MSMBuilder

Statistical models for Biomolecular Dynamics

MSMBuilder is an application and python library. It builds statistical models for high-dimensional time-series. The particular focus of the package is on the analysis of atomistic simulations of biomolecular dynamics such as protein folding and conformational change.

To get started via Anaconda Python, use:

conda install -c omnia msmbuilder

MSMBuilder includes algorithms for constructing dynamical models:

• Featurization
• Feature Selection
• Preprocessing
• Decomposition
• Clustering
• Markov state models (MSMs)
• Hidden Markov models (HMMs)
• Continuous-time MSMs

As well as methods for analysis and validation of the models:

• Model Selection using GMRQ
• Transition Path Theory

New users should check out:

• Motivation
• Installation
• Tutorial
• Examples
• FAQs

MSMBuilder is most effective as a library. Intermediate users should familiarize themselves with:

• API Patterns
• Datasets
• Changelog

MSMBuilder is developed by primarily by researchers at Stanford University, and we welcome contributions. The development all takes place on Github. MSMBuilder is licensed under the GNU LGPL (v2.1 or later).