DeepModeling retweeted
DMFF: An Open-Source Automatic Differentiable Platform for Molecular Force Field Development and Molecular Dynamics Simulation | Journal of Chemical Theory and Computation pubs.acs.org/doi/10.1021/acs…
DeepModeling retweeted
It is online the new paper showing the new features implemented in the last years in DeePMD-kit!!
DeePMD-kit v2: A software package for deep potential models pubs.aip.org/aip/jcp/article…
DeepModeling retweeted
Our paper on ice nucleation using first principles MD simulations driven by an ML model just appeared online in PNAS. 300,000 atoms with ab initio accuracy! Thanks @snsf_ch @doescience @CcscCsi @DeepModeling @plumed_org for making this possible. pnas.org/doi/full/10.1073/pn…
DeepModeling retweeted
Excited to announce the publication of my 2nd first author paper, as part of my PhD, in @JCIM_JCTC @jctc_papers titled "Combined Deep Learning and Classical Potential Approach for Modeling Diffusion in UiO-66". #MOF #chemtwitter #compchem #deepmd
[ASAP] Combined Deep Learning and Classical Potential Approach for Modeling Diffusion in UiO-66 ift.tt/JjZ13Rs
DeepModeling retweeted
Structural Phase Transitions in SrTiO3 from Deep Potential Molecular Dynamics. (arXiv:2201.06902v1 [cond-mat.mtrl-sci]) #machinelearning https://nitter.cf/t.co/FNiZHTuZKp
DeepModeling retweeted
#AI makes it possible to simulate 25 billion water molecules at once
Simulations of clouds of atoms & molecules always trade scale for accuracy, but a new technique shows that both are possible at once using AI and clever coding
newscientist.com/article/230…
#HPC via @EvanKirstel
DeepModeling retweeted
In this paper, researchers have introduced a new optimized version of DeePMD-kit, based in a novel tabulated deep potential model and system optimizations, able to save 82% of floating-point operations compared with the previous state-of-the-art. #HPC
arxiv.org/pdf/2201.01446.pdf
DeepModeling retweeted
受賞歴のある分子動力学シミュレーションシステム「DeePMD-kit」がGraphcore IPUハードウェアで利用可能に。
創薬から材料設計まで幅広い用途を支える分子動力学。
hubs.la/Q0110Kvp0
DeepModeling retweeted
Reproduce partial features of DeePMD-kit using PyTorch
✅ #coding #dev #developer #programmer #programming #python #pytorch #web #webdev pythonawesome.com/reproduce-…
DeepModeling retweeted
While fcc catalysts Au, Pt, Pd, and Pd-Sn alloys are selective for aniline, intermetallics Pd2Ge, Pd2Sn, Pd3Sn2, and PtSn are selective for azoxyarenes. MD simulations with ML potentials (DeePMD) unveil key reaction species. @carenalyne @vela_group
fal.cn/3jXVM
DeepModeling retweeted
Award-winning #moleculardynamics simulation system, DeePMD-kit, is now available for @graphcoreai IPU hardware.
Molecular dynamics underpins a vast range of applications, from #drugdiscovery to materials design.
hubs.la/Q010ycyS0
DeepModeling retweeted
Here is our latest @arxiv preprint on the "Liquid-Liquid Critical Point in Phosphorus" arxiv.org/abs/2104.14688 with Manyi Yang, @TarakChem & @GroupParrinello
We calculated ab initio accurate LL phase diagram (ML potential) and located a second-order critical point.
DeepModeling retweeted
The major MLatom.com release with many features and higher efficiency for #MLchem #compchem. KREG and interfaces to other cool ML potentials (ANI, DeepMD, sGDML, GAP-SOAP, PhysNet with help by @max_jr). @MarioBarbatti
doi.org/10.1007/s41061-021-0…
DeepModeling retweeted
New Milestone for Deep Potential Application: Predicting the Phase Diagram of Water | https://nitter.cf/t.co/1jrK8yV6BC
#AI #ML #ArtificialIntelligence #MachineLearning #Technology #DeepPotential #PhaseDiagram #MolecularDynamicsSimulation #Physics























