Journal Article

DZNE-2025-00381

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png DrugDiff: small molecule diffusion model with flexible guidance towards molecular properties.

Oestreich, M. (First author)DZNE* ; Merdivan, E. ; Lee, M.DZNE* ; Schultze, J. L.DZNE* ; Piraud, M. ; Becker, M. (Last author)DZNE*

2025
BioMed Central London

This record in other databases:    

Please use a persistent id in citations: doi:10.1186/s13321-025-00965-x

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.

Keyword(s): Drug development ; Generative modelling ; Latent diffusion ; Targeted generation

---

Contributing Institute(s):

1. Modular High Performance Computing and Artificial Intelligence (AG Becker)
2. Clinical Single Cell Omics (CSCO) / Systems Medicine (AG Schultze)
3. Platform for Single Cell Genomics and Epigenomics (PRECISE)

Research Program(s):

1. 354 - Disease Prevention and Healthy Aging (POF4-354) (POF4-354)
2. 352 - Disease Mechanisms (POF4-352) (POF4-352)

Experiment(s):

1. Platform for Single Cell Genomics and Epigenomics at DZNE University of Bonn

Appears in the scientific report 2025

---

Database coverage:
; ; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Ebsco Academic Search ; Essential Science Indicators ; Fees ; IF >= 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---

---

Linked articles:

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Software Oestreich, M. (First author)DZNE* ; Merdivan, E. ; Lee, M.DZNE* ; Schultze, J. L.DZNE* ; Piraud, M. ; Becker, M. (Last author)DZNE*
Model: DrugDiff - small molecule diffusion model with flexible guidance towards molecular properties (v1)
Zenodo (2024) [10.5281/ZENODO.12755763]2024 BibTeX | EndNote: XML, Text | RIS

---