A kernel-based approach to molecular conformation analysis
This provides a unified framework for analyzing molecular dynamics, potentially improving efficiency in computational biology, though it appears incremental as it builds on existing methods.
The paper tackles the problem of understanding conformation dynamics of biomolecules by combining kernel-based techniques with transfer operator theory, showing that existing methods like Markov State Models are special cases and enabling new efficient algorithms, with results illustrated on examples such as alanine dipeptide and NTL9.
We present a novel machine learning approach to understanding conformation dynamics of biomolecules. The approach combines kernel-based techniques that are popular in the machine learning community with transfer operator theory for analyzing dynamical systems in order to identify conformation dynamics based on molecular dynamics simulation data. We show that many of the prominent methods like Markov State Models, EDMD, and TICA can be regarded as special cases of this approach and that new efficient algorithms can be constructed based on this derivation. The results of these new powerful methods will be illustrated with several examples, in particular the alanine dipeptide and the protein NTL9.