Fragment Linker Prediction Using the Deep Encoder-Decoder Network for PROTACs Drug Design

A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and has not been able to be resolved using computational methods. Deep learning has been utilized in various fields and achieved tremendous succ...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of chemical information and modeling Ročník 63; číslo 10; s. 2918
Hlavní autoři: Kao, Chien-Ting, Lin, Chieh-Te, Chou, Cheng-Li, Lin, Chu-Chung
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 22.05.2023
Témata:
ISSN:1549-960X, 1549-960X
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and has not been able to be resolved using computational methods. Deep learning has been utilized in various fields and achieved tremendous success in designing novel molecules in the pharmaceutical industry. Herein, we use state-of-the-art techniques to propose a deep neural network, AIMLinker, to rapidly design and generate meaningful drug-like proteolysis targeting chimeras (PROTACs) analogs. The model extracts the structural information from the input fragments and generates linkers to incorporate them. We integrate filters in the model to exclude nondruggable structures guided via protein-protein complexes while retaining molecules with potent chemical properties. The novel PROTACs subsequently pass through molecular docking, taking root-mean-square deviation (RMSD), relative Gibbs free energy ( ), molecular dynamics (MD) simulation, and free energy perturbation (FEP) calculations as the measurement criteria for testing the robustness and feasibility of the model. The generated novel PROTACs molecules possess similar structural information with superior binding affinity to the binding pockets compared to the existing CRBN-dBET6-BRD4 ternary complexes. We demonstrate the effectiveness of the methodology of leveraging AIMLinker to design novel compounds for PROTACs molecules exhibiting better chemical properties compared to the dBET6 crystal pose.
AbstractList A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and has not been able to be resolved using computational methods. Deep learning has been utilized in various fields and achieved tremendous success in designing novel molecules in the pharmaceutical industry. Herein, we use state-of-the-art techniques to propose a deep neural network, AIMLinker, to rapidly design and generate meaningful drug-like proteolysis targeting chimeras (PROTACs) analogs. The model extracts the structural information from the input fragments and generates linkers to incorporate them. We integrate filters in the model to exclude nondruggable structures guided via protein-protein complexes while retaining molecules with potent chemical properties. The novel PROTACs subsequently pass through molecular docking, taking root-mean-square deviation (RMSD), relative Gibbs free energy (ΔΔGbinding), molecular dynamics (MD) simulation, and free energy perturbation (FEP) calculations as the measurement criteria for testing the robustness and feasibility of the model. The generated novel PROTACs molecules possess similar structural information with superior binding affinity to the binding pockets compared to the existing CRBN-dBET6-BRD4 ternary complexes. We demonstrate the effectiveness of the methodology of leveraging AIMLinker to design novel compounds for PROTACs molecules exhibiting better chemical properties compared to the dBET6 crystal pose.A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and has not been able to be resolved using computational methods. Deep learning has been utilized in various fields and achieved tremendous success in designing novel molecules in the pharmaceutical industry. Herein, we use state-of-the-art techniques to propose a deep neural network, AIMLinker, to rapidly design and generate meaningful drug-like proteolysis targeting chimeras (PROTACs) analogs. The model extracts the structural information from the input fragments and generates linkers to incorporate them. We integrate filters in the model to exclude nondruggable structures guided via protein-protein complexes while retaining molecules with potent chemical properties. The novel PROTACs subsequently pass through molecular docking, taking root-mean-square deviation (RMSD), relative Gibbs free energy (ΔΔGbinding), molecular dynamics (MD) simulation, and free energy perturbation (FEP) calculations as the measurement criteria for testing the robustness and feasibility of the model. The generated novel PROTACs molecules possess similar structural information with superior binding affinity to the binding pockets compared to the existing CRBN-dBET6-BRD4 ternary complexes. We demonstrate the effectiveness of the methodology of leveraging AIMLinker to design novel compounds for PROTACs molecules exhibiting better chemical properties compared to the dBET6 crystal pose.
A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and has not been able to be resolved using computational methods. Deep learning has been utilized in various fields and achieved tremendous success in designing novel molecules in the pharmaceutical industry. Herein, we use state-of-the-art techniques to propose a deep neural network, AIMLinker, to rapidly design and generate meaningful drug-like proteolysis targeting chimeras (PROTACs) analogs. The model extracts the structural information from the input fragments and generates linkers to incorporate them. We integrate filters in the model to exclude nondruggable structures guided via protein-protein complexes while retaining molecules with potent chemical properties. The novel PROTACs subsequently pass through molecular docking, taking root-mean-square deviation (RMSD), relative Gibbs free energy ( ), molecular dynamics (MD) simulation, and free energy perturbation (FEP) calculations as the measurement criteria for testing the robustness and feasibility of the model. The generated novel PROTACs molecules possess similar structural information with superior binding affinity to the binding pockets compared to the existing CRBN-dBET6-BRD4 ternary complexes. We demonstrate the effectiveness of the methodology of leveraging AIMLinker to design novel compounds for PROTACs molecules exhibiting better chemical properties compared to the dBET6 crystal pose.
Author Lin, Chu-Chung
Lin, Chieh-Te
Kao, Chien-Ting
Chou, Cheng-Li
Author_xml – sequence: 1
  givenname: Chien-Ting
  surname: Kao
  fullname: Kao, Chien-Ting
  organization: AnHorn Medicines Co., Ltd., Taipei 115202, Taiwan
– sequence: 2
  givenname: Chieh-Te
  orcidid: 0000-0001-5262-1050
  surname: Lin
  fullname: Lin, Chieh-Te
  organization: Department of Biomedical Engineering, University of California Davis, Davis, California 95616, United States
– sequence: 3
  givenname: Cheng-Li
  surname: Chou
  fullname: Chou, Cheng-Li
  organization: AnHorn Medicines Co., Ltd., Taipei 115202, Taiwan
– sequence: 4
  givenname: Chu-Chung
  surname: Lin
  fullname: Lin, Chu-Chung
  organization: AnHorn Medicines Co., Ltd., Taipei 115202, Taiwan
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37150933$$D View this record in MEDLINE/PubMed
BookMark eNpNkDtPwzAYRS0Eog_YmZBHlhS_4jRj1QcgVRShIsEUOfbn4LZxip0I8e-poEhM5w7n3uEO0KlvPCB0RcmIEkZvlY6jjXb1iGlC2Tg7QX2aijzJJXk9_Zd7aBDjhhDOc8nOUY9nNCU55330tgiqqsG3eOn8FgJ-CmCcbl3j8Ut0vsLtO-AZwB7PvW4MhGQGP8SP0H42YYttc2g9r9aTacSz0FUHO7rKX6Azq3YRLo8covVivp7eJ8vV3cN0skyUkKxNjEgFJaUep5kRVuuylFaxUnNjcpDKCmIMt2bMMiOJBUolV0Rzm2lFU6nYEN38zu5D89FBbIvaRQ27nfLQdLFgY0oZFUzkB_X6qHZlDabYB1er8FX8vcG-AYPvZQY
CitedBy_id crossref_primary_10_1021_acs_chemrev_4c00969
crossref_primary_10_1002_mco2_70258
crossref_primary_10_1016_j_apsb_2024_04_007
crossref_primary_10_3390_pharmaceutics17091160
crossref_primary_10_1016_j_tips_2024_10_006
crossref_primary_10_3390_ph16121649
crossref_primary_10_1002_wcms_70013
crossref_primary_10_1016_j_cmpb_2025_108687
crossref_primary_10_1016_j_ijbiomac_2024_134293
crossref_primary_10_1016_j_ejmech_2025_117432
crossref_primary_10_1016_j_sbi_2025_102995
crossref_primary_10_1016_j_ejmech_2023_115793
crossref_primary_10_1016_j_bioorg_2025_108985
crossref_primary_10_1016_j_eswa_2023_123127
crossref_primary_10_1093_bioinformatics_btaf191
crossref_primary_10_2174_0113852728361926250123092017
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1021/acs.jcim.2c01287
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
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 1549-960X
ExternalDocumentID 37150933
Genre Journal Article
GroupedDBID ---
-~X
4.4
55A
5GY
5VS
7~N
AABXI
ABBLG
ABJNI
ABLBI
ABMVS
ABQRX
ABUCX
ACGFS
ACIWK
ACNCT
ACS
ADHLV
AEESW
AENEX
AFEFF
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
AQSVZ
CGR
CUPRZ
CUY
CVF
D0L
DU5
EBS
ECM
ED~
EIF
F5P
GGK
GNL
IH9
JG~
NPM
P2P
PQQKQ
RNS
ROL
UI2
VF5
VG9
W1F
7X8
ID FETCH-LOGICAL-a462t-d45410bc857d4fccbb6fa2bc3dd9e6af40dd3fd827d60fe1163a0c3f7ca156a2
IEDL.DBID 7X8
ISICitedReferencesCount 23
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000986540300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1549-960X
IngestDate Tue Dec 16 12:36:35 EST 2025
Sat Aug 02 01:41:17 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 10
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a462t-d45410bc857d4fccbb6fa2bc3dd9e6af40dd3fd827d60fe1163a0c3f7ca156a2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-5262-1050
OpenAccessLink https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.2c01287
PMID 37150933
PQID 2811214249
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2811214249
pubmed_primary_37150933
PublicationCentury 2000
PublicationDate 2023-05-22
PublicationDateYYYYMMDD 2023-05-22
PublicationDate_xml – month: 05
  year: 2023
  text: 2023-05-22
  day: 22
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of chemical information and modeling
PublicationTitleAlternate J Chem Inf Model
PublicationYear 2023
SSID ssj0033962
Score 2.532517
Snippet A drug discovery and development pipeline is a prolonged and complex process that remains challenging for both computational methods and medicinal chemists and...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 2918
SubjectTerms Drug Design
Molecular Docking Simulation
Molecular Dynamics Simulation
Proteolysis
Title Fragment Linker Prediction Using the Deep Encoder-Decoder Network for PROTACs Drug Design
URI https://www.ncbi.nlm.nih.gov/pubmed/37150933
https://www.proquest.com/docview/2811214249
Volume 63
WOSCitedRecordID wos000986540300001&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/eLvHCXMwpV3JTsMwELXYJLiwL2WTkbi6TTxJnJwQakEcoFSoh3KqvFZFIi1Jy_czTlM4ISFxSS6xlIydmed543mEXGuhIUkNMIgEsIi7kGVGZkwJFVsRh8qYaqYfRbebDgZZr064lXVZ5dInVo7aTLTPkbd4isjAH8vKbqYfzKtGeXa1ltBYJesQQuJ754vBN4sAkFWCor4LGUOkPqhpSgxrLanL5psevze59i5a_A4wq0Bzv_PfV9wl2zXEpLeLNbFHVmy-TzbbS2W3A_KKaHXks4LU70RtQXuFp2v8FNGqhIAiKqQda6f0Lvdn3gvWsdWddhdV4xShLu29PPdv2yXtFPMRPu0rQQ5J__6u335gtcQCk1HCZ8xEcRQGSqexMJHTWqnESa40GJPZRLooMAacSbkwSeBsiOhNBhqc0BI3fpIfkbV8ktsTQkP0quB4bBECRg63ZTJIlQFQMjYYh22DXC2NNsTP9bSEzO1kXg5_zNYgxwvLD6eLVhtDEAhYM4DTP4w-I1teC95T-5yfk3WH_6-9IBv6czYui8tqaeC123v6AvcExKs
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=Fragment+Linker+Prediction+Using+the+Deep+Encoder-Decoder+Network+for+PROTACs+Drug+Design&rft.jtitle=Journal+of+chemical+information+and+modeling&rft.au=Kao%2C+Chien-Ting&rft.au=Lin%2C+Chieh-Te&rft.au=Chou%2C+Cheng-Li&rft.au=Lin%2C+Chu-Chung&rft.date=2023-05-22&rft.eissn=1549-960X&rft.volume=63&rft.issue=10&rft.spage=2918&rft_id=info:doi/10.1021%2Facs.jcim.2c01287&rft_id=info%3Apmid%2F37150933&rft_id=info%3Apmid%2F37150933&rft.externalDocID=37150933
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1549-960X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1549-960X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1549-960X&client=summon