@DeepModeling profile picture
DeepModeling @DeepModeling

Define the future of scientific computing together

Joined June 2021
  • Tweets 49
  • Following 2
  • Followers 288
2 Photos and videos
Pinned Tweet
DeepModeling@DeepModeling
11 Jun 2021
The DeepModeling Manifesto deepmodeling.org/blog/manife…
2
1
Can ML simulate carbon nanotube growth? 🧬🚀 Discover how the new DeepCNT-22 force field, based on DeePMD, enables precise large-scale simulations. Learn more about this breakthrough in nanomaterials! doi.org/10.1038/s41467-024-4…

Dynamics of growing carbon nanotube interfaces probed by machine learning-enabled molecular...

Nature Communications - There is a lack of atomic level insight on the role of defects on carbon nanotubes' growth. Here, authors present a machine learning force field to drive...

nature.com
1
1
4
285
🚀 New Insights from DeePMD-kit! 🚀 Check out the latest Nature Chemistry article where DeePMD-kit reveals a dual-gated mechanism of proton transport in water, advancing our understanding of this vital process. 🔗 Read more: doi.org/10.1038/s41557-024-0… #DeepModeling #DeePMD #AI4S

Neural-network-based molecular dynamics simulations reveal that proton transport in water is doubly...

Nature Chemistry - Recent vibrational spectroscopy experiments suggested that excess proton transport in water is more complex than previously thought. Now the proton transport mechanism has been...

nature.com
1
1
4
544
🚀Machine learning potential model was generated for the Pt-TiO2 system using DeePMD-kit. This model studies the effect of atomic isolation walls on catalyst stability and illustrates noble metal particle sintering on TiO2-supported Pt particles. doi.org/10.1016/j.jcat.2024.…
187
🧬 Exciting news! Researchers Xi Cheng, Liuqing Wen, and Dingyan Wang introduced DeepGlycanSite, a deep learning model for accurate carbohydrate-binding site prediction on proteins. nature.com/articles/s41467-0… #deepmodeling #unimol #opensource

Highly accurate carbohydrate-binding site prediction with DeepGlycanSite

Nature Communications - Carbohydrates are essential for regulating various biological processes. Here, the authors developed DeepGlycanSite, a deep learning model that accurately predicts...

nature.com
171
🔧 The DeepModeling community developed Dflow, a Python toolkit for building workflows. Key features please check: github.com/deepmodeling/dflo… #deepmodeling @dflow @ai4s @opensource

GitHub - deepmodeling/dflow: Dflow is a Python framework for constructing scientific computing...

Dflow is a Python framework for constructing scientific computing workflows (e.g. concurrent learning workflows) employing Argo Workflows as the workflow engine. - deepmodeling/dflow

github.com
115
Excited about this research! Dr. Jianchuan Liu & team developed ML interatomic potential models for 19 Group IIB-VIA semiconductors using ABACUS & DeePMD-kit. Amazing work! Check out their article and models/datasets: #MachineLearning #DFT #ABACUS #DeePMD doi.org/10.1021/acs.jctc.3c0…

Machine-Learning-Based Interatomic Potentials for Group IIB to VIA Semiconductors: Toward a...

Rapid advancements in machine-learning methods have led to the emergence of machine-learning-based interatomic potentials as a new cutting-edge tool for simulating large systems with ab initio...

pubs.acs.org
3
129
Exciting News! 🚀 We're thrilled to announce ABACUS v3.7.0, packed with major updates! Explore the new features and join the conversation! github.com/deepmodeling/abac…

GitHub - deepmodeling/abacus-develop: An electronic structure package based on either plane wave...

An electronic structure package based on either plane wave basis or numerical atomic orbitals. - deepmodeling/abacus-develop

github.com
1
81
🚀 Exciting news! DeePMD-kit v3 (v3.0.0a0) is here! Train models on TensorFlow & PyTorch. New PyTorch backend supports large atomic models with the DPA-2 model. Fully Python-based for easy dev & debugging. Thanks to all contributors! Learn more & download: github.com/deepmodeling/deep…

Release v3.0.0a0 · deepmodeling/deepmd-kit

DeePMD-kit v3: A multiple-backend framework for deep potentials We are excited to announce the first alpha version of DeePMD-kit v3. DeePMD-kit v3 allows you to train and run deep potential models ...

github.com
2
13
417
🚀 We're thrilled to launch the #OpenLAM initiative! 🌟 With the new DPA-2 model, we're ready to "Conquer the Periodic Table". Join us in this exciting journey! Learn more: aissquare.com/openlam #DeepPotential #opensource #DeepModeling
7
142
Excited to share that Uni-Mol has joined the DeepModeling community! 🚀 Our 3D molecular representation framework is revolutionizing molecular design. Check out our GitHub for more details and to contribute: github.com/deepmodeling/Uni-… #unimol #deepmodeling #opensource

GitHub - deepmodeling/Uni-Mol: Official Repository for the Uni-Mol Series Methods

Official Repository for the Uni-Mol Series Methods - deepmodeling/Uni-Mol

github.com
4
15
651
We just released the first alpha version of DeePMD-kit v3, bringing a multiple-backend platform, the PyTorch backend, and the support for large atomic models. github.com/deepmodeling/deep…

Release v3.0.0a0 · deepmodeling/deepmd-kit

DeePMD-kit v3: A multiple-backend framework for deep potentials We are excited to announce the first alpha version of DeePMD-kit v3. DeePMD-kit v3 allows you to train and run deep potential models ...

github.com
2
6
790
DeepModeling retweeted
Shef Wang@shefwang
27 Dec 2022
AI for Science in action. intelli-science.com/p/exclus…. @DeepModeling @UCBerkeley
1
2
185
DeepModeling posted OpenLAM 2024 Q0 report: deepmodeling.com/blog/openla…
2
155
DeepModeling launches the OpenLAM Initiative to "conquer the Periodic Table". deepmodeling.com/blog/openla…
1
1
432
DeepModeling retweeted
Blue Snow@bluesnow2023
22 Aug 2023
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…

DMFF: An Open-Source Automatic Differentiable Platform for Molecular Force Field Development and...

In the simulation of molecular systems, the underlying force field (FF) model plays an extremely important role in determining the reliability of the simulation. However, the quality of the state-o...

pubs.acs.org
1
182
DeepModeling retweeted
Davide Tisi@tis930
1 Aug 2023
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…

DeePMD-kit v2: A software package for deep potential models

DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential

pubs.aip.org
1
10
17
2,880
We are excited to be hosting the first AI for Science Salon & Workshop in Hong Kong in CB-A, Chow Yei Ching Building, Main Campus, the University of Hong Kong, May 24-25, 2023. Click to know more: deepmodeling.typeform.com/hk…

Discover Typeform, where forms = fun

Instantly create forms that are easy to make and take. Start conversations, automate workflows, and turn leads into revenue with ease.

typeform.com
6
6
1,453
DeepModeling retweeted
Pablo Piaggi@PiaggiPablo
8 Aug 2022
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…

Homogeneous ice nucleation in an ab initio machine-learning model of water | PNAS

Molecular simulations have provided valuable insight into the microscopic mechanisms underlying homogeneous ice nucleation. While empirical models ...

pnas.org
6
18
114
Load more