Mixtape is a python package which implements a series of statistical models for high-dimensional time-series -- the particular focus of the library is on the analysis of atomistic simulations of biomolecular dynamics such as protein folding and conformational change. Mixtape is available under the LGPL (v2.1 or later).
Mixtape is under active development. Many of the algorithms and models implemented are "mature", but others are rapidly changing.
Algorithms available include:
- Geometric clustering
- Markov state models
- Time-structure independent components analysis
- L1-regularized reversible hidden Markov models