Reproduce “SupraTITO: Transferable Generative Molecular Dynamics for Supramolecular Systems” 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
Weilong Chen, Nuno Costa, Julija Zavadlav
SupraTITO models stochastic finite-lag transitions to simulate peptide self-assembly, conditioning each step on sequence, connectivity, current configuration, and periodic geometry. In a benchmark of 400 dipeptides, it generated trajectories capturing assembly behavior and outperformed direct ensemble prediction on all six structural observables. Its held-out-sequence SASA mean absolute error was 5.733 nm² versus 15.167 nm²; transfer beyond these conditions remains unestablished.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.