材料领域深度学习模型库和数据库

dlmatreview

This repository contains links to software packages and databases used in deep-learning applications for materials science and engineering. If you would like to contribute similar repositories/packages, please fork this repository, add the information in the current format and make a pull request to this repository. We welcome your contributions!

Citation

https://arxiv.org/abs/2110.14820

Atomistic databases and software packages

Database nameDatasizeWeb
QM9134khttp://quantum-machine.org/datasets/
ANI20 milhttps://github.com/isayev/ANI1 dataset
MD171milhttp://quantum-machine.org/datasets/#md-datasets
Tox21760khttps://tox21.gov/resources/
CCCBDB2069https://cccbdb.nist.gov/
HOPV15350https://doi.org/10.6084/m9.figshare.1610063
C2DB4000https://cmr.fysik.dtu.dk/c2db/c2db.html
FreeSolv504https://github.com/MobleyLab/FreeSolv
MP144khttps://materialsproject.org/
OQMD816khttp://oqmd.org/
AFLOW3.5 milhttp://www.aflowlib.org/
JARVIS-DFT56khttps://jarvis.nist.gov/jarvisdft/
JARVIS-FF2.5khttps://jarvis.nist.gov/jarvisff/
NOMAD11 milhttps://nomad-lab.eu/prod/rae/gui/search
MCloud22milhttps://www.materialscloud.org/home#statistics
CoreMOF163khttps://mof.tech.northwestern.edu/
QMOF22khttps://github.com/arosen93/QMOF
PDB183khttps://www.rcsb.org/
PDBBind23khttp://www.pdbbind.org.cn/
MOAD39khttp://www.bindingmoad.org/

Software packages

ModelnameApplicationsWeb
ALIGNNMol,Solhttps://github.com/usnistgov/alignn
SchNetPackMol,Solhttps://github.com/atomistic-machine-learning/schnetpack
CGCNNSolhttps://github.com/txie-93/cgcnn
MEGNetMol,Solhttps://github.com/materialsvirtuallab/megnet
DimeNetMolhttps://github.com/klicperajo/dimenet
MPNNMolhttps://github.com/priba/nmpqc
ANIMolhttps://github.com/isayev/ASEANI
AmpSolhttps://bitbucket.org/andrewpeterson/amp
TensorMolMolhttps://github.com/jparkhill/TensorMol
PROPhetSolhttps://github.com/biklooost/PROPhet
DeepMDMolhttps://github.com/deepmodeling/deepmd-kit
ænetSolhttps://github.com/atomisticnet/aenet
E3NNMolhttps://github.com/e3nn/e3nn
neural-fingerprintMolhttps://github.com/HIPS/neural-fingerprint
DeepChemStableMolhttps://github.com/MingCPU/DeepChemStable
MoleculeNetMol,Solhttps://github.com/deepchem/deepchem
dgl-lifesciProthttps://github.com/awslabs/dgl-lifesci
gninaProthttps://github.com/gnina/gnina

Chemicalformula

ModelnameWeb
MatMinerhttps://github.com/hackingmaterials/matminer
MagPiehttps://bitbucket.org/wolverton/magpie
DScribehttps://github.com/SINGROUP/dscribe
ElemNethttps://github.com/NU-CUCIS/ElemNet
IRNethttps://github.com/NU-CUCIS/IRNet
Roosthttps://github.com/CompRhys/roost
CrabNethttps://github.com/anthony-wang/CrabNet
CFID-Chemhttps://github.com/usnistgov/jarvis/
Atom2vechttps://github.com/idocx/Atom2Vec

SMILES and fragments

Software nameWeb
DeepSMILEShttps://github.com/baoilleach/deepsmiles
ChemicalVAEhttps://github.com/aspuru-guzik-group/chemicalvae
CVAEhttps://github.com/jaechanglim/CVAE
DeepChemhttps://github.com/deepchem/deepchem
DeepFRAGhttps://git.durrantlab.pitt.edu/jdurrant/deepfrag/
DeepFRAG-khttps://github.com/yaohangli/DeepFragK/

Spectra based

DBnameDatasizeWeb
MPXAS-DB490khttps://materialsproject.org/
JVDielec.func.16khttp://jarvis.nist.gov/jarvisdft
JVInfrared5khttp://jarvis.nist.gov/jarvisdft
RRUFF3527https://rruff.info
ICDDXRD1076439https://www.icdd.com/pdf-product-summary/
ICSDXRD150000https://icsd.nist.gov/
MPXRD140000https://materialsproject.org/
JVXRD60000https://jarvis.nist.gov/jarvisdft/
Ramanopendb1133https://solsa.crystallography.net/rod/index.php
Chem.WebBook1133https://webbook.nist.gov/chemistry/
SDBS34600http://sdbs.riodb.aist.go.jp/sdbs/cgi-bin/creindex.cgi
NMRShiftDB44371https://nmrshiftdb.nmr.uni-koeln.de/
SpectraBase?https://spectrabase.com/
SOPspectrallib.325https://soprano.kikirpa.be/index.php?lib=sop
HTEM140000https://htem.nrel.gov/
SoftwarenameApplicationsWebpage
DOSNetSolhttps://github.com/vxfung/DOSnet
PCA-CGCNNSolhttps://github.com/kihoon-bang/PCA-CGCNN
autoXRDSolhttps://github.com/PV-Lab/autoXRD

Image based

DB NameLink
JARVIS-STMhttps://jarvis.nist.gov/jarvisstm
atomaginedhttps://github.com/MaterialEyes/atomagined
deep damagehttps://git.rwth-aachen.de/Sandra.Korte.Kerzel/DeepDamage/
NanoSEMhttps://doi.org/10.1038/sdata.2018.172
UHCSDBhttp://hdl.handle.net/11256/940
UHCS microconst. DBhttp://hdl.handle.net/11256/964
SmBFOhttps://drive.google.com/
Diranethttps://github.com/arturluis/diranet
Peregrine v2021-03https://doi.org/10.13139/ORNLNCCS/1779073
Microscopy Datasetshttps://github.com/Jerey-Ede/datasets/wiki
Software packages
Package NameLink
PyCroscopyhttps://github.com/pycroscopy/pycroscopy
Prismatichttps://github.com/prism-em/prismatic
py4DSTEMhttps://github.com/py4dstem/py4DSTEM
abTEMhttps://github.com/jacobjma/abTEM
QSTEMhttps://github.com/QSTEM/QSTEM
MuSTEMhttps://github.com/HamishGBrown/MuSTEM
AICrystallographerhttps://github.com/pycroscopy/AICrystallographer
AtomAIhttps://github.com/pycroscopy/atomai
NionSwifthttps://github.com/nion-software/nionswift
EENCMhttps://github.com/ceright1/Prediction-material-property
DefectSegNethttps://github.com/rajatsainju/DefectSegNet
AMPIShttps://github.com/rccohn/AMPIS
partial-STEMhttps://github.com/Jefrey-Ede/partial-STEM/tree/1.0.0
ZeroCostDL4Michttps://github.com/HenriquesLab/ZeroCostDL4Mic

NLP

SoftwarenameLink
Borgeshttps://github.com/CederGroupHub/Borges
ChemDataExtractorhttp://chemdataextractor.org
ChemicalTaggerhttps://github.com/BlueObelisk/chemicaltagger
ChemListemhttps://bitbucket.org/rscapplications/chemlistem/
ChemSpothttps://github.com/rockt/ChemSpot
LBNLPhttps://github.com/lbnlp/lbnlp
mat2vechttps://github.com/materialsintelligence/mat2vec
MaterialsParserhttps://github.com/CederGroupHub/MaterialParser
OSCAR4https://github.com/BlueObelisk/oscar4
SynthesisProjecthttps://www.synthesisproject.org
tmChemhttps://www.ncbi.nlm.nih.gov/research/bionlp/Tools/tmchem/
  • 0
    点赞
  • 22
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
创建远程学习材料和搭建学习者模型库是为自适应学习系统提供个性化学习体验所必需的步骤。下面是一些关键步骤和考虑事项: 1. 收集学习材料:收集适合不同学习者的学习材料,包括教科书、课程讲义、视频教程、练习题等。确保这些材料涵盖了各个知识领域和难度级别,并且具备适应不同学习风格和兴趣的特点。 2. 标记和组织材料:对收集到的学习材料进行标记和分类,以便系统能够根据学习者的需求和兴趣进行个性化推荐。标记包括主题、难度级别、类型等,组织可以采用目录结构或者关系数据库等方式。 3. 构建学习者模型库:建立一个学习者模型库,用于存储和管理学习者的个性化信息。这些信息可以包括学习者的兴趣、学习历史、学习目标、能力评估等。确保数据库的设计能够支持高效的查询和更新操作。 4. 数据分析和预处理:对学习者模型库中的数据进行分析和预处理,以发现学习者的学习模式和特征。这可以通过数据挖掘和机器学习技术来实现,例如聚类、关联规则挖掘、特征工程等。 5. 构建推荐系统:利用学习者模型库和学习材料库,构建个性化推荐系统。这包括选择合适的推荐算法,例如基于内容的推荐、协同过滤、深度学习推荐等。推荐系统需要根据学习者的个性化信息和学习材料的特点,为学习者提供最相关和有针对性的学习资源。 6. 不断优化和改进:通过对学习者的反馈和系统性能的评估,不断优化和改进远程学习材料和学习者模型库。这可以包括更新学习材料、更新模型库的数据录入方式、优化推荐算法等。 通过以上步骤,可以建立一个完善的远程学习材料和学习者模型库,为自适应学习系统提供个性化的学习体验,提高学习效果和用户满意度。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值