SchNetPack: A Deep Learning Toolbox For Atomistic Systems

SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple acc...

Full description

Saved in:
Bibliographic Details
Published in:Journal of chemical theory and computation Vol. 15; no. 1; p. 448
Main Authors: Schütt, K T, Kessel, P, Gastegger, M, Nicoli, K A, Tkatchenko, A, Müller, K-R
Format: Journal Article
Language:English
Published: United States 08.01.2019
ISSN:1549-9626, 1549-9626
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models. For now, SchNetPack includes implementations of (weighted) atom-centered symmetry functions and the deep tensor neural network SchNet, as well as ready-to-use scripts that allow one to train these models on molecule and material datasets. Based on the PyTorch deep learning framework, SchNetPack allows one to efficiently apply the neural networks to large datasets with millions of reference calculations, as well as parallelize the model across multiple GPUs. Finally, SchNetPack provides an interface to the Atomic Simulation Environment in order to make trained models easily accessible to researchers that are not yet familiar with neural networks.
AbstractList SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models. For now, SchNetPack includes implementations of (weighted) atom-centered symmetry functions and the deep tensor neural network SchNet, as well as ready-to-use scripts that allow one to train these models on molecule and material datasets. Based on the PyTorch deep learning framework, SchNetPack allows one to efficiently apply the neural networks to large datasets with millions of reference calculations, as well as parallelize the model across multiple GPUs. Finally, SchNetPack provides an interface to the Atomic Simulation Environment in order to make trained models easily accessible to researchers that are not yet familiar with neural networks.
SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models. For now, SchNetPack includes implementations of (weighted) atom-centered symmetry functions and the deep tensor neural network SchNet, as well as ready-to-use scripts that allow one to train these models on molecule and material datasets. Based on the PyTorch deep learning framework, SchNetPack allows one to efficiently apply the neural networks to large datasets with millions of reference calculations, as well as parallelize the model across multiple GPUs. Finally, SchNetPack provides an interface to the Atomic Simulation Environment in order to make trained models easily accessible to researchers that are not yet familiar with neural networks.SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical properties of molecules and materials. It contains basic building blocks of atomistic neural networks, manages their training, and provides simple access to common benchmark datasets. This allows for an easy implementation and evaluation of new models. For now, SchNetPack includes implementations of (weighted) atom-centered symmetry functions and the deep tensor neural network SchNet, as well as ready-to-use scripts that allow one to train these models on molecule and material datasets. Based on the PyTorch deep learning framework, SchNetPack allows one to efficiently apply the neural networks to large datasets with millions of reference calculations, as well as parallelize the model across multiple GPUs. Finally, SchNetPack provides an interface to the Atomic Simulation Environment in order to make trained models easily accessible to researchers that are not yet familiar with neural networks.
Author Nicoli, K A
Müller, K-R
Schütt, K T
Kessel, P
Gastegger, M
Tkatchenko, A
Author_xml – sequence: 1
  givenname: K T
  orcidid: 0000-0001-8342-0964
  surname: Schütt
  fullname: Schütt, K T
  organization: Machine Learning Group , Technische Universität Berlin , 10587 Berlin , Germany
– sequence: 2
  givenname: P
  surname: Kessel
  fullname: Kessel, P
  organization: Machine Learning Group , Technische Universität Berlin , 10587 Berlin , Germany
– sequence: 3
  givenname: M
  surname: Gastegger
  fullname: Gastegger, M
  organization: Machine Learning Group , Technische Universität Berlin , 10587 Berlin , Germany
– sequence: 4
  givenname: K A
  surname: Nicoli
  fullname: Nicoli, K A
  organization: Machine Learning Group , Technische Universität Berlin , 10587 Berlin , Germany
– sequence: 5
  givenname: A
  orcidid: 0000-0002-1012-4854
  surname: Tkatchenko
  fullname: Tkatchenko, A
  organization: Physics and Materials Science Research Unit , University of Luxembourg , L-1511 Luxembourg , Luxembourg
– sequence: 6
  givenname: K-R
  surname: Müller
  fullname: Müller, K-R
  organization: Max-Planck-Institut für Informatik , Saarbrücken , Germany
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30481453$$D View this record in MEDLINE/PubMed
BookMark eNpNj81LwzAchoNM3IfePUmOXlrz1TTxNqZTYaiweS7Jr6l2tk1tMnD_vQMneHrfw8PD-07RqPOdQ-iSkpQSRm8MhHQLEVJlCdFEnaAJzYROtGRy9K-P0TSELSGcC8bP0JgToajI-ATpNXw8u_hq4PMWz_Gdcz1eOTN0dfeON9431n_jpR_wPPq2DrEGvN6H6Npwjk4r0wR3ccwZelvebxaPyerl4WkxXyWGSxETW0JeWZtXgknDqkoAiAwMSKOhVEaRjGVUCCMFtbokkFWUSCvBamWdyTWboetfbz_4r50LsTjsANc0pnN-FwpGuZKC5UQe0KsjurOtK4t-qFsz7Iu_u-wH9tRZbA
CitedBy_id crossref_primary_10_1021_acs_jcim_5c00676
crossref_primary_10_1038_s41524_019_0181_4
crossref_primary_10_1021_acscentsci_3c00870
crossref_primary_10_3390_biom12091246
crossref_primary_10_1002_smtd_202300534
crossref_primary_10_1007_s10822_020_00346_6
crossref_primary_10_1039_D4CP00535J
crossref_primary_10_1016_j_pecs_2025_101220
crossref_primary_10_1186_s13321_019_0391_2
crossref_primary_10_1016_j_cpc_2025_109701
crossref_primary_10_1039_D2CS00203E
crossref_primary_10_1088_2632_2153_ad5074
crossref_primary_10_1038_s41467_020_19267_x
crossref_primary_10_1109_MSP_2022_3153277
crossref_primary_10_1016_j_commatsci_2022_111612
crossref_primary_10_1016_j_cpc_2019_02_007
crossref_primary_10_1021_acs_jcim_5c00948
crossref_primary_10_1007_s10822_021_00409_2
crossref_primary_10_1016_j_mtcomm_2025_111997
crossref_primary_10_1038_s41467_024_48609_2
crossref_primary_10_1038_s41563_020_0777_6
crossref_primary_10_1063_5_0274240
crossref_primary_10_1002_aisy_202100014
crossref_primary_10_1038_s41524_022_00734_6
crossref_primary_10_1039_D1SC01542G
crossref_primary_10_1039_D3NR00399J
crossref_primary_10_1039_D3SC00841J
crossref_primary_10_1016_j_compchemeng_2021_107599
crossref_primary_10_1038_s41467_022_28526_y
crossref_primary_10_1038_s41570_020_0189_9
crossref_primary_10_1021_acs_jpclett_5c00952
crossref_primary_10_1016_j_commatsci_2024_112966
crossref_primary_10_1002_qua_26870
crossref_primary_10_1063_5_0155600
crossref_primary_10_1016_j_bpc_2022_106854
crossref_primary_10_1039_D4DD00265B
crossref_primary_10_1088_2632_2153_ada220
crossref_primary_10_1002_jcc_70121
crossref_primary_10_1039_D4CY00763H
crossref_primary_10_1073_pnas_2313023120
crossref_primary_10_1038_s43588_022_00391_1
crossref_primary_10_1088_2632_2153_abfe3f
crossref_primary_10_1088_2632_2153_ad871d
crossref_primary_10_1016_j_mser_2025_101050
crossref_primary_10_1063_5_0021915
crossref_primary_10_1038_s41524_021_00510_y
crossref_primary_10_1038_s41557_022_00950_z
crossref_primary_10_1063_5_0276133
crossref_primary_10_1002_jcc_70081
crossref_primary_10_1016_j_cpc_2022_108580
crossref_primary_10_1016_j_commatsci_2023_112535
crossref_primary_10_1088_1361_648X_ada106
crossref_primary_10_1038_s41524_022_00884_7
crossref_primary_10_3390_molecules26226761
crossref_primary_10_1063_5_0133023
crossref_primary_10_1016_j_chemphys_2021_111347
crossref_primary_10_1039_D4NH00487F
crossref_primary_10_1016_j_mtcomm_2021_102294
crossref_primary_10_1038_s41570_022_00416_3
crossref_primary_10_1021_acs_jctc_4c01386
crossref_primary_10_1088_2632_2153_accd45
crossref_primary_10_1088_1361_6528_adf64b
crossref_primary_10_1088_2632_2153_ad652c
crossref_primary_10_1109_TMBMC_2020_3035383
crossref_primary_10_1021_acs_jctc_5c00340
crossref_primary_10_1039_D5CP01580D
crossref_primary_10_1038_s41467_023_39214_w
crossref_primary_10_1088_2752_5724_ac681d
crossref_primary_10_1063_5_0253847
crossref_primary_10_1139_cjc_2023_0152
crossref_primary_10_1016_j_cpc_2025_109512
crossref_primary_10_1063_5_0159349
crossref_primary_10_1038_s41598_023_46382_8
crossref_primary_10_1038_s43246_022_00315_6
crossref_primary_10_1088_2632_2153_abba6f
crossref_primary_10_1088_2632_2153_ab9c3e
crossref_primary_10_1039_D5CP01632K
crossref_primary_10_1021_acs_jctc_4c01792
crossref_primary_10_1016_j_chempr_2020_12_009
crossref_primary_10_1146_annurev_matsci_070218_010015
crossref_primary_10_1002_wcms_1558
crossref_primary_10_1021_acsomega_5c05634
crossref_primary_10_1039_D5CP02987B
crossref_primary_10_1088_2632_2153_abfd96
crossref_primary_10_1186_s13321_021_00533_z
crossref_primary_10_1002_advs_202302816
crossref_primary_10_1039_D4NR00017J
crossref_primary_10_1007_s40843_023_2836_0
crossref_primary_10_1146_annurev_physchem_042018_052331
crossref_primary_10_1002_qua_27110
crossref_primary_10_3389_fchem_2023_1100210
crossref_primary_10_1021_acs_jcim_4c02441
crossref_primary_10_1038_s41524_022_00865_w
crossref_primary_10_1111_jace_19934
crossref_primary_10_1002_qute_201900023
crossref_primary_10_1007_s10910_022_01334_x
crossref_primary_10_1038_s41467_023_41343_1
crossref_primary_10_1039_D2ME00073C
crossref_primary_10_1002_jcc_70053
crossref_primary_10_1002_jcc_27269
crossref_primary_10_1038_s41524_022_00807_6
crossref_primary_10_1016_j_cclet_2019_12_006
crossref_primary_10_1038_s42004_023_01045_7
crossref_primary_10_1371_journal_pone_0256990
crossref_primary_10_1016_j_commatsci_2021_110567
crossref_primary_10_1557_mrc_2019_107
crossref_primary_10_1021_acs_jctc_5c00085
crossref_primary_10_1038_s41524_022_00736_4
crossref_primary_10_1088_2632_2153_ac9955
crossref_primary_10_1039_D5CP00005J
crossref_primary_10_1002_qua_70036
crossref_primary_10_1038_s41467_024_50407_9
crossref_primary_10_1016_j_commatsci_2024_113459
crossref_primary_10_1109_TPAMI_2021_3115452
crossref_primary_10_1016_j_csbj_2021_06_034
crossref_primary_10_1039_D4SC05655H
crossref_primary_10_1016_j_cpc_2020_107206
crossref_primary_10_1063_5_0155760
crossref_primary_10_1039_D4DD00394B
crossref_primary_10_1063_5_0244175
crossref_primary_10_1039_D4NR02114B
crossref_primary_10_1021_acs_jctc_5c00996
crossref_primary_10_1088_2515_7655_ab2060
crossref_primary_10_1039_D5SC05579B
crossref_primary_10_1002_pssb_202200553
crossref_primary_10_1016_j_mattod_2021_08_012
crossref_primary_10_1016_j_physrep_2021_08_002
crossref_primary_10_1039_D4CP04275A
crossref_primary_10_1038_s41467_025_56481_x
crossref_primary_10_3390_cryst14110930
crossref_primary_10_1038_s41578_020_00255_y
crossref_primary_10_1088_2632_2153_ac191c
crossref_primary_10_1002_aenm_201903242
crossref_primary_10_1016_j_compbiolchem_2022_107656
crossref_primary_10_1063_5_0227821
crossref_primary_10_1038_s41467_019_12875_2
crossref_primary_10_1088_1361_6404_ab7027
crossref_primary_10_1063_1_5126701
crossref_primary_10_1088_1361_651X_ad9d63
crossref_primary_10_1038_s41570_021_00278_1
crossref_primary_10_1038_s41467_024_48567_9
crossref_primary_10_1007_s40192_020_00179_z
crossref_primary_10_1021_acs_jpca_5c02047
crossref_primary_10_1039_D5CP00373C
crossref_primary_10_1063_5_0023697
crossref_primary_10_1016_j_rser_2025_115358
crossref_primary_10_1002_jcc_27327
crossref_primary_10_1063_5_0152215
crossref_primary_10_1029_2022GL100337
crossref_primary_10_1002_wcms_1645
crossref_primary_10_1016_j_cpc_2019_106913
crossref_primary_10_1063_5_0214754
crossref_primary_10_1186_s13321_025_01010_7
crossref_primary_10_1016_j_comptc_2023_114161
crossref_primary_10_1039_C9NR10687A
crossref_primary_10_1016_j_inffus_2024_102923
crossref_primary_10_1038_s41524_019_0221_0
crossref_primary_10_1360_SSC_2024_0270
crossref_primary_10_1021_prechem_4c00060
crossref_primary_10_1038_s41524_025_01762_8
crossref_primary_10_1039_D2SC04056E
crossref_primary_10_1088_2515_7639_ab8c2d
crossref_primary_10_1016_j_joule_2022_08_008
crossref_primary_10_1103_PhysRevMaterials_6_063802
crossref_primary_10_1002_advs_202409009
crossref_primary_10_1016_j_coche_2019_02_008
crossref_primary_10_1073_pnas_2120333119
crossref_primary_10_1021_acs_jpcc_5c01790
crossref_primary_10_3390_computation11050095
crossref_primary_10_1063_5_0287366
crossref_primary_10_1088_2515_7639_ab084b
crossref_primary_10_1088_2632_2153_ad4ae5
crossref_primary_10_1038_s41524_025_01523_7
crossref_primary_10_1038_s41467_023_36666_y
crossref_primary_10_1016_j_micromeso_2024_113219
crossref_primary_10_3390_ma16072633
crossref_primary_10_1007_s11814_021_0869_2
crossref_primary_10_1016_j_scib_2025_07_007
crossref_primary_10_1088_2632_2153_ac6ec6
crossref_primary_10_1038_s41524_021_00650_1
ContentType Journal Article
DBID NPM
7X8
DOI 10.1021/acs.jctc.8b00908
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Chemistry
EISSN 1549-9626
ExternalDocumentID 30481453
Genre Journal Article
GroupedDBID 4.4
53G
55A
5GY
5VS
7~N
AABXI
ABJNI
ABMVS
ABQRX
ABUCX
ACGFS
ACIWK
ACS
ADHLV
AEESW
AENEX
AFEFF
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
AQSVZ
BAANH
CS3
CUPRZ
D0L
DU5
EBS
ED~
EJD
F5P
GGK
GNL
IH9
J9A
JG~
NPM
P2P
RNS
ROL
UI2
VF5
VG9
W1F
7X8
ABBLG
ABLBI
ID FETCH-LOGICAL-a364t-bdc7fbb7f426a2ff4cc45cac6a9cd8a80525144a641b9d0c5f106b6cb98bea792
IEDL.DBID 7X8
ISICitedReferencesCount 335
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000455558200040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1549-9626
IngestDate Fri Jul 11 07:52:23 EDT 2025
Thu Jan 02 23:05:26 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a364t-bdc7fbb7f426a2ff4cc45cac6a9cd8a80525144a641b9d0c5f106b6cb98bea792
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-1012-4854
0000-0001-8342-0964
PMID 30481453
PQID 2138642706
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2138642706
pubmed_primary_30481453
PublicationCentury 2000
PublicationDate 2019-01-08
PublicationDateYYYYMMDD 2019-01-08
PublicationDate_xml – month: 01
  year: 2019
  text: 2019-01-08
  day: 08
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of chemical theory and computation
PublicationTitleAlternate J Chem Theory Comput
PublicationYear 2019
SSID ssj0033423
Score 2.6840625
Snippet SchNetPack is a toolbox for the development and application of deep neural networks that predict potential energy surfaces and other quantum-chemical...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 448
Title SchNetPack: A Deep Learning Toolbox For Atomistic Systems
URI https://www.ncbi.nlm.nih.gov/pubmed/30481453
https://www.proquest.com/docview/2138642706
Volume 15
WOSCitedRecordID wos000455558200040&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3LSgMxFA1qBd34ftQXEdxOO490kriRUi1uHApW6G5IbhLfM7Uzip9vMp3RlSC4yS4Qbm5yT-4J5yB0Jv1QCi1CD2KuPBIr5UlOA08aCHyjKqqqMpugScImEz6qG25F_a2yuROri1rl4Hrk3TCImMXK1I8vpm-ec41y7GptobGIWpGFMi6r6eSbRYicul2ll0qcCmXY0JS2rHUFFJ0nKKHDbN5xn_0OMKtCM1z_7xI30FoNMXF_nhObaEFnW2hl0Di7bSN-Cw-JLkcCns9xH19qPcW1zuo9Huf5i8w_8TCf4X6Zv1ZCzrgWNt9Bd8Or8eDaqy0UPBHFpPSkAmqkpMYWYhEaQwBIDwTEgoNiwvkZWMREREwCyZUPPWOfiDIGyZnUgvJwFy1leab3Eab25EeBoEoxRlTkW-AYisBGT7HY2FdLG502UUnt2hzvIDKdvxfpT1zaaG8e2nQ619JII6dXQ3rRwR9mH6JVC1d41QBhR6hl7AHVx2gZPsrHYnZS7b0dk9HNF6TAuOY
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=SchNetPack%3A+A+Deep+Learning+Toolbox+For+Atomistic+Systems&rft.jtitle=Journal+of+chemical+theory+and+computation&rft.au=Sch%C3%BCtt%2C+K+T&rft.au=Kessel%2C+P&rft.au=Gastegger%2C+M&rft.au=Nicoli%2C+K+A&rft.date=2019-01-08&rft.issn=1549-9626&rft.eissn=1549-9626&rft.volume=15&rft.issue=1&rft.spage=448&rft_id=info:doi/10.1021%2Facs.jctc.8b00908&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-9626&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-9626&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-9626&client=summon