Learning Protein Dynamics with Metastable Switching Systems
This work addresses the challenge of accurately modeling protein dynamics for applications like rational drug design, though it appears incremental as it extends existing switching models with a new constraint.
The paper tackles the problem of extracting fine-grained representations of protein evolution from molecular dynamics datasets by introducing metastable switching linear dynamical systems with a stability constraint, resulting in significant improvements in temporal coherence over HMMs and standard switching models for met-enkephalin and enabling sample transition paths for Src-kinase.
We introduce a machine learning approach for extracting fine-grained representations of protein evolution from molecular dynamics datasets. Metastable switching linear dynamical systems extend standard switching models with a physically-inspired stability constraint. This constraint enables the learning of nuanced representations of protein dynamics that closely match physical reality. We derive an EM algorithm for learning, where the E-step extends the forward-backward algorithm for HMMs and the M-step requires the solution of large biconvex optimization problems. We construct an approximate semidefinite program solver based on the Frank-Wolfe algorithm and use it to solve the M-step. We apply our EM algorithm to learn accurate dynamics from large simulation datasets for the opioid peptide met-enkephalin and the proto-oncogene Src-kinase. Our learned models demonstrate significant improvements in temporal coherence over HMMs and standard switching models for met-enkephalin, and sample transition paths (possibly useful in rational drug design) for Src-kinase.