Run `wenxian` in an issue
njzjz opened this issue · comments
In this issue, comment with @njzjz-bot <id>:
@njzjz-bot 2312.15492
The GitHub Actions will reply with
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz-bot 2312.15492
@njzjz Here is the BibTeX entry for 2312.15492 : bibtex @Article{Zhang_arXiv_2023_p2312.15492, author = {Duo Zhang and Xinzijian Liu and Xiangyu Zhang and Chengqian Zhang and Chun Cai and Hangrui Bi and Yiming Du and Xuejian Qin and Jiameng Huang and Bowen Li and Yifan Shan and Jinzhe Zeng and Yuzhi Zhang and Siyuan Liu and Yifan Li and Junhan Chang and Xinyan Wang and Shuo Zhou and Jianchuan Liu and Xiaoshan Luo and Zhenyu Wang and Wanrun Jiang and Jing Wu and Yudi Yang and Jiyuan Yang and Manyi Yang and Fu-Qiang Gong and Linshuang Zhang and Mengchao Shi and Fu-Zhi Dai and Darrin M. York and Shi Liu and Tong Zhu and Zhicheng Zhong and Jian Lv and Jun Cheng and Weile Jia and Mohan Chen and Guolin Ke and Weinan E and Linfeng Zhang and Han Wang}, title = {{DPA-2: Towards a universal large atomic model for molecular and material simulation}}, journal = {arXiv}, year = 2023, pages = {2312.15492}, doi = {10.48550/arXiv.2312.15492}, annote = {The rapid development of artificial intelligence (AI) is driving significant changes in the field of atomic modeling, simulation, and design. AI-based potential energy models have been successfully used to perform large-scale and long-time simulations with the accuracy of ab initio electronic structure methods. However, the model generation process still hinders applications at scale. We envision that the next stage would be a model-centric ecosystem, in which a large atomic model (LAM), pre-trained with as many atomic datasets as possible and can be efficiently fine-tuned and distilled to downstream tasks, would serve the new infrastructure of the field of molecular modeling. We propose DPA-2, a novel architecture for a LAM, and develop a comprehensive pipeline for model fine-tuning, distillation, and application, associated with automatic workflows. We show that DPA-2 can accurately represent a diverse range of chemical systems and materials, enabling high-quality simulations and predictions with significantly reduced efforts compared to traditional methods. Our approach paves the way for a universal large atomic model that can be widely applied in molecular and material simulation research, opening new opportunities for scientific discoveries and industrial applications.}, }
@njzjz-bot 2312.15492
@njzjz Here is the BibTeX entry for 2312.15492 :
@Article{Zhang_arXiv_2023_p2312.15492,
author = {Duo Zhang and Xinzijian Liu and Xiangyu Zhang and Chengqian Zhang and
Chun Cai and Hangrui Bi and Yiming Du and Xuejian Qin and Jiameng
Huang and Bowen Li and Yifan Shan and Jinzhe Zeng and Yuzhi Zhang and
Siyuan Liu and Yifan Li and Junhan Chang and Xinyan Wang and Shuo Zhou
and Jianchuan Liu and Xiaoshan Luo and Zhenyu Wang and Wanrun Jiang
and Jing Wu and Yudi Yang and Jiyuan Yang and Manyi Yang and Fu-Qiang
Gong and Linshuang Zhang and Mengchao Shi and Fu-Zhi Dai and Darrin M.
York and Shi Liu and Tong Zhu and Zhicheng Zhong and Jian Lv and Jun
Cheng and Weile Jia and Mohan Chen and Guolin Ke and Weinan E and
Linfeng Zhang and Han Wang},
title = {{DPA-2: Towards a universal large atomic model for molecular and
material simulation}},
journal = {arXiv},
year = 2023,
pages = {2312.15492},
doi = {10.48550/arXiv.2312.15492},
annote = {The rapid development of artificial intelligence (AI) is driving
significant changes in the field of atomic modeling, simulation, and
design. AI-based potential energy models have been successfully used
to perform large-scale and long-time simulations with the accuracy of
ab initio electronic structure methods. However, the model generation
process still hinders applications at scale. We envision that the next
stage would be a model-centric ecosystem, in which a large atomic
model (LAM), pre-trained with as many atomic datasets as possible and
can be efficiently fine-tuned and distilled to downstream tasks, would
serve the new infrastructure of the field of molecular modeling. We
propose DPA-2, a novel architecture for a LAM, and develop a
comprehensive pipeline for model fine-tuning, distillation, and
application, associated with automatic workflows. We show that DPA-2
can accurately represent a diverse range of chemical systems and
materials, enabling high-quality simulations and predictions with
significantly reduced efforts compared to traditional methods. Our
approach paves the way for a universal large atomic model that can be
widely applied in molecular and material simulation research, opening
new opportunities for scientific discoveries and industrial
applications.},
}@njzjz-bot 10.1038/s41524-024-01278-7
@njzjz Here is the BibTeX entry for 10.1038/s41524-024-01278-7:
@Article{Zhang_NpjComputMater_2024_v10_p94,
author = {Duo Zhang and Hangrui Bi and Fu-Zhi Dai and Wanrun Jiang and Xinzijian
Liu and Linfeng Zhang and Han Wang},
title = {{Pretraining of attention-based deep learning potential model for
molecular simulation}},
journal = {Npj Comput. Mater},
year = 2024,
volume = 10,
issue = 1,
pages = 94,
doi = {10.1038/s41524-024-01278-7},
annote = {<jats:title>Abstract</jats:title><jats:p>Machine learning-assisted
modeling of the inter-atomic potential energy surface (PES) is
revolutionizing the field of molecular simulation. With the
accumulation of high-quality electronic structure data, a model that
can be pretrained on all available data and finetuned on downstream
tasks with a small additional effort would bring the field to a new
stage. Here we propose DPA-1, a Deep Potential model with a gated
attention mechanism, which is highly effective for representing the
conformation and chemical spaces of atomic systems and learning the
PES. We tested DPA-1 on a number of systems and observed superior
performance compared with existing benchmarks. When pretrained on
large-scale datasets containing 56 elements, DPA-1 can be successfully
applied to various downstream tasks with a great improvement of sample
efficiency. Surprisingly, for different elements, the learned type
embedding parameters form a <jats:italic>s</jats:italic><jats:italic>p
</jats:italic><jats:italic>i</jats:italic><jats:italic>r</jats:italic>
<jats:italic>a</jats:italic><jats:italic>l</jats:italic> in the latent
space and have a natural correspondence with their positions on the
periodic table, showing interesting interpretability of the pretrained
DPA-1 model.</jats:p>},
}@njzjz-bot 10.1021/acs.jctc.1c00201
@njzjz-bot 10.1021/acs.jctc.1c00201
@njzjz-bot 10.1021/acs.jctc.1c00201
@njzjz-bot 10.1021/acs.jctc.1c00201
@njzjz Here is the BibTeX entry for 10.1021/acs.jctc.1c00201:
@Article{Zeng_JChemTheoryComput_2021_v17_p6993,
author = {Jinzhe Zeng and Timothy J. Giese and {\c{S}}{\"o}len Ekesan and Darrin
M. York},
title = {{Development of Range-Corrected Deep Learning Potentials for Fast,
Accurate Quantum Mechanical/Molecular Mechanical Simulations of
Chemical Reactions in Solution}},
journal = {J. Chem. Theory Comput.},
year = 2021,
volume = 17,
number = 11,
pages = {6993--7009},
doi = {10.1021/acs.jctc.1c00201},
abstract = {We develop a new deep potential-range correction (DPRc) machine
learning potential for combined quantum mechanical/molecular
mechanical (QM/MM) simulations of chemical reactions in the condensed
phase. The new range correction enables short-ranged QM/MM
interactions to be tuned for higher accuracy, and the correction
smoothly vanishes within a specified cutoff. We further develop an
active learning procedure for robust neural network training. We test
the DPRc model and training procedure against a series of six
nonenzymatic phosphoryl transfer reactions in solution that are
important in mechanistic studies of RNA-cleaving enzymes.
Specifically, we apply DPRc corrections to a base QM model and test
its ability to reproduce free-energy profiles generated from a target
QM model. We perform these comparisons using the MNDO/d and DFTB2
semiempirical models because they differ in the way they treat orbital
orthogonalization and electrostatics and produce free-energy profiles
which differ significantly from each other, thereby providing us a
rigorous stress test for the DPRc model and training procedure. The
comparisons show that accurate reproduction of the free-energy
profiles requires correction of the QM/MM interactions out to 6
{\r{A}}. We further find that the model's initial training benefits
from generating data from temperature replica exchange simulations and
including high-temperature configurations into the fitting procedure,
so the resulting models are trained to properly avoid high-energy
regions. A single DPRc model was trained to reproduce four different
reactions and yielded good agreement with the free-energy profiles
made from the target QM/MM simulations. The DPRc model was further
demonstrated to be transferable to 2D free-energy surfaces and 1D
free-energy profiles that were not explicitly considered in the
training. Examination of the computational performance of the DPRc
model showed that it was fairly slow when run on CPUs but was sped up
almost 100-fold when using NVIDIA V100 GPUs, resulting in almost
negligible overhead. The new DPRc model and training procedure provide
a potentially powerful new tool for the creation of next-generation
QM/MM potentials for a wide spectrum of free-energy applications
ranging from drug discovery to enzyme design.},
}@njzjz-bot 10.1063/5.0211276
@njzjz Here is the BibTeX entry for 10.1063/5.0211276:
@Article{Tao_JChemPhys_2024_v160_p224104,
author = {Yujun Tao and Timothy J. Giese and {\c{S}}{\"o}len Ekesan and Jinzhe
Zeng and B{\'a}lint Aradi and Ben Hourahine and Hasan Metin Aktulga
and Andreas W. G{\"o}tz and Kenneth M. {Merz Jr} and Darrin M. York},
title = {{Amber free energy tools: Interoperable software for free energy
simulations using generalized quantum mechanical/molecular mechanical
and machine learning potentials}},
journal = {J. Chem. Phys.},
year = 2024,
volume = 160,
number = 22,
pages = 224104,
doi = {10.1063/5.0211276},
abstract = {We report the development and testing of new integrated
cyberinfrastructure for performing free energy simulations with
generalized hybrid quantum mechanical/molecular mechanical (QM/MM) and
machine learning potentials (MLPs) in Amber. The Sander molecular
dynamics program has been extended to leverage fast, density-
functional tight-binding models implemented in the DFTB+ and xTB
packages, and an interface to the DeePMD-kit software enables the use
of MLPs. The software is integrated through application program
interfaces that circumvent the need to perform "system calls" and
enable the incorporation of long-range Ewald electrostatics into the
external software's self-consistent field procedure. The
infrastructure provides access to QM/MM models that may serve as the
foundation for QM/MM-{\ensuremath{\Delta}}MLP potentials, which
supplement the semiempirical QM/MM model with a MLP correction trained
to reproduce ab{~}initio QM/MM energies and forces. Efficient
optimization of minimum free energy pathways is enabled through a new
surface-accelerated finite-temperature string method implemented in
the FE-ToolKit package. Furthermore, we interfaced Sander with the
i-PI software by implementing the socket communication protocol used
in the i-PI client-server model. The new interface with i-PI allows
for the treatment of nuclear quantum effects with semiempirical
QM/MM-{\ensuremath{\Delta}}MLP models. The modular interoperable
software is demonstrated on proton transfer reactions in guanine-
thymine mispairs in a B-form deoxyribonucleic acid helix. The current
work represents a considerable advance in the development of modular
software for performing free energy simulations of chemical reactions
that are important in a wide range of applications.},
}