FusionCLM: enhanced molecular property prediction via knowledge fusion of chemical language models

Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide uni...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of cheminformatics Ročník 17; číslo 1; s. 133 - 12
Hlavní autoři: Lu, Yutong, Li, Yan Yi, Sun, Yan, Hu, Pingzhao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 29.08.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Témata:
ISSN:1758-2946, 1758-2946
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM’s potential in advancing molecular property prediction. Scientific Contribution FusionCLM uses the stacking-ensemble learning method that integrates unique representation learning from multiple CLMs, allowing a more comprehensive learning of molecular SMILES data. This results in providing more accurate molecular property prediction, which can help in facilitating early discovery and development of promising drug candidates. By evaluating and comparing its performance against individual CLMs and existing multimodal deep learning frameworks, FusionCLM demonstrates improvements in prediction accuracy, distinguishing itself from prior models in this domain.
AbstractList Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM’s potential in advancing molecular property prediction. FusionCLM uses the stacking-ensemble learning method that integrates unique representation learning from multiple CLMs, allowing a more comprehensive learning of molecular SMILES data. This results in providing more accurate molecular property prediction, which can help in facilitating early discovery and development of promising drug candidates. By evaluating and comparing its performance against individual CLMs and existing multimodal deep learning frameworks, FusionCLM demonstrates improvements in prediction accuracy, distinguishing itself from prior models in this domain.
Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM’s potential in advancing molecular property prediction. Scientific Contribution FusionCLM uses the stacking-ensemble learning method that integrates unique representation learning from multiple CLMs, allowing a more comprehensive learning of molecular SMILES data. This results in providing more accurate molecular property prediction, which can help in facilitating early discovery and development of promising drug candidates. By evaluating and comparing its performance against individual CLMs and existing multimodal deep learning frameworks, FusionCLM demonstrates improvements in prediction accuracy, distinguishing itself from prior models in this domain.
Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM's potential in advancing molecular property prediction. Keywords: Large language Models, Knowledge fusion, Ensemble learning, Molecular property prediction, Drug discovery
Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM's potential in advancing molecular property prediction.Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM's potential in advancing molecular property prediction.
Abstract Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM’s potential in advancing molecular property prediction.
Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM's potential in advancing molecular property prediction.
Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line Entry System (SMILES), a notation used to represent molecular structures. Different CLMs, developed from various architectures, can provide unique insights into molecular properties. To harness the uniqueness of different CLMs, we propose FusionCLM, a novel stacking-ensemble learning algorithm that integrate the outputs of multiple CLMs into a unified framework. FusionCLM first generates SMILES embeddings, predictions, and losses from each CLM. Auxiliary models are trained on these first-level predictions and embeddings to estimate test losses during inference. The losses and predictions are then concatenated to create an integrated feature matrix, which trains second-level meta-models for final predictions. Empirical testing on five datasets demonstrates that FusionCLM have better performance than individual CLM at the first level and three advanced multimodal deep learning frameworks, showcasing FusionCLM’s potential in advancing molecular property prediction.Scientific ContributionFusionCLM uses the stacking-ensemble learning method that integrates unique representation learning from multiple CLMs, allowing a more comprehensive learning of molecular SMILES data. This results in providing more accurate molecular property prediction, which can help in facilitating early discovery and development of promising drug candidates. By evaluating and comparing its performance against individual CLMs and existing multimodal deep learning frameworks, FusionCLM demonstrates improvements in prediction accuracy, distinguishing itself from prior models in this domain.
ArticleNumber 133
Audience Academic
Author Hu, Pingzhao
Lu, Yutong
Li, Yan Yi
Sun, Yan
Author_xml – sequence: 1
  givenname: Yutong
  surname: Lu
  fullname: Lu, Yutong
  organization: Biostatistics Division, Dalla Lana School of Public Health, University of Toronto
– sequence: 2
  givenname: Yan Yi
  surname: Li
  fullname: Li, Yan Yi
  organization: Biostatistics Division, Dalla Lana School of Public Health, University of Toronto
– sequence: 3
  givenname: Yan
  surname: Sun
  fullname: Sun, Yan
  organization: Department of Biochemistry, Western University, Department of Computer Science, Western University
– sequence: 4
  givenname: Pingzhao
  surname: Hu
  fullname: Hu, Pingzhao
  email: phu49@uwo.ca
  organization: Biostatistics Division, Dalla Lana School of Public Health, University of Toronto, Department of Biochemistry, Western University, Department of Computer Science, Western University, Department of Oncology, Western University, Department of Epidemiology and Biostatistics, Western University, The Children’s Health Research Institute, Lawson Health Research Institute
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40883821$$D View this record in MEDLINE/PubMed
BookMark eNp9kktv1DAUhSNURB_wB1igSGxgkeJH7NhsUDWiMNIgJB5r68a5yWTI2FM7KfTf45kpbQch5IUt-zvH8vE5zY6cd5hlzyk5p1TJN5FyzmhBmCgIJRUv5KPshFZCFUyX8ujB-jg7jXFFiBQVqZ5kxyVRiitGT7L6coq9d7PFp7c5uiU4i02-9gPaaYCQb4LfYBhv0gKb3o4Jza97yH84_3PApsO83elz3-Z2ievewpAP4LoJ0tnaNzjEp9njFoaIz27ns-z75ftvs4_F4vOH-exiUVihxVjI2rYMlGUtTbPWHIQA4LaWNUpFW6opgJKogZWMQFOhtpwSYVXLqKgsP8vme9_Gw8psQr-GcGM89Ga34UNnIIy9HdCUmkustCUg67KRRNdKEE050FY2FWmS17u912aq19hYdGOA4cD08MT1S9P5a0MZ16KiMjm8unUI_mrCOJp1Hy0OKRz0UzSclZILrRVJ6Mu_0JWfgktZbalSSyVYeU91kF7Qu9ani-3W1FwowRXXSrJEnf-DSqPZfk7qT9un_QPB6wNBYkb8NXYwxWjmX78csi8epnIXx586JYDtARt8jAHbO4QSs-2s2XfWpM6aXWfNNim-F8UEuw7D_fP_o_oNS-Xsqg
Cites_doi 10.1016/B978-0-12-373593-5.00069-0
10.1023/A:1010933404324
10.6019/CHEMBL3301361
10.1186/s13321-02000441-8
10.1039/C7SC02664A
10.1093/bib/bbac408
10.1093/nar/gky1033
10.1023/B:MACH.0000015881.36452.6e
10.1021/ci049714+
10.1037/h0078850
10.1021/ci00057a005
10.21203/rs.3.rs-1570270/v1
10.1101/095653
10.1016/j.chembiol.2016.07.023
10.3389/fphar.2022.1046524
10.1021/ci034243x
10.1016/j.ddtec.2020.05.001
10.1021/ci300124c
10.1021/acs.jmedchem.1c00927
10.1093/nar/gkw1074
10.1038/s42256-022-00557-6
10.1145/3307339.3342186
10.48550/arXiv.1310.5103
10.48550/arXiv.2306.02561
10.1109/UIC-ATC.2017.8397411
10.1021/acs.jcim.8b00839
10.48550/arXiv.2209.01712
10.1038/nature14539
10.1021/acs.jcim.6b00290
10.1038/s42256-02300626-4
10.1186/s12859020-3406-0
10.1016/j.dche.2022.100034
10.48550/arXiv.2208.13994
10.2307/3001968
10.48550/arXiv.2011.13230
10.1016/S0893-6080(05)80023-1
10.1109/CVPR52729.2023.02271
10.1186/s12859-0193135-4
10.1093/bib/bbad306
ContentType Journal Article
Copyright The Author(s) 2025
2025. The Author(s).
COPYRIGHT 2025 BioMed Central Ltd.
The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
The Author(s) 2025 2025
Copyright_xml – notice: The Author(s) 2025
– notice: 2025. The Author(s).
– notice: COPYRIGHT 2025 BioMed Central Ltd.
– notice: The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: The Author(s) 2025 2025
DBID C6C
AAYXX
CITATION
NPM
ISR
3V.
7QO
7X7
7XB
8AO
8FD
8FE
8FG
8FH
8FI
8FJ
8FK
ABJCF
ABUWG
AEUYN
AFKRA
ARAPS
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
CCPQU
D1I
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
HCIFZ
K9.
KB.
LK8
M0S
M7P
P5Z
P62
P64
PDBOC
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
7X8
5PM
DOA
DOI 10.1186/s13321-025-01073-6
DatabaseName Springer Nature OA Free Journals
CrossRef
PubMed
Gale In Context: Science
ProQuest Central (Corporate)
Biotechnology Research Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
ProQuest Pharma Collection
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Natural Science Collection
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest One Sustainability
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials - QC
Biological Science Collection
ProQuest Central
ProQuest Technology Collection
Natural Science Collection
ProQuest One
ProQuest Materials Science Collection
ProQuest Central Korea
Engineering Research Database
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
Materials Science Database
ProQuest Biological Science Collection
ProQuest Health & Medical Collection
Biological Science Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Biotechnology and BioEngineering Abstracts
Materials Science Collection
Proquest Central Premium
ProQuest One Academic (New)
ProQuest Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
Publicly Available Content Database
ProQuest Central Student
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
Materials Science Collection
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Pharma Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest One Sustainability
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Biotechnology Research Abstracts
Health and Medicine Complete (Alumni Edition)
Natural Science Collection
ProQuest Central Korea
Biological Science Collection
Materials Science Database
ProQuest Central (New)
ProQuest Materials Science Collection
Advanced Technologies & Aerospace Collection
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
Advanced Technologies & Aerospace Database
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList


MEDLINE - Academic



Publicly Available Content Database
PubMed
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Chemistry
EISSN 1758-2946
EndPage 12
ExternalDocumentID oai_doaj_org_article_4936e79c0a6b4d609b850913a1f6d70d
PMC12395716
A853839862
40883821
10_1186_s13321_025_01073_6
Genre Journal Article
GrantInformation_xml – fundername: Canadian Institutes of Health Research
  grantid: PLL 185683, PJT 190272
– fundername: Natural Sciences and Engineering Research Council of Canada
  grantid: RGPIN-2021-04072
– fundername: Canada Foundation for Innovation (CFI) John R. Evans Leaders Fund (JELF) program
  grantid: #43481
– fundername: Canada Research Chairs Tier II Program
  grantid: CRC-2021-00482
– fundername: CIHR
  grantid: PLL 185683, PJT 190272
GroupedDBID 0R~
29K
2WC
4.4
40G
53G
5VS
7X7
8AO
8FE
8FG
8FH
8FI
8FJ
AAFWJ
AAJSJ
AAKKN
AAKPC
AASML
ABDBF
ABEEZ
ABJCF
ABUWG
ACACY
ACGFS
ACIHN
ACIWK
ACPRK
ACUHS
ACULB
ADBBV
ADRAZ
ADUKV
AEAQA
AENEX
AEUYN
AFGXO
AFKRA
AFPKN
AFRAH
AHBYD
AHMBA
AHYZX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIJS
ARAPS
BAPOH
BAWUL
BBNVY
BCNDV
BENPR
BFQNJ
BGLVJ
BHPHI
BMC
BPHCQ
BVXVI
C24
C6C
CCPQU
D-I
D1I
DIK
E3Z
EBLON
EBS
ESX
F5P
FYUFA
GROUPED_DOAJ
GX1
HCIFZ
HH5
HMCUK
HYE
IAO
IGS
IHR
ISR
ITC
KB.
KQ8
LK8
M7P
MK0
M~E
O5R
O5S
OK1
P62
PDBOC
PGMZT
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
PUEGO
RBZ
RNS
RPM
RVI
SOJ
SPH
TR2
TUS
U2A
UKHRP
AAYXX
AFFHD
CITATION
NPM
3V.
7QO
7XB
8FD
8FK
AZQEC
DWQXO
FR3
GNUQQ
K9.
P64
PJZUB
PKEHL
PPXIY
PQEST
PQUKI
PRINS
7X8
5PM
ID FETCH-LOGICAL-c595t-6bcf2a8c2f1f2a993a55aa3cb6be681f191aa86e9a2420ad7e9c3105c8f2157c3
IEDL.DBID C24
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001560396600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1758-2946
IngestDate Fri Oct 03 12:35:13 EDT 2025
Tue Nov 04 02:05:20 EST 2025
Thu Sep 04 12:32:53 EDT 2025
Sat Oct 18 23:46:55 EDT 2025
Tue Nov 11 10:47:26 EST 2025
Tue Nov 04 18:12:04 EST 2025
Thu Nov 13 15:55:57 EST 2025
Tue Sep 16 01:43:43 EDT 2025
Sat Nov 29 07:30:16 EST 2025
Sat Aug 30 01:21:07 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Knowledge fusion
Large language Models
Molecular property prediction
Drug discovery
Ensemble learning
Language English
License 2025. The Author(s).
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c595t-6bcf2a8c2f1f2a993a55aa3cb6be681f191aa86e9a2420ad7e9c3105c8f2157c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
OpenAccessLink https://link.springer.com/10.1186/s13321-025-01073-6
PMID 40883821
PQID 3244968524
PQPubID 54992
PageCount 12
ParticipantIDs doaj_primary_oai_doaj_org_article_4936e79c0a6b4d609b850913a1f6d70d
pubmedcentral_primary_oai_pubmedcentral_nih_gov_12395716
proquest_miscellaneous_3246359980
proquest_journals_3244968524
gale_infotracmisc_A853839862
gale_infotracacademiconefile_A853839862
gale_incontextgauss_ISR_A853839862
pubmed_primary_40883821
crossref_primary_10_1186_s13321_025_01073_6
springer_journals_10_1186_s13321_025_01073_6
PublicationCentury 2000
PublicationDate 2025-08-29
PublicationDateYYYYMMDD 2025-08-29
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-08-29
  day: 29
PublicationDecade 2020
PublicationPlace Cham
PublicationPlace_xml – name: Cham
– name: England
– name: London
PublicationTitle Journal of cheminformatics
PublicationTitleAbbrev J Cheminform
PublicationTitleAlternate J Cheminform
PublicationYear 2025
Publisher Springer International Publishing
BioMed Central Ltd
Springer Nature B.V
BMC
Publisher_xml – name: Springer International Publishing
– name: BioMed Central Ltd
– name: Springer Nature B.V
– name: BMC
References D Weininger (1073_CR7) 1988; 28
X Tong (1073_CR38) 2021; 64
N Ding (1073_CR6) 2023; 5
Y LeCun (1073_CR4) 2015; 521
F Wilcoxon (1073_CR34) 1945; 1
G Shafer (1073_CR41) 2007; 9
1073_CR1
S Kim (1073_CR22) 2019; 47
M Barton (1073_CR16) 2022; 3
1073_CR40
AV Artemov (1073_CR31) 2016
L Breiman (1073_CR25) 2001; 45
A Gaulton (1073_CR24) 2017; 45
W Kong (1073_CR37) 2022; 13
X Zeng (1073_CR3) 2022; 4
J Gao (1073_CR20) 2023
JS Delaney (1073_CR28) 2004; 44
S Kwon (1073_CR2) 2019; 20
1073_CR26
H Cai (1073_CR18) 2022
S Džeroski (1073_CR14) 2004; 54
DH Wolpert (1073_CR13) 1992; 5
J Shen (1073_CR5) 2019; 32–33
M Wenlock (1073_CR27) 2015
W Zhu (1073_CR19) 2022; 63
1073_CR39
N Brown (1073_CR23) 2019; 59
JJ Irwin (1073_CR21) 2005; 45
KM Gayvert (1073_CR30) 2016; 23
DW Zimmerman (1073_CR35) 1993; 47
Z Wu (1073_CR17) 2018; 9
G Subramanian (1073_CR29) 2016; 56
1073_CR11
H-C Yi (1073_CR15) 2020; 21
IF Martins (1073_CR32) 2012; 52
1073_CR33
1073_CR10
J Ross (1073_CR9) 2022; 4
J Arús-Pous (1073_CR36) 2020; 12
1073_CR12
1073_CR8
References_xml – ident: 1073_CR1
  doi: 10.1016/B978-0-12-373593-5.00069-0
– volume: 45
  start-page: 5
  issue: 1
  year: 2001
  ident: 1073_CR25
  publication-title: Mach Learn
  doi: 10.1023/A:1010933404324
– year: 2015
  ident: 1073_CR27
  doi: 10.6019/CHEMBL3301361
– volume: 12
  start-page: 38
  issue: 1
  year: 2020
  ident: 1073_CR36
  publication-title: J Cheminform
  doi: 10.1186/s13321-02000441-8
– volume: 9
  start-page: 513
  issue: 2
  year: 2018
  ident: 1073_CR17
  publication-title: Chem Sci
  doi: 10.1039/C7SC02664A
– year: 2022
  ident: 1073_CR18
  publication-title: Brief Bioinform
  doi: 10.1093/bib/bbac408
– volume: 47
  start-page: D1102
  issue: D1
  year: 2019
  ident: 1073_CR22
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gky1033
– volume: 54
  start-page: 255
  issue: 3
  year: 2004
  ident: 1073_CR14
  publication-title: Mach Learn
  doi: 10.1023/B:MACH.0000015881.36452.6e
– volume: 45
  start-page: 177
  issue: 1
  year: 2005
  ident: 1073_CR21
  publication-title: J Chem Inf Model
  doi: 10.1021/ci049714+
– volume: 47
  start-page: 523
  issue: 3
  year: 1993
  ident: 1073_CR35
  publication-title: Can J Exp Psychol
  doi: 10.1037/h0078850
– volume: 28
  start-page: 31
  issue: 1
  year: 1988
  ident: 1073_CR7
  publication-title: J Chem Inf Comput Sci
  doi: 10.1021/ci00057a005
– volume: 4
  start-page: 1256
  issue: 12
  year: 2022
  ident: 1073_CR9
  publication-title: Nat Mach Intell
  doi: 10.21203/rs.3.rs-1570270/v1
– year: 2016
  ident: 1073_CR31
  publication-title: BioRxiv
  doi: 10.1101/095653
– volume: 23
  start-page: 1294
  issue: 10
  year: 2016
  ident: 1073_CR30
  publication-title: Cell Chem Biol
  doi: 10.1016/j.chembiol.2016.07.023
– volume: 13
  start-page: 1046524
  year: 2022
  ident: 1073_CR37
  publication-title: Front Pharmacol
  doi: 10.3389/fphar.2022.1046524
– volume: 44
  start-page: 1000
  issue: 3
  year: 2004
  ident: 1073_CR28
  publication-title: J Chem Inf Comput Sci
  doi: 10.1021/ci034243x
– volume: 32–33
  start-page: 29
  year: 2019
  ident: 1073_CR5
  publication-title: Drug Discov Today Technol
  doi: 10.1016/j.ddtec.2020.05.001
– volume: 52
  start-page: 1686
  issue: 6
  year: 2012
  ident: 1073_CR32
  publication-title: J Chem Inf Model
  doi: 10.1021/ci300124c
– volume: 64
  start-page: 14011
  issue: 19
  year: 2021
  ident: 1073_CR38
  publication-title: J Med Chem
  doi: 10.1021/acs.jmedchem.1c00927
– volume: 45
  start-page: D945
  issue: D1
  year: 2017
  ident: 1073_CR24
  publication-title: Nucleic Acids Res
  doi: 10.1093/nar/gkw1074
– volume: 4
  start-page: 1004
  issue: 11
  year: 2022
  ident: 1073_CR3
  publication-title: Nat Mach Intell
  doi: 10.1038/s42256-022-00557-6
– ident: 1073_CR11
  doi: 10.1145/3307339.3342186
– ident: 1073_CR33
  doi: 10.48550/arXiv.1310.5103
– ident: 1073_CR26
  doi: 10.48550/arXiv.2306.02561
– ident: 1073_CR39
  doi: 10.1109/UIC-ATC.2017.8397411
– volume: 59
  start-page: 1096
  issue: 3
  year: 2019
  ident: 1073_CR23
  publication-title: J Chem Inf Model
  doi: 10.1021/acs.jcim.8b00839
– ident: 1073_CR8
  doi: 10.48550/arXiv.2209.01712
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 1073_CR4
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: 1073_CR40
– volume: 56
  start-page: 1936
  issue: 10
  year: 2016
  ident: 1073_CR29
  publication-title: J Chem Inf Model
  doi: 10.1021/acs.jcim.6b00290
– volume: 5
  start-page: 220
  issue: 3
  year: 2023
  ident: 1073_CR6
  publication-title: Nat Mach Intell
  doi: 10.1038/s42256-02300626-4
– volume: 21
  start-page: 60
  issue: 1
  year: 2020
  ident: 1073_CR15
  publication-title: BMC Bioinform
  doi: 10.1186/s12859020-3406-0
– volume: 3
  year: 2022
  ident: 1073_CR16
  publication-title: Digit Chem Eng
  doi: 10.1016/j.dche.2022.100034
– volume: 63
  start-page: 43
  issue: 1
  year: 2022
  ident: 1073_CR19
  publication-title: J Chem Inf Model
  doi: 10.48550/arXiv.2208.13994
– volume: 1
  start-page: 80
  year: 1945
  ident: 1073_CR34
  publication-title: Biometrics Bulletin
  doi: 10.2307/3001968
– volume: 9
  start-page: 371
  issue: 2
  year: 2007
  ident: 1073_CR41
  publication-title: J Mach Learn Res
– ident: 1073_CR10
  doi: 10.48550/arXiv.2011.13230
– volume: 5
  start-page: 241
  issue: 2
  year: 1992
  ident: 1073_CR13
  publication-title: Neural Netw
  doi: 10.1016/S0893-6080(05)80023-1
– ident: 1073_CR12
  doi: 10.1109/CVPR52729.2023.02271
– volume: 20
  start-page: 521
  issue: 1
  year: 2019
  ident: 1073_CR2
  publication-title: BMC Bioinform
  doi: 10.1186/s12859-0193135-4
– year: 2023
  ident: 1073_CR20
  publication-title: Brief Bioinform
  doi: 10.1093/bib/bbad306
SSID ssj0065707
Score 2.36657
Snippet Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular Input Line...
Abstract Chemical Language Models (CLMs) have demonstrated capabilities in extracting patterns and predicting from vast volume of the Simplified Molecular...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
springer
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 133
SubjectTerms Chemistry
Chemistry and Materials Science
Computational Biology/Bioinformatics
Computer Applications in Chemistry
Data mining
Datasets
Deep learning
Documentation and Information in Chemistry
Drug development
Drug discovery
Ensemble learning
Knowledge fusion
Language
Large language Models
Machine learning
Molecular properties
Molecular property prediction
Molecular structure
Predictions
Theoretical and Computational Chemistry
Uniqueness
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3di9QwEB_kEPRF_LZ6ShTBBy3XTZs08e1cXBTOQ_zi3kKSJt4-2D22uwf-986k7Xo9EV982mUzXZr5TZKZZPIbgOeiio1zSuShcVVe8ahz3UQ65G3qwLnTMvFsfzuqj4_VyYn-eKHUF-WE9fTAveIOKl3KUGtfWOmqRhYa_5i4LO0syqYuGpp9i1qPwVQ_B1M-Rz1ekVHyoMNIjGPYzClRDY06l5NlKLH1_zknX1iULidMXjo1TYvR4ibcGLxIdti__S24EtrbcG0-Fm-7A26xpW2w-dGH1yy0p-mYn_0YS-GyM9qCX29-4hc6qCFw2PnSst0OG4vpebaKzA-UAmzc2mSpek53F74u3n6Zv8uHcgq5F1pscul85FZ5Hmf4iX6JFcLa0jvpglSziJGbtUoGbXHZLixipT06f8KriH5B7ct7sNeu2vAAmJd0AxtbvAiVjF5hmBgjF1bVJeGUwctRu-asZ80wKdpQ0vRYGMTCJCyMzOANAbCTJMbr9APagRnswPzLDjJ4RvAZ4rRoKWnmu912nXn_-ZM5RJcE_UCM3TJ4MQjFFQLp7XAHAXtFNFgTyf2JJMLnp82jlZhh0HcGfdNKSyU49v_prpmepES2Nqy2SQZdPIxxiwzu90a163eFM36p-CwDNTG3iWKmLe3yNFGCo_-hBYa-GbwaLfP3e_1d8w__h-YfwXWeRhZd59mHvc16Gx7DVX--WXbrJ2lc_gLBCDpW
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: Biological Science Database
  dbid: M7P
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED_BQIKX8TkIDGQQEg8QLXVjx-YFjYoKpDFNfGlvluPYWx9IuqadxH_PnZt0ZAheeGpUX6I4v_N9-XwH8ELkoSpLJVJflXma86BTXQXa5K0Kz3mpZayz_f2gODxUx8f6qAu4tV1aZS8To6CuGkcx8j1U_LmWSvD87fwspa5RtLvatdC4CteoSgKPqXtHvSSmrI6iPyij5F6L_hhH55lTuhqydioHyijW7P9TMv-mmi6nTV7aO40qaXrrfydzG7Y7Y5Ttr7nnDlzx9V24Mel7wN2DcrqiaNrk4NMb5uvTmC3AfvQdddmcIvmL5U-8oP0ewpidzyzbBOpYiPezJjDXVSZgfYSUxSY87X34Nn3_dfIh7boypE5osUxl6QK3yvEwwl80b6wQ1o5dKUsv1SigA2itkl5b1P6ZRci1QxtSOBUQosKNd2Crbmr_EJiTdJAbR5zwuQxOobcZAhdWFWMryzyBVz08Zr4uvmGi06KkWYNpEEwTwTQygXeE4IaSCmfHP5rFienWocn1WPpCu4yeX8lMI59SaVQ7CrIqsiqB54S_odIYNeXenNhV25qPXz6bfbRs0JxEFzCBlx1RaJATnO2OMuCsqJrWgHJ3QInwueFwzx-mkx2tuWCOBJ5thulOyoerfbOKNGgpoqucJfBgzZWbeeeoOMaKjxJQA34dfJjhSD07jZXF0YzRAj3oBF73rH3xXn__8o_-PY3HcJPHRUfnfXZha7lY-Sdw3Z0vZ-3iaVyyvwD6LUkT
  priority: 102
  providerName: ProQuest
Title FusionCLM: enhanced molecular property prediction via knowledge fusion of chemical language models
URI https://link.springer.com/article/10.1186/s13321-025-01073-6
https://www.ncbi.nlm.nih.gov/pubmed/40883821
https://www.proquest.com/docview/3244968524
https://www.proquest.com/docview/3246359980
https://pubmed.ncbi.nlm.nih.gov/PMC12395716
https://doaj.org/article/4936e79c0a6b4d609b850913a1f6d70d
Volume 17
WOSCitedRecordID wos001560396600002&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: PRVADU
  databaseName: BioMed Central Open Access Free
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: RBZ
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.biomedcentral.com/search/
  providerName: BioMedCentral
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: DOA
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: M~E
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: P5Z
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: P5Z
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: M7P
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: 7X7
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: 7X7
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Materials Science Database
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: KB.
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/materialsscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: BENPR
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: BENPR
  dateStart: 20090101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: PIMPY
  dateStart: 20240101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerOpen
  customDbUrl:
  eissn: 1758-2946
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065707
  issn: 1758-2946
  databaseCode: C24
  dateStart: 20090112
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1db9Mw0GIbEnvhmxEYlUFIPECgdWPH5m2tWjGxVdH4UMeL5Tj21gfSqWkn8cJv585NChnwAC9OVJ-j-u7s-_DdmZDnPPFFnkseuyJP4oR5FavC4yFvkTrGciVCne3PR-lkIqdTldVJYVUT7d4cSYadOixrKd5UYE0xMH0ZBpsBY8Zii-zwnlQYyDfEHIf1_ouxHGmTHvPHcS0RFCr1_74f_yKQrgZLXjkxDYJofOv_pnCb3KwVT3qw5pQ75Jor75Ibw-a-t3skH6_QczY8On5LXXkeIgPo1-b2XHqBXvvF8hu84NkO0pNezgzdOOWoD-Pp3FNbVyGgjTeUhgt3qvvk03j0cfgurm9giC1XfBmL3HpmpGW-B09QZQznxvRtLnInZM-DsWeMFE4ZkPRdA-RVFvRFbqUHVSK1_Qdku5yX7iGhVmDSNvRY7hLhrQTL0nvGjUz7RuRJRF42RNEX60IbOhgoUug13jTgTQe8aRGRAdJtA4lFssMP88WZrtecTlRfuFTZLn6_EF0FPIllUE3PiyLtFhF5hlTXWAajxDibM7OqKn344UQfgBYDqiOYexF5UQP5OdDfmjptAWaFlbNakPstSCCfbXc3zKXrfaLSoM4mSkjOYP5PN904EmPfSjdfBRjQCsEs7kZkb82Lm3knICT6kvUiIltc2kJMu6ecnYcq4qCyKA7WckReNcz683_9HfOP_g38Mdllgd8x12efbC8XK_eEXLeXy1m16JCtdJqGVnbIzmA0yU46YTF3gm8E2veD1x2Mx82w_T6CNuNfADY7PM5OfwDcJUht
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD4aHdJ44X4JDDAIxANEa93EsZEQGoVp1dqqgg2NJ-M49tYHktK0Q_tT_EaO3aQjQ_C2B54a1U4UO9-5-dwAnsWRzdKUx6HJ0iiMqBWhyKxz8maJoTQVzNfZ_jxIRiN-eCjGa_CzzoVxYZU1T_SMOiu0OyPfQsEfCcZjGr2dfg9d1yjnXa1baCxhsWdOf6DJVr7pv8fv-5zSnQ_7vd2w6ioQ6ljE85Cl2lLFNbUd_EXxrOJYqa5OWWoY71g0YJTizAiF0qut8JWFRh0o1tyieEx0F597CdYjB_YWrI_7w_GXmve7OJKkTs3hbKtEC5CiuU5dgBwSU8ga4s93CfhTFvwmDM8Hap7z1nohuHPtf9u-63C1UrfJ9pI-bsCayW_CRq_ucncL0p2FOy_sDYavicmPfTwE-Vb3DCZT56uYzU_xwnm0HIrJyUSR1VEksf5-Uliiq9oLpD4DJr7NUHkbDi5kiXeglRe5uQdEM5eqjiM6NhGzmqM9bS2NFU-6iqVRAC9rOMjpsryI9GYZZ3IJHongkR48kgXwziFmNdOVBvd_FLMjWXEaGYkuM4nQbff8jLUFUqIr_qo6lmVJOwvgqcObdMU_chdddKQWZSn7nz7KbdTdUGFGIzeAF9UkWyDytKqSNXBVrl5YY-ZmYyZ-Pt0crvEoK-5YyjMwBvBkNezudBF_uSkWfg7qwkLwdgB3l1SwWneEorHLaScA3qCPxsY0R_LJsa-djoqaiJMObuWrmpTO3uvvO3__38t4DBu7-8OBHPRHew_gCvUE77KbNqE1ny3MQ7isT-aTcvaoYhgEvl40kf0CWheozw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELaWBQEX3o_AAgaBOEDU1o0dGwmhpUtFtaWqeGnFxTiOvdsDaWnaRfvX-HXMuEmXLILbHjg1qidR7HzjmfG8CHnME59nmeSxy7MkTphXsco9Onnz1DGWKRHqbH8epqOR3NtT4w3ys86FwbDKek8MG3U-tXhG3gLBnyghOUtavgqLGO_0X82-x9hBCj2tdTuNFUR23dEPMN_Kl4Md-NZPGOu_-dh7G1cdBmLLFV_EIrOeGWmZ78AviGrDuTFdm4nMCdnxYMwYI4VTBiRZ28DrKwv6ELfSg6hMbReee4acTcHGxHDCMf9SSwGMKEnrJB0pWiXYggwMd4ahcsBWsWgIwtAv4E-p8JtYPBmyecJvG8Rh__L_vJBXyKVKCafbK665SjZccY1c6NW9766TrL_EU8Te8N0L6oqDECVBv9WdhOkMPRjzxRFcoJ8LsU0PJ4auDyipD_fTqae2qshA65NhGpoPlTfIp1OZ4k2yWUwLd5tQKzCBHUYsd4nwVoKV7T3jRqZdI7IkIs9qaOjZquiIDsaaFHoFJA1A0gFIWkTkNaJnTYkFw8Mf0_m-rvYfnaiucKmybXx-LtoK-BNLwpqOF3naziPyCLGnsSRIgZjYN8uy1IMP7_U2aHSgRoPpG5GnFZGfAgqtqVI4YFZYRaxBudWghM9nm8M1NnW1Z5b6GJgRebgexjsxDrBw02WgAQ1ZKdmOyK0VR6znnYDA7ErWiYhs8EpjYZojxeQgVFQH9U3xtANL-bxmq-P3-vvK3_n3NB6Q88BZejgY7d4lF1ngfUx52iKbi_nS3SPn7OFiUs7vh52Dkq-nzWG_AARksDI
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=FusionCLM%3A+enhanced+molecular+property+prediction+via+knowledge+fusion+of+chemical+language+models&rft.jtitle=Journal+of+cheminformatics&rft.au=Lu%2C+Yutong&rft.au=Li%2C+Yan+Yi&rft.au=Sun%2C+Yan&rft.au=Hu%2C+Pingzhao&rft.date=2025-08-29&rft.pub=BioMed+Central+Ltd&rft.issn=1758-2946&rft.eissn=1758-2946&rft.volume=17&rft.issue=1&rft_id=info:doi/10.1186%2Fs13321-025-01073-6&rft.externalDocID=A853839862
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1758-2946&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1758-2946&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1758-2946&client=summon