Reproduce “Characterizing metastable states with the help of machine learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Pietro Novelli, Luigi Bonati, Massimiliano Pontil, Michele Parrinello
The authors combine VAC with LASSO to interpret molecular-simulation trajectories by identifying slow, long-lived protein states and selecting a small set of physical descriptors that distinguishes them. In Chignolin, the TYR1-O–TYR10-N contact classified folded and unfolded configurations with 99% reported accuracy among 318 candidate contacts. The paper demonstrates two proteins, not causal explanations or validation across other systems.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.