 2019Data-driven approximation of the Koopman generator: Model reduction, system identification, and controlcited by 85
  2. 2017Sparse learning of stochastic dynamic equationscited by 76
  3. 2017Time-lagged autoencoders: Deep learning of slow collective variables for molecular kineticscited by 65
  4. 2017Variational approach for learning Markov processes from time series datacited by 52
  5. 2018On the Convergence of the SINDy Algorithmcited by 49
  6. 2019A unified sparse optimization framework to learn parsimonious physics-informed models from datacited by 49
  7. 2017Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spacescited by 48
  8. 2013Sparsity-promoting dynamic mode decompositioncited by 30
  9. 2017Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape explorationcited by 24
  10. 2017Variational Encoding of Complex Dynamicscited by 21
  11. 2018Deep Generative Markov State Modelscited by 19
  12. 2019Kernel methods for detecting coherent structures in dynamical datacited by 13
  13. 2018Variational Selection of Features for Molecular Kineticscited by 8
  14. 2018Simultaneous Coherent Structure Coloring facilitates interpretable clustering of scientific data by amplifying dissimilaritycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 9; 2024: 6; 2025: 9; 2026: 7.

38 papers.

Sort:

By area:

  1. 2023Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamicscited by 72
  2. 2024Protein Conformation Generation via Force-Guided SE(3) Diffusion Modelscited by 45
  3. 2022Flow-matching -- efficient coarse-graining of molecular dynamics without forcescited by 36
  4. 2023Str2Str: A Score-based Framework for Zero-shot Protein Conformation Samplingcited by 29
  5. 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Modelscited by 23
  6. 2024Structure Language Models for Protein Conformation Generationcited by 17
  7. 2023Implicit Transfer Operator Learning: Multiple Time-Resolution Surrogates for Molecular Dynamicscited by 14
  8. 2023PyKoopman: A Python Package for Data-Driven Approximation of the Koopman Operatorcited by 10
  9. 2022GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomoleculescited by 8
  10. 2025BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimationcited by 7
  11. 2022Thermodynamics-inspired Explanations of Artificial Intelligencecited by 6
  12. 2023Reaction coordinate flows for model reduction of molecular kineticscited by 6
26 more
  1. 2023Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneckcited by 6
  2. 2024Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptidescited by 6
  3. 2025MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Modelscited by 6
  4. 2023Learning noise-induced transitions by multi-scaling reservoir computingcited by 5
  5. 2021Collective variable discovery in the age of machine learning: reality, hype and everything in betweencited by 2
  6. 2024Flow Matching for Optimal Reaction Coordinates of Biomolecular Systemcited by 2
  7. 2025How deep is your network? Deep vs. shallow learning of transfer operatorscited by 2
  8. 2026Unified Biomolecular Trajectory Generation via Pretrained Variational Bridgecited by 2
  9. 2023Internal-Coordinate Density Modelling of Protein Structure: Covariance Matterscited by 1
  10. 2023SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented Datacited by 1
  11. 2024Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulationscited by 1
  12. 2024Optimizing adaptive sampling via Policy Rankingcited by 1
  13. 2025Addressing Challenges in Time Series Forecasting: A Comprehensive Comparison of Machine Learning Techniquescited by 1
  14. 2025Minimum-Excess-Work Guidancecited by 1
  15. 2025Learning Collective Variables from BioEmu with Time-Lagged Generationcited by 1
  16. 2025A Standardized Benchmark for Machine-Learned Molecular Dynamics using Weighted Ensemble Samplingcited by 1
  17. 2021The Past as a Stochastic Processcited by 0
  18. 2022Building Robust Machine Learning Models for Small Chemical Science Data: The Case of Shear Viscositycited by 0
  19. 2022Koopman-theoretic Approach for Identification of Exogenous Anomalies in Nonstationary Time-series Datacited by 0
  20. 2025Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learningcited by 0
  21. 2026Representation choice shapes the interpretation of protein conformational dynamicscited by 0
  22. 2026Optimization of randomized neural networks for transfer operator approximationcited by 0
  23. 2026Temperature transferable Machine Learned Coarse Grained model for proteinscited by 0
  24. 2026Learning Topological Representations of Protein Structure and Dynamicscited by 0
  25. 2026Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Samplingcited by 0
  26. 2026Looking Under the Streetlight: Evaluation in Generative Molecular Dynamicscited by 0