Generative models produce three-dimensional molecular structures with high geometric accuracy, yet they are trained on distributions of atomic coordinates without explicit access to the underlying physics. The potential energy surface (PES) describes how the energy changes around a molecular geometry, and the RMSD betw...
S. Darouich, Juliane Geisler, Jacob W. Toney et al.· 0 citations
SymDrift is a framework that makes the drifting field itself symmetry-aware, and introduces two complementary strategies: a symmetrized drift in coordinate space based on optimal alignment, and a $G$-invariant embedding that removes symmetry ambiguity by construction.
S. Darouich, Vinh Tong, L. Pastor-Pérez et al.· arXiv.org· 1 citation
Novel physics-inspired molecular fingerprints are introduced based on principles from spectral graph theory, which represent molecules as a complete graph in 3D space, with edge weights encoding heuristic physical interactions and revealing the utility of this molecular representation in machine learning and cheminform...
Jacob W. Toney, Ayleen Y. Farnood, S. Darouich et al.· 0 citations
The ElemeNet software package enables the training of advanced ML models for diverse properties and datasets with an enlarged range of elemental compositions, and introduces moiety predictions, a unified, general-purpose software package for molecular machine learning.
Jacob W. Toney, S. Darouich, Yiran Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
