MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction

Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of chemical information and modeling Ročník 64; číslo 13; s. 4980
Hlavní autoři: Ranjan, Amit, Bess, Adam, Alvin, Chris, Mukhopadhyay, Supratik
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 08.07.2024
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 Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.
AbstractList Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.
Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.
Author Ranjan, Amit
Alvin, Chris
Mukhopadhyay, Supratik
Bess, Adam
Author_xml – sequence: 1
  givenname: Amit
  orcidid: 0000-0002-7940-5865
  surname: Ranjan
  fullname: Ranjan, Amit
  organization: Department of Environmental Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States
– sequence: 2
  givenname: Adam
  surname: Bess
  fullname: Bess, Adam
  organization: Department of Environmental Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States
– sequence: 3
  givenname: Chris
  surname: Alvin
  fullname: Alvin, Chris
  organization: Department of Computer Science, Furman University, Greenville, South Carolina 29613, United States
– sequence: 4
  givenname: Supratik
  surname: Mukhopadhyay
  fullname: Mukhopadhyay, Supratik
  organization: Department of Environmental Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38888163$$D View this record in MEDLINE/PubMed
BookMark eNpNkD1PwzAQhi1URD9gZ0IeWVLs2HFrttC0gNQKhiJ1ixznXFwlTrGTof-eIIrELfcMz3s6vWM0cI0DhG4pmVIS0welw_SgbT3lmhBGyQUa0YTLSAqyG_zjIRqHcOgVJkV8hYZs3g8VbIR2m2wVZdv0Ead401WtjTJbgwu2carCq-4HcHo8-kbpT2wajzPf7aOt8nto8ZN1pXV7nBpjnW1P-N1DaXXbh67RpVFVgJvznqCP1XK7eInWb8-vi3QdKS7iNoqFYAUXoLWUuhSaJywBIRLOCcgEDFEFSGM4ByZjSQsoWSnnilMDBS2JiCfo_vdu_-JXB6HNaxs0VJVy0HQhZ2RGZjLhgvXq3VntihrK_Ohtrfwp_2sj_gaH8mP7
CitedBy_id crossref_primary_10_1016_j_ejmech_2025_118153
crossref_primary_10_1109_ACCESS_2025_3583338
crossref_primary_10_1016_j_compbiomed_2025_110438
crossref_primary_10_3390_cancers17183023
crossref_primary_10_1007_s12539_025_00712_8
crossref_primary_10_3390_biom15020221
crossref_primary_10_1007_s10822_025_00605_4
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1021/acs.jcim.4c00310
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 38888163
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-2663b46ecc99cd6c4535e665440e95ef0abe9ff44e39291bed3d98a41feb1d062
IEDL.DBID 7X8
ISICitedReferencesCount 11
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001250641100001&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 Wed Oct 01 14:57:29 EDT 2025
Mon Jul 21 06:02:30 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 13
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a462t-2663b46ecc99cd6c4535e665440e95ef0abe9ff44e39291bed3d98a41feb1d062
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-7940-5865
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC11234358
PMID 38888163
PQID 3070795463
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3070795463
pubmed_primary_38888163
PublicationCentury 2000
PublicationDate 2024-07-08
PublicationDateYYYYMMDD 2024-07-08
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-08
  day: 08
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of chemical information and modeling
PublicationTitleAlternate J Chem Inf Model
PublicationYear 2024
SSID ssj0033962
Score 2.5112147
Snippet Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming,...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 4980
SubjectTerms Deep Learning
Drug Discovery - methods
Machine Learning
Pharmaceutical Preparations - chemistry
Pharmaceutical Preparations - metabolism
Protein Binding
Proteins - chemistry
Proteins - metabolism
Title MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction
URI https://www.ncbi.nlm.nih.gov/pubmed/38888163
https://www.proquest.com/docview/3070795463
Volume 64
WOSCitedRecordID wos001250641100001&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/eLvHCXMwpV1bS8MwFA7qBH3xfpk3IviauTXZ2vgidbP4srGHCX0rTXIiFezmLoL_3pOs0ydBEErpS6E9Sc75Ts7J9xFyk0OkA-PS1BDTVQFGoB-0moEOQ2VbSkvQXmwiHAyiNJXDasNtVrVVrnyid9RmrN0e-S33XG6OvP1-8s6capSrrlYSGuukxhHKuJauMP2uInAuvaCoYyFjiNTTqkyJYe0217PGqy7eGkJ7dszfAaYPNMnufz9xj-xUEJPGyzmxT9agPCBb3ZWy2yFJ-72E9UbxHY2pP4DLeo7jf8nPQZOFe6BxRTZOEdXS3nTxwka-aZw-FP4gDI2tLdAffNLh1BV73AAfkefkcdR9YpXCAstFJ5gzjM5ciQ4Oo5TadLRo8zY4PWLRBNkG28wVSGuFAAejWgoMNzLKRcuiizfNTnBMNspxCaeEQmRybXMlwQZCCSvxsqKpcL1HioOpk-uV0TL8XVeWyEsYL2bZj9nq5GRp-WyypNrIOCboEULGsz-8fU62A0Qcvpc2uiA1i-sXLsmm_pgXs-mVnxp4Hwz7XwqrxUg
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=MDF-DTA%3A+A+Multi-Dimensional+Fusion+Approach+for+Drug-Target+Binding+Affinity+Prediction&rft.jtitle=Journal+of+chemical+information+and+modeling&rft.au=Ranjan%2C+Amit&rft.au=Bess%2C+Adam&rft.au=Alvin%2C+Chris&rft.au=Mukhopadhyay%2C+Supratik&rft.date=2024-07-08&rft.issn=1549-960X&rft.eissn=1549-960X&rft.volume=64&rft.issue=13&rft.spage=4980&rft_id=info:doi/10.1021%2Facs.jcim.4c00310&rft.externalDBID=NO_FULL_TEXT
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