000277318 001__ 277318
000277318 005__ 20250323000918.0
000277318 0247_ $$2doi$$a10.1186/s13321-025-00965-x
000277318 0247_ $$2pmid$$apmid:40001177
000277318 0247_ $$2altmetric$$aaltmetric:174624266
000277318 037__ $$aDZNE-2025-00381
000277318 041__ $$aEnglish
000277318 082__ $$a540
000277318 1001_ $$0P:(DE-2719)9002070$$aOestreich, Marie$$b0$$eFirst author$$udzne
000277318 245__ $$aDrugDiff: small molecule diffusion model with flexible guidance towards molecular properties.
000277318 260__ $$aLondon$$bBioMed Central$$c2025
000277318 3367_ $$2DRIVER$$aarticle
000277318 3367_ $$2DataCite$$aOutput Types/Journal article
000277318 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1740585001_14535
000277318 3367_ $$2BibTeX$$aARTICLE
000277318 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000277318 3367_ $$00$$2EndNote$$aJournal Article
000277318 520__ $$aWith the cost/yield-ratio of drug development becoming increasingly unfavourable, recent work has explored machine learning to accelerate early stages of the development process. Given the current success of deep generative models across domains, we here investigated their application to the property-based proposal of new small molecules for drug development. Specifically, we trained a latent diffusion model-DrugDiff-paired with predictor guidance to generate novel compounds with a variety of desired molecular properties. The architecture was designed to be highly flexible and easily adaptable to future scenarios. Our experiments showed successful generation of unique, diverse and novel small molecules with targeted properties. The code is available at https://github.com/MarieOestreich/DrugDiff . SCIENTIFIC CONTRIBUTION: This work expands the use of generative modelling in the field of drug development from previously introduced models for proteins and RNA to the here presented application to small molecules. With small molecules making up the majority of drugs, but simultaneously being difficult to model due to their elaborate chemical rules, this work tackles a new level of difficulty in comparison to sequence-based molecule generation as is the case for proteins and RNA. Additionally, the demonstrated framework is highly flexible, allowing easy addition or removal of considered molecular properties without the need to retrain the model, making it highly adaptable to diverse research settings and it shows compelling performance for a wide variety of targeted molecular properties.
000277318 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000277318 536__ $$0G:(DE-HGF)POF4-352$$a352 - Disease Mechanisms (POF4-352)$$cPOF4-352$$fPOF IV$$x1
000277318 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000277318 650_7 $$2Other$$aDrug development
000277318 650_7 $$2Other$$aGenerative modelling
000277318 650_7 $$2Other$$aLatent diffusion
000277318 650_7 $$2Other$$aTargeted generation
000277318 693__ $$0EXP:(DE-2719)PRECISE-20190321$$5EXP:(DE-2719)PRECISE-20190321$$ePlatform for Single Cell Genomics and Epigenomics at DZNE  University of Bonn$$x0
000277318 7001_ $$0P:(DE-HGF)0$$aMerdivan, Erinc$$b1
000277318 7001_ $$0P:(DE-2719)9000637$$aLee, Michael$$b2$$udzne
000277318 7001_ $$0P:(DE-2719)2811660$$aSchultze, Joachim L$$b3$$udzne
000277318 7001_ $$0P:(DE-HGF)0$$aPiraud, Marie$$b4
000277318 7001_ $$0P:(DE-2719)2812750$$aBecker, Matthias$$b5$$eLast author$$udzne
000277318 773__ $$0PERI:(DE-600)2486539-4$$a10.1186/s13321-025-00965-x$$gVol. 17, no. 1, p. 23$$n1$$p23$$tJournal of cheminformatics$$v17$$x1758-2946$$y2025
000277318 7870_ $$0DZNE-2024-00911$$aOestreich, Marie et.al.$$dZenodo, 2024$$iRelatedTo$$r$$tModel: DrugDiff - small molecule diffusion model with flexible guidance towards molecular properties (v1)
000277318 8564_ $$uhttps://pub.dzne.de/record/277318/files/DZNE-2025-00381.pdf$$yOpenAccess
000277318 8564_ $$uhttps://pub.dzne.de/record/277318/files/DZNE-2025-00381.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000277318 909CO $$ooai:pub.dzne.de:277318$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000277318 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002070$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE
000277318 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9000637$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000277318 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811660$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000277318 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812750$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b5$$kDZNE
000277318 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000277318 9131_ $$0G:(DE-HGF)POF4-352$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Mechanisms$$x1
000277318 9141_ $$y2025
000277318 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-01
000277318 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000277318 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bJ CHEMINFORMATICS : 2022$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bJ CHEMINFORMATICS : 2022$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-04-10T15:40:53Z
000277318 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-04-10T15:40:53Z
000277318 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000277318 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-01
000277318 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-01
000277318 9201_ $$0I:(DE-2719)5000079$$kAG Becker$$lModular High Performance Computing and Artificial Intelligence$$x0
000277318 9201_ $$0I:(DE-2719)1013038$$kAG Schultze$$lClinical Single Cell Omics (CSCO) / Systems Medicine$$x1
000277318 9201_ $$0I:(DE-2719)1013031$$kPRECISE$$lPlatform for Single Cell Genomics and Epigenomics$$x2
000277318 980__ $$ajournal
000277318 980__ $$aVDB
000277318 980__ $$aUNRESTRICTED
000277318 980__ $$aI:(DE-2719)5000079
000277318 980__ $$aI:(DE-2719)1013038
000277318 980__ $$aI:(DE-2719)1013031
000277318 9801_ $$aFullTexts