MolEM: a unified generative framework for molecular graphs and sequential orders

Abstract Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Briefings in bioinformatics Ročník 26; číslo 2
Hlavní autoři:	Zhang, Hanwen, Xiong, Deng, Liu, Xianggen, Lv, Jiancheng
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	England Oxford University Press 04.03.2025 Oxford Publishing Limited (England)
Témata:	Affinity Algorithms Binding Drug Design Drug development Graphs Lower bounds Molecular docking Molecular Docking Simulation Problem Solving Protocol Proteins - chemistry Proteins - metabolism Software Training structure-based drug design sequential generative model molecular graph generation variational expectation-maximization sequential order
ISSN:	1467-5463, 1477-4054, 1477-4054
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Abstract Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then maximize the likelihood of the resulting sequences. However, the exact likelihood is computationally intractable, which involves a sum over all possible sequential orders. Molecular graphs lack an inherent order and the number of orders is factorial in the graph size. To avoid the intractable full space of factorially-many orders, existing works pre-define a fixed node ordering scheme such as depth-first search to sequentialize the 3D molecular graphs. In these cases, the training objectives are loose lower bounds of the exact likelihoods which are suboptimal for generation. To address the challenges, we propose a unified generative framework named MolEM to learn the 3D molecular graphs and corresponding sequential orders jointly. We derive a tight lower bound of the likelihood and maximize it via variational expectation-maximization algorithm, opening a new line of research in learning-based ordering schemes for 3D molecular graph generation. Besides, we first incorporate the molecular docking method QuickVina 2 to manipulate the binding poses, leading to accurate and flexible ligand conformations. Experimental results demonstrate that MolEM significantly outperforms baseline models in generating molecules with high binding affinities and realistic structures. Our approach efficiently approximates the true marginal graph likelihood and identifies reasonable orderings for 3D molecular graphs, aligning well with relevant chemical priors.
AbstractList	Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then maximize the likelihood of the resulting sequences. However, the exact likelihood is computationally intractable, which involves a sum over all possible sequential orders. Molecular graphs lack an inherent order and the number of orders is factorial in the graph size. To avoid the intractable full space of factorially-many orders, existing works pre-define a fixed node ordering scheme such as depth-first search to sequentialize the 3D molecular graphs. In these cases, the training objectives are loose lower bounds of the exact likelihoods which are suboptimal for generation. To address the challenges, we propose a unified generative framework named MolEM to learn the 3D molecular graphs and corresponding sequential orders jointly. We derive a tight lower bound of the likelihood and maximize it via variational expectation-maximization algorithm, opening a new line of research in learning-based ordering schemes for 3D molecular graph generation. Besides, we first incorporate the molecular docking method QuickVina 2 to manipulate the binding poses, leading to accurate and flexible ligand conformations. Experimental results demonstrate that MolEM significantly outperforms baseline models in generating molecules with high binding affinities and realistic structures. Our approach efficiently approximates the true marginal graph likelihood and identifies reasonable orderings for 3D molecular graphs, aligning well with relevant chemical priors. Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then maximize the likelihood of the resulting sequences. However, the exact likelihood is computationally intractable, which involves a sum over all possible sequential orders. Molecular graphs lack an inherent order and the number of orders is factorial in the graph size. To avoid the intractable full space of factorially-many orders, existing works pre-define a fixed node ordering scheme such as depth-first search to sequentialize the 3D molecular graphs. In these cases, the training objectives are loose lower bounds of the exact likelihoods which are suboptimal for generation. To address the challenges, we propose a unified generative framework named MolEM to learn the 3D molecular graphs and corresponding sequential orders jointly. We derive a tight lower bound of the likelihood and maximize it via variational expectation-maximization algorithm, opening a new line of research in learning-based ordering schemes for 3D molecular graph generation. Besides, we first incorporate the molecular docking method QuickVina 2 to manipulate the binding poses, leading to accurate and flexible ligand conformations. Experimental results demonstrate that MolEM significantly outperforms baseline models in generating molecules with high binding affinities and realistic structures. Our approach efficiently approximates the true marginal graph likelihood and identifies reasonable orderings for 3D molecular graphs, aligning well with relevant chemical priors.Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then maximize the likelihood of the resulting sequences. However, the exact likelihood is computationally intractable, which involves a sum over all possible sequential orders. Molecular graphs lack an inherent order and the number of orders is factorial in the graph size. To avoid the intractable full space of factorially-many orders, existing works pre-define a fixed node ordering scheme such as depth-first search to sequentialize the 3D molecular graphs. In these cases, the training objectives are loose lower bounds of the exact likelihoods which are suboptimal for generation. To address the challenges, we propose a unified generative framework named MolEM to learn the 3D molecular graphs and corresponding sequential orders jointly. We derive a tight lower bound of the likelihood and maximize it via variational expectation-maximization algorithm, opening a new line of research in learning-based ordering schemes for 3D molecular graph generation. Besides, we first incorporate the molecular docking method QuickVina 2 to manipulate the binding poses, leading to accurate and flexible ligand conformations. Experimental results demonstrate that MolEM significantly outperforms baseline models in generating molecules with high binding affinities and realistic structures. Our approach efficiently approximates the true marginal graph likelihood and identifies reasonable orderings for 3D molecular graphs, aligning well with relevant chemical priors. Abstract Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies employ sequential generative models. Their standard training method is to sequentialize molecular graphs into ordered sequences and then maximize the likelihood of the resulting sequences. However, the exact likelihood is computationally intractable, which involves a sum over all possible sequential orders. Molecular graphs lack an inherent order and the number of orders is factorial in the graph size. To avoid the intractable full space of factorially-many orders, existing works pre-define a fixed node ordering scheme such as depth-first search to sequentialize the 3D molecular graphs. In these cases, the training objectives are loose lower bounds of the exact likelihoods which are suboptimal for generation. To address the challenges, we propose a unified generative framework named MolEM to learn the 3D molecular graphs and corresponding sequential orders jointly. We derive a tight lower bound of the likelihood and maximize it via variational expectation-maximization algorithm, opening a new line of research in learning-based ordering schemes for 3D molecular graph generation. Besides, we first incorporate the molecular docking method QuickVina 2 to manipulate the binding poses, leading to accurate and flexible ligand conformations. Experimental results demonstrate that MolEM significantly outperforms baseline models in generating molecules with high binding affinities and realistic structures. Our approach efficiently approximates the true marginal graph likelihood and identifies reasonable orderings for 3D molecular graphs, aligning well with relevant chemical priors.
Author	Xiong, Deng Lv, Jiancheng Liu, Xianggen Zhang, Hanwen
Author_xml	– sequence: 1 givenname: Hanwen orcidid: 0009-0001-4760-2338 surname: Zhang fullname: Zhang, Hanwen – sequence: 2 givenname: Deng surname: Xiong fullname: Xiong, Deng – sequence: 3 givenname: Xianggen surname: Liu fullname: Liu, Xianggen email: liuxianggen@scu.edu.cn – sequence: 4 givenname: Jiancheng surname: Lv fullname: Lv, Jiancheng email: lvjiancheng@scu.edu.cn
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/40163755$$D View this record in MEDLINE/PubMed
BookMark	eNp9kd1LHDEUxYNY_GqffC-BQimU0WSSbGZ8kSLWFhT7YJ9DPm7W2JlkTXYU__tm2VW0D326F-6Pc8-9Zx9txxQBoUNKjijp2bEJ5tgY7UnPt9Ae5VI2nAi-vepnshF8xnbRfil3hLREdnQH7XJCZ0wKsYd-XaXh_OoEazzF4AM4PIcIWS_DA2Cf9QiPKf_BPmU8pgHsNOiM51kvbgvW0eEC9xPEZdADTtlBLu_RO6-HAh829QD9_n5-c_ajuby--Hn27bKxdfmyYdBzaw3veAvUdZSBNN4S6VxrfOeIML10lkrrZS-IBO2pFq02XtPWekbYATpd6y4mM4Kz1UTWg1rkMOr8pJIO6u0khls1Tw-K0l7IdsarwpeNQk71iLJUYygWhkFHSFNRjHZcSEF6UdFP_6B3acqx3qdYy7tO1H-uLH18benFy_O3K_B1DdicSsngXxBK1CpLVbNUmywr_XlNp2nxX_AvwKmgWw
Cites_doi	10.1039/D1SC04444C 10.1021/acs.jcim.1c00203 10.1038/s43588-023-00530-2 10.1093/bioinformatics/btv082 10.1111/j.2517-6161.1977.tb01600.x 10.1145/3366423.3380201 10.1016/j.sbi.2023.102548 10.1006/jmbi.1996.0897 10.1021/acs.jmedchem.1c01830 10.1038/s43588-023-00511-5 10.1093/bib/bbac520 10.1039/D1SC05976A 10.1038/s41467-024-48837-6 10.1093/bib/bbab072 10.1093/bib/bbad323 10.1038/s43588-024-00627-2 10.1002/jcc.21256 10.1186/s13321-015-0069-3 10.1021/acs.jcim.2c01057 10.1016/j.addr.2012.09.019 10.1021/acscentsci.3c00572 10.1021/jm020017n 10.1080/07391102.2023.2257800 10.1016/j.drudis.2022.103439 10.1021/jm0306430 10.1038/s42256-021-00409-9 10.1038/s41467-024-47011-2 10.1039/D3SC06803J 10.1038/s41467-024-46569-1 10.1039/D3SC04091G 10.1038/s41467-022-34692-w 10.1038/s42256-023-00775-6 10.1021/acs.jcim.0c00411 10.1038/s42256-024-00815-9 10.1038/s43588-024-00737-x 10.1038/s42256-024-00808-8 10.1021/cc9800071
ContentType	Journal Article
Copyright	The Author(s) 2025. Published by Oxford University Press. 2025 The Author(s) 2025. Published by Oxford University Press. 2025 The Author(s) 2025. Published by Oxford University Press. This work is published under https://creativecommons.org/licenses/by-nc/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2025. Published by Oxford University Press. 2025 – notice: The Author(s) 2025. Published by Oxford University Press. – notice: 2025 The Author(s) 2025. Published by Oxford University Press. This work is published under https://creativecommons.org/licenses/by-nc/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	TOX AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 7SC 8FD FR3 JQ2 K9. L7M L~C L~D P64 RC3 7X8 5PM
DOI	10.1093/bib/bbaf094
DatabaseName	Oxford Journals Open Access Collection CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Biotechnology Research Abstracts Computer and Information Systems Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts Genetics Abstracts MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Genetics Abstracts Biotechnology Research Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Health & Medical Complete (Alumni) Engineering Research Database Advanced Technologies Database with Aerospace Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	MEDLINE Genetics Abstracts CrossRef 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: TOX name: Oxford Journals Open Access Collection url: https://academic.oup.com/journals/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	1477-4054
ExternalDocumentID	PMC11957264 40163755 10_1093_bib_bbaf094 10.1093/bib/bbaf094
Genre	Journal Article
GrantInformation_xml	– fundername: Natural Science Foundation of Sichuan Province grantid: 2023NSFSC1408 – fundername: Sichuan Province Engineering Technology Research Center of Broadband Electronics Intelligent Manufacturing – fundername: Fundamental Research Funds for the Central Universities grantid: 1082204112364 – fundername: National Natural Science Foundation of China grantid: 62206192 – fundername: National Major Scientific Instruments and Equipments Development Project of National Natural Science Foundation of China grantid: 62427820 – fundername: ; – fundername: ; grantid: 62206192 – fundername: ; grantid: 1082204112364 – fundername: ; grantid: 62427820 – fundername: ; grantid: 2023NSFSC1408; 2024NSFTD0048
GroupedDBID	--- -E4 .2P .I3 0R~ 1TH 23N 2WC 36B 4.4 48X 53G 5GY 5VS 6J9 70D 77I 8VB AAGQS AAHBH AAIJN AAIMJ AAJKP AAJQQ AAMDB AAMVS AAOGV AAPQZ AAPXW AARHZ AAUQX AAVAP AAVLN ABDBF ABEJV ABEUO ABGNP ABIXL ABNKS ABPQP ABPTD ABQLI ABWST ABXVV ABXZS ABZBJ ACGFO ACGFS ACGOD ACIWK ACPRK ACUFI ACUHS ACUXJ ACYTK ADBBV ADEYI ADFTL ADGKP ADGZP ADHKW ADHZD ADOCK ADPDF ADQBN ADRDM ADRTK ADVEK ADYVW ADZTZ ADZXQ AECKG AEGPL AEGXH AEJOX AEKKA AEKSI AELWJ AEMDU AEMOZ AENEX AENZO AEPUE AETBJ AEWNT AFFZL AFGWE AFIYH AFOFC AFRAH AGINJ AGKEF AGQXC AGSYK AHGBF AHMBA AHQJS AHXPO AIAGR AIJHB AJEEA AJEUX AKHUL AKVCP AKWXX ALMA_UNASSIGNED_HOLDINGS ALTZX ALUQC ALXQX AMNDL ANAKG APIBT APWMN ARIXL AXUDD AYOIW AZVOD BAWUL BAYMD BEYMZ BHONS BQDIO BQUQU BSWAC BTQHN C1A C45 CAG CDBKE COF CS3 CZ4 DAKXR DIK DILTD DU5 D~K E3Z EAD EAP EAS EBA EBC EBD EBR EBS EBU EE~ EJD EMB EMK EMOBN EST ESX F5P F9B FHSFR FLIZI FLUFQ FOEOM FQBLK GAUVT GJXCC GROUPED_DOAJ GX1 H13 H5~ HAR HW0 HZ~ IOX J21 JXSIZ K1G KBUDW KOP KSI KSN M-Z MK~ ML0 N9A NGC NLBLG NMDNZ NOMLY NU- O0~ O9- OAWHX ODMLO OJQWA OK1 OVD OVEED P2P PAFKI PEELM PQQKQ Q1. Q5Y QWB RD5 RPM RUSNO RW1 RXO SV3 TEORI TH9 TJP TLC TOX TR2 TUS W8F WOQ X7H YAYTL YKOAZ YXANX ZKX ZL0 ~91 AAYXX CITATION ROX CGR CUY CVF ECM EIF NPM 7QO 7SC 8FD FR3 JQ2 K9. L7M L~C L~D P64 RC3 7X8 5PM
ID	FETCH-LOGICAL-c401t-3e94ccb4842e1d813e7bfc07dd2bf8d05b97dc17cf79507eaf1a52abfa12cf303
IEDL.DBID	TOX
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001482373500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1467-5463 1477-4054
IngestDate	Tue Sep 30 17:04:44 EDT 2025 Fri Sep 05 17:50:34 EDT 2025 Thu Nov 13 06:22:08 EST 2025 Mon Jul 21 05:41:37 EDT 2025 Sat Nov 29 08:08:21 EST 2025 Mon Nov 17 07:40:34 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	structure-based drug design sequential generative model molecular graph generation variational expectation-maximization sequential order
Language	English
License	This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com https://creativecommons.org/licenses/by-nc/4.0 The Author(s) 2025. Published by Oxford University Press.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c401t-3e94ccb4842e1d813e7bfc07dd2bf8d05b97dc17cf79507eaf1a52abfa12cf303
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0009-0001-4760-2338
OpenAccessLink	https://dx.doi.org/10.1093/bib/bbaf094
PMID	40163755
PQID	3248850160
PQPubID	26846
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_11957264 proquest_miscellaneous_3184575095 proquest_journals_3248850160 pubmed_primary_40163755 crossref_primary_10_1093_bib_bbaf094 oup_primary_10_1093_bib_bbaf094
PublicationCentury	2000
PublicationDate	2025-Mar-04
PublicationDateYYYYMMDD	2025-03-04
PublicationDate_xml	– month: 03 year: 2025 text: 2025-Mar-04 day: 04
PublicationDecade	2020
PublicationPlace	England
PublicationPlace_xml	– name: England – name: Oxford
PublicationTitle	Briefings in bioinformatics
PublicationTitleAlternate	Brief Bioinform
PublicationYear	2025
Publisher	Oxford University Press Oxford Publishing Limited (England)
Publisher_xml	– name: Oxford University Press – name: Oxford Publishing Limited (England)
References	Dempster (2025033118431917300_ref49) 1977; 39 Han (2025033118431917300_ref27) 2023; 24 Cohen-Karlik (2025033118431917300_ref14) 2024; 2024 Shuqi (2025033118431917300_ref6) 2024; 2024 Li (2025033118431917300_ref31) 2023; 24 Zhou (2025033118431917300_ref46) Long (2025033118431917300_ref35) 2022; 35 Danel (2025033118431917300_ref51) 2023; 28 Zhang (2025033118431917300_ref56) 2021; 34 Masuda (2025033118431917300_ref8) Zhang (2025033118431917300_ref34) 2023 Yuejiang (2025033118431917300_ref36) Li (2025033118431917300_ref20) Francoeur (2025033118431917300_ref59) 2020; 60 Méndez-Lucio (2025033118431917300_ref2) 2021; 3 Yanru (2025033118431917300_ref7) Hongyan (2025033118431917300_ref5) 2023; 14 Goyal (2025033118431917300_ref21) 2020 Zhang (2025033118431917300_ref26) 2023; 3 Zhung (2025033118431917300_ref28) 2024; 15 Winter (2025033118431917300_ref22) 2021; 34 Min (2025033118431917300_ref57) Isert (2025033118431917300_ref23) 2023; 79 Morris (2025033118431917300_ref39) 2009; 30 Corso (2025033118431917300_ref44) 2023 Meng (2025033118431917300_ref54) 2019 Friesner (2025033118431917300_ref42) 2004; 47 Peng (2025033118431917300_ref25) 2022 Bajusz (2025033118431917300_ref63) 2015; 7 Siebenmorgen (2025033118431917300_ref66) 2024; 4 Zhang (2025033118431917300_ref58) 2023 Zhu (2025033118431917300_ref38) 2024; 15 Eberhardt (2025033118431917300_ref40) 2021; 61 Wang (2025033118431917300_ref47) 2023; 24 Zhang (2025033118431917300_ref4) Lipinski (2025033118431917300_ref61) 2012; 64 Ragoza (2025033118431917300_ref9) Bryant (2025033118431917300_ref48) 2024; 15 Hongyu (2025033118431917300_ref3) 2023; 42 Powers (2025033118431917300_ref50) 2023 Jiang (2025033118431917300_ref29) 2024; 6 Wang (2025033118431917300_ref1) 2021; 22 Ragoza (2025033118431917300_ref10) 2022; 13 Guan (2025033118431917300_ref12) 2023 Schneuing (2025033118431917300_ref11) Krasoulis (2025033118431917300_ref45) 2022; 62 Irwin (2025033118431917300_ref17) Zhang (2025033118431917300_ref37) 2023; 3 Jiang (2025033118431917300_ref30) 2021; 64 Jones (2025033118431917300_ref43) 1997; 267 Tanimoto (2025033118431917300_ref64) 1958 Sun (2025033118431917300_ref55) 2020 Ghose (2025033118431917300_ref60) 1999; 1 Igashov (2025033118431917300_ref15) 2024; 6 Chen (2025033118431917300_ref18) 2021 Jing (2025033118431917300_ref33) 2022; 35 Norris (2025033118431917300_ref52) 1998 Kelvinius (2025033118431917300_ref19) 2023 Huang (2025033118431917300_ref13) 2024; 15 Li (2025033118431917300_ref65) 2022; 13 Borman (2025033118431917300_ref53) Kong (2025033118431917300_ref16) 2023 Alhossary (2025033118431917300_ref41) 2015; 31 Feng (2025033118431917300_ref32) 2024; 6 Veber (2025033118431917300_ref62) 2002; 45 Li (2025033118431917300_ref24) 2021; 12
References_xml	– volume: 35 start-page: 24240 year: 2022 ident: 2025033118431917300_ref33 article-title: Torsional diffusion for molecular conformer generation publication-title: Adv Neural Inf Process Syst – volume: 12 start-page: 13664 year: 2021 ident: 2025033118431917300_ref24 article-title: Structure-based de novo drug design using 3D deep generative models publication-title: Chem Sci doi: 10.1039/D1SC04444C – start-page: 17644 volume-title: International Conference on Machine Learning year: 2022 ident: 2025033118431917300_ref25 article-title: Pocket2Mol: efficient molecular sampling based on 3D protein pockets – volume: 61 start-page: 3891 year: 2021 ident: 2025033118431917300_ref40 article-title: AutoDock Vina 1.2. 0: new docking methods, expanded force field, and Python bindings publication-title: J Chem Inf Model doi: 10.1021/acs.jcim.1c00203 – volume: 3 start-page: 849 year: 2023 ident: 2025033118431917300_ref26 article-title: Learning on topological surface and geometric structure for 3D molecular generation publication-title: Nat Comput Sci doi: 10.1038/s43588-023-00530-2 – volume: 31 start-page: 2214 year: 2015 ident: 2025033118431917300_ref41 article-title: Fast, accurate, and reliable molecular docking with QuickVina 2 publication-title: Bioinformatics doi: 10.1093/bioinformatics/btv082 – volume: 34 start-page: 3218 year: 2021 ident: 2025033118431917300_ref56 article-title: VigDet: knowledge informed neural temporal point process for coordination detection on social media publication-title: Adv Neural Inf Process Syst – volume: 39 start-page: 1 year: 1977 ident: 2025033118431917300_ref49 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J R Stat Soc B Methodol doi: 10.1111/j.2517-6161.1977.tb01600.x – start-page: 1253 volume-title: Proceedings of the Web Conference 2020 year: 2020 ident: 2025033118431917300_ref21 article-title: GraphGen: a scalable approach to domain-agnostic labeled graph generation doi: 10.1145/3366423.3380201 – volume: 79 start-page: 102548 year: 2023 ident: 2025033118431917300_ref23 article-title: Structure-based drug design with geometric deep learning publication-title: Curr Opin Struct Biol doi: 10.1016/j.sbi.2023.102548 – ident: 2025033118431917300_ref17 article-title: Efficient 3D molecular generation with flow matching and scale optimal transport – volume: 267 start-page: 727 year: 1997 ident: 2025033118431917300_ref43 article-title: Development and validation of a genetic algorithm for flexible docking publication-title: J Mol Biol doi: 10.1006/jmbi.1996.0897 – volume: 64 start-page: 18209 year: 2021 ident: 2025033118431917300_ref30 article-title: InteractionGraphNet: a novel and efficient deep graph representation learning framework for accurate protein–ligand interaction predictions publication-title: J Med Chem doi: 10.1021/acs.jmedchem.1c01830 – ident: 2025033118431917300_ref4 article-title: A survey on graph diffusion models: generative AI in science for molecule, protein and material – volume: 3 start-page: 789 year: 2023 ident: 2025033118431917300_ref37 article-title: Efficient and accurate large library ligand docking with KarmaDock publication-title: Nat Comput Sci doi: 10.1038/s43588-023-00511-5 – start-page: 9249 volume-title: International Conference on Machine Learning year: 2020 ident: 2025033118431917300_ref55 article-title: An EM approach to non-autoregressive conditional sequence generation – volume: 24 year: 2023 ident: 2025033118431917300_ref47 article-title: A fully differentiable ligand pose optimization framework guided by deep learning and a traditional scoring function publication-title: Brief Bioinform doi: 10.1093/bib/bbac520 – volume-title: Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research ident: 2025033118431917300_ref7 article-title: MolCRAFT: structure-based drug design in continuous parameter space – volume-title: International Conference on Machine Learning year: 2023 ident: 2025033118431917300_ref19 article-title: Autoregressive diffusion models with non-uniform generation order – volume-title: Markov Chains. Cambridge Series in Statistical and Probabilistic Mathematics year: 1998 ident: 2025033118431917300_ref52 – volume: 35 start-page: 23894 year: 2022 ident: 2025033118431917300_ref35 article-title: Zero-shot 3D drug design by sketching and generating publication-title: Adv Neural Inf Process Syst – ident: 2025033118431917300_ref53 article-title: The expectation maximization algorithm-a short tutorial – volume: 13 start-page: 2701 year: 2022 ident: 2025033118431917300_ref10 article-title: Generating 3D molecules conditional on receptor binding sites with deep generative models publication-title: Chem Sci doi: 10.1039/D1SC05976A – volume: 15 start-page: 4536 year: 2024 ident: 2025033118431917300_ref48 article-title: Structure prediction of protein-ligand complexes from sequence information with Umol publication-title: Nat Commun doi: 10.1038/s41467-024-48837-6 – volume: 22 start-page: bbab072 year: 2021 ident: 2025033118431917300_ref1 article-title: DeepDTAF: a deep learning method to predict protein–ligand binding affinity publication-title: Brief Bioinform doi: 10.1093/bib/bbab072 – volume: 24 year: 2023 ident: 2025033118431917300_ref31 article-title: 3D based generative protac linker design with reinforcement learning publication-title: Brief Bioinform doi: 10.1093/bib/bbad323 – volume: 4 year: 2024 ident: 2025033118431917300_ref66 article-title: MISATO: machine learning dataset of protein–ligand complexes for structure-based drug discovery publication-title: Nat Comput Sci doi: 10.1038/s43588-024-00627-2 – volume: 2024 year: 2024 ident: 2025033118431917300_ref14 article-title: Overcoming order in autoregressive graph generation publication-title: Transact Mach Learn Res – volume: 30 start-page: 2785 year: 2009 ident: 2025033118431917300_ref39 article-title: AutoDock4 and AutoDockTools4: automated docking with selective receptor flexibility publication-title: J Comput Chem doi: 10.1002/jcc.21256 – start-page: 1630 volume-title: International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research year: 2021 ident: 2025033118431917300_ref18 article-title: Order matters: probabilistic modeling of node sequence for graph generation – volume: 7 start-page: 1 year: 2015 ident: 2025033118431917300_ref63 article-title: Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? publication-title: J Chem doi: 10.1186/s13321-015-0069-3 – ident: 2025033118431917300_ref9 article-title: Learning a continuous representation of 3D molecular structures with deep generative models – volume: 62 start-page: 4642 year: 2022 ident: 2025033118431917300_ref45 article-title: DENVIS: scalable and high-throughput virtual screening using graph neural networks with atomic and surface protein pocket features publication-title: J Chem Inf Model doi: 10.1021/acs.jcim.2c01057 – volume: 34 start-page: 9559 year: 2021 ident: 2025033118431917300_ref22 article-title: Permutation-invariant variational autoencoder for graph-level representation learning publication-title: Adv Neural Inf Process Syst – ident: 2025033118431917300_ref46 article-title: Do deep learning methods really perform better in molecular conformation generation? – volume: 64 start-page: 4 year: 2012 ident: 2025033118431917300_ref61 article-title: Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings publication-title: Adv Drug Deliv Rev doi: 10.1016/j.addr.2012.09.019 – volume: 24 start-page: 1 year: 2023 ident: 2025033118431917300_ref27 article-title: Fitting autoregressive graph generative models through maximum likelihood estimation publication-title: J Mach Learn Res – start-page: 17391 volume-title: International Conference on Machine Learning year: 2023 ident: 2025033118431917300_ref16 article-title: Autoregressive diffusion model for graph generation – start-page: 2257 volume-title: Geometric Deep Learning for Structure-Based Ligand Design year: 2023 ident: 2025033118431917300_ref50 doi: 10.1021/acscentsci.3c00572 – volume-title: International Conference on Learning Representations year: 2023 ident: 2025033118431917300_ref58 article-title: Molecule generation for target protein binding with structural motifs – volume: 45 start-page: 2615 year: 2002 ident: 2025033118431917300_ref62 article-title: Molecular properties that influence the oral bioavailability of drug candidates publication-title: J Med Chem doi: 10.1021/jm020017n – start-page: 5241 volume-title: International Conference on Machine Learning year: 2019 ident: 2025033118431917300_ref54 article-title: GMNN: graph Markov neural networks – volume: 42 start-page: 10565 year: 2023 ident: 2025033118431917300_ref3 article-title: The binding mechanism of failed, in processing and succeed inhibitors target SARS-CoV-2 main protease publication-title: J Biomol Struct Dyn doi: 10.1080/07391102.2023.2257800 – volume: 28 start-page: 103439 year: 2023 ident: 2025033118431917300_ref51 article-title: Docking-based generative approaches in the search for new drug candidates publication-title: Drug Discov Today doi: 10.1016/j.drudis.2022.103439 – volume: 47 start-page: 1739 year: 2004 ident: 2025033118431917300_ref42 article-title: Glide: a new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy publication-title: J Med Chem doi: 10.1021/jm0306430 – volume: 3 start-page: 1033 year: 2021 ident: 2025033118431917300_ref2 article-title: A geometric deep learning approach to predict binding conformations of bioactive molecules publication-title: Nat Mach Intell doi: 10.1038/s42256-021-00409-9 – volume: 15 year: 2024 ident: 2025033118431917300_ref28 article-title: 3D molecular generative framework for interaction-guided drug design publication-title: Nat Commun doi: 10.1038/s41467-024-47011-2 – volume: 2024 year: 2024 ident: 2025033118431917300_ref6 article-title: 3D molecular generation via virtual dynamics publication-title: Transact Mach Learn Res – volume: 15 start-page: 7926 year: 2024 ident: 2025033118431917300_ref38 article-title: DiffBindFR: an SE (3) equivariant network for flexible protein–ligand docking publication-title: Chem Sci doi: 10.1039/D3SC06803J – volume: 15 start-page: 2657 year: 2024 ident: 2025033118431917300_ref13 article-title: A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets publication-title: Nat Commun doi: 10.1038/s41467-024-46569-1 – volume-title: International Conference on Learning Representations year: 2023 ident: 2025033118431917300_ref12 article-title: 3D equivariant diffusion for target-aware molecule generation and affinity prediction – ident: 2025033118431917300_ref20 article-title: Learning deep generative models of graphs – volume: 14 start-page: 12166 year: 2023 ident: 2025033118431917300_ref5 article-title: A flexible data-free framework for structure-based de novo drug design with reinforcement learning publication-title: Chem Sci doi: 10.1039/D3SC04091G – volume: 13 start-page: 6891 year: 2022 ident: 2025033118431917300_ref65 article-title: Generative deep learning enables the discovery of a potent and selective RIPK1 inhibitor publication-title: Nat Commun doi: 10.1038/s41467-022-34692-w – ident: 2025033118431917300_ref8 article-title: Generating 3D molecular structures conditional on a receptor binding site with deep generative models – ident: 2025033118431917300_ref36 article-title: Do deep learning models really outperform traditional approaches in molecular docking? – volume-title: International Conference on Learning Representations year: 2023 ident: 2025033118431917300_ref44 article-title: DiffDock: diffusion steps, twists, and turns for molecular docking – volume: 6 start-page: 62 year: 2024 ident: 2025033118431917300_ref32 article-title: Generation of 3D molecules in pockets via a language model publication-title: Nat Mach Intell doi: 10.1038/s42256-023-00775-6 – ident: 2025033118431917300_ref57 article-title: Transformer for graphs: an overview from architecture perspective – volume: 60 start-page: 4200 year: 2020 ident: 2025033118431917300_ref59 article-title: Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design publication-title: J Chem Inf Model doi: 10.1021/acs.jcim.0c00411 – volume: 6 start-page: 417 year: 2024 ident: 2025033118431917300_ref15 article-title: Equivariant 3D-conditional diffusion model for molecular linker design publication-title: Nat Mach Intell doi: 10.1038/s42256-024-00815-9 – start-page: 41382 volume-title: International Conference on Machine Learning year: 2023 ident: 2025033118431917300_ref34 article-title: Learning subpocket prototypes for generalizable structure-based drug design – ident: 2025033118431917300_ref11 article-title: Structure-based drug design with equivariant diffusion models doi: 10.1038/s43588-024-00737-x – volume: 6 start-page: 326 year: 2024 ident: 2025033118431917300_ref29 article-title: Pocketflow is a data-and-knowledge-driven structure-based molecular generative model publication-title: Nat Mach Intell doi: 10.1038/s42256-024-00808-8 – volume: 1 start-page: 55 year: 1999 ident: 2025033118431917300_ref60 article-title: A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases publication-title: J Comb Chem doi: 10.1021/cc9800071 – volume-title: Elementary Mathematical Theory of Classification and Prediction year: 1958 ident: 2025033118431917300_ref64
SSID	ssj0020781
Score	2.42307
Snippet	Abstract Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary... Structure-based drug design aims to generate molecules that fill the cavity of the protein pocket with a high binding affinity. Many contemporary studies...
SourceID	pubmedcentral proquest pubmed crossref oup
SourceType	Open Access Repository Aggregation Database Index Database Publisher
SubjectTerms	Affinity Algorithms Binding Drug Design Drug development Graphs Lower bounds Molecular docking Molecular Docking Simulation Problem Solving Protocol Proteins - chemistry Proteins - metabolism Software Training
Title	MolEM: a unified generative framework for molecular graphs and sequential orders
URI	https://www.ncbi.nlm.nih.gov/pubmed/40163755 https://www.proquest.com/docview/3248850160 https://www.proquest.com/docview/3184575095 https://pubmed.ncbi.nlm.nih.gov/PMC11957264
Volume	26
WOSCitedRecordID	wos001482373500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1477-4054 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020781 issn: 1467-5463 databaseCode: DOA dateStart: 20240101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVASL databaseName: Oxford Journals Open Access Collection customDbUrl: eissn: 1477-4054 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0020781 issn: 1467-5463 databaseCode: TOX dateStart: 20000101 isFulltext: true titleUrlDefault: https://academic.oup.com/journals/ providerName: Oxford University Press
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB60KHjx_aiPGsHr0u5uYrLeRCpeWj0o9LZsHqMF3YrbCv57J7vbYouo58yyYSaTfEMm3wdwrqTtOI6cUjySAbdWBSqSIgiRG7wwUovElGITst9Xg0FyXzfIFj9c4SdxWw91W-sMqRChrTYUygsVPNwNZnWV56upHhHJwLO718_wFr6dO3jmHrN9w5SLrZHfzpqbjf_OchPWazTJrqrwb8GSy7dhtdKX_NyB-97opdu7ZBmb5EMksMmeSpZpv8UxnLZlMcKt7HUqk8tKCuuCZbllVZ817QEvrKToLHbh8ab7cH0b1BIKgaHCaRzELuHGaK545EKrwthJjaYjrY00KtsROpHWhJ6bKCFk6DIMMxFlGrMwMkjH2x408lHuDoDpWBuurFDGeMp21IgoUFKcQ0STRE04n_o3fauYMtLqhjtOyTlp7ZwmnJLvf7c4nsYlrROqSAn3KSU8HV4TzmbDlAr-fiPL3WhCNlStCo-ARBP2qzDO_kPeuIiloBE1F-CZgafZnh_Jh88l3bYnxZOEGw__nPkRrEVeHti3qPFjaIzfJ-4EVszHeFi8t2BZDlSrLPpb5QL-An8i7cI
linkProvider	Oxford University Press
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=MolEM%3A+a+unified+generative+framework+for+molecular+graphs+and+sequential+orders&rft.jtitle=Briefings+in+bioinformatics&rft.au=Zhang%2C+Hanwen&rft.au=Xiong%2C+Deng&rft.au=Liu%2C+Xianggen&rft.au=Lv%2C+Jiancheng&rft.date=2025-03-04&rft.issn=1467-5463&rft.eissn=1477-4054&rft.volume=26&rft.issue=2&rft_id=info:doi/10.1093%2Fbib%2Fbbaf094&rft.externalDBID=n%2Fa&rft.externalDocID=10_1093_bib_bbaf094
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1467-5463&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1467-5463&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1467-5463&client=summon