Sign in

Thomas Plé

@thomasple.bsky.social
36 followers 23 following 2 posts
PostsRepliesMedia
Thomas Plé @thomasple.bsky.social · 17/12/2025
In the case of FeNNix-Bio1, we directly simulate the dynamics of the protein with an all-atom ML potential with near ab initio accuracy.
110
Thomas Plé @thomasple.bsky.social · 17/12/2025
Hi there. The scope of the paper you mention is actually quite different: in their case, the ML model performs coarse-grained MD to accelerate the dynamics of an all-atoms force field (AMBER in this case) so it is limited by the accuracy of the underlying FF.
110
Reposted by Thomas Plé
Jean-Philip Piquemal @jppiquem.bsky.social · 06/05/2025
#compchem New preprint: "A Foundation Model for Accurate Atomistic Simulations in Drug Design" FeNNix-Bio1, a foundation #machinelearning model for biosimulations doi.org/10.26434/che... #compchemsky #biosky Great work by T. Plé & the teams @lct-umr7616.bsky.social & @qubit-pharma.bsky.social
doi.org
A Foundation Model for Accurate Atomistic Simulations in Drug Design
Neural network potentials now offer robust alternatives to electronic structure and empirical force fields computations for the on-the-fly production of the potential energy surfaces required in atomi...
0235
Reposted by Thomas Plé
Jean-Philip Piquemal @jppiquem.bsky.social · 09/05/2025
1/3 #compchem Preprint: "Pushing the Accuracy Limit of Foundation Neural Network Models with Quantum Monte Carlo Forces & Path Integrals" 💫: arxiv.org/abs/2504.07948 An end-to-end multi-level exascale strategy to produce highly accurate quantum chemistry datasets (energies & forces): DFT/QMC/sCI.
53815
Reposted by Thomas Plé
Jean-Philip Piquemal @jppiquem.bsky.social · 31/01/2025
#biosky #compbio #hpc #supercomputing
061
Reposted by Thomas Plé
Jean-Philip Piquemal @jppiquem.bsky.social · 20/12/2024
#compchem New group preprint: "Velocity Jumps for Molecular Dynamics". arxiv.org/abs/2412.15073 Fantastic work by N. Gouraud @lct-umr7616.bsky.social @qubit-pharma.bsky.social .
0257