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

TL;DR

Deeptime is a versatile Python library that facilitates the estimation and analysis of dynamical models from time-series data, integrating traditional and deep learning methods for scientific applications.

Contribution

It introduces a comprehensive, user-friendly Python library combining various dynamical modeling techniques, including deep learning, with analysis tools for time-series data.

Findings

Supports multiple modeling approaches including MSMs, Hidden Markov Models, Koopman models, VAMPnets, and deep MSMs.

Provides analysis methods for thermodynamic, kinetic, and dynamical quantities.

Designed for ease of use, extensibility, and compatibility with scikit-learn.

Abstract

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.