% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Oestreich:277318,
author = {Oestreich, Marie and Merdivan, Erinc and Lee, Michael and
Schultze, Joachim L and Piraud, Marie and Becker, Matthias},
title = {{D}rug{D}iff: small molecule diffusion model with flexible
guidance towards molecular properties.},
journal = {Journal of cheminformatics},
volume = {17},
number = {1},
issn = {1758-2946},
address = {London},
publisher = {BioMed Central},
reportid = {DZNE-2025-00381},
pages = {23},
year = {2025},
abstract = {With 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.},
keywords = {Drug development (Other) / Generative modelling (Other) /
Latent diffusion (Other) / Targeted generation (Other)},
cin = {AG Becker / AG Schultze / PRECISE},
ddc = {540},
cid = {I:(DE-2719)5000079 / I:(DE-2719)1013038 /
I:(DE-2719)1013031},
pnm = {354 - Disease Prevention and Healthy Aging (POF4-354) / 352
- Disease Mechanisms (POF4-352)},
pid = {G:(DE-HGF)POF4-354 / G:(DE-HGF)POF4-352},
experiment = {EXP:(DE-2719)PRECISE-20190321},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40001177},
doi = {10.1186/s13321-025-00965-x},
url = {https://pub.dzne.de/record/277318},
}