TY - JOUR
T1 - Equivariant 3D-conditional diffusion model for molecular linker design
AU - Igashov, Ilia
AU - Stärk, Hannes
AU - Vignac, Clément
AU - Schneuing, Arne
AU - Satorras, Victor Garcia
AU - Frossard, Pascal
AU - Welling, Max
AU - Bronstein, Michael
AU - Correia, Bruno
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2024
Y1 - 2024
N2 - Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically relevant candidate drug molecules. In this work, we propose DiffLinker, an E(3)-equivariant three-dimensional conditional diffusion model for molecular linker design. Given a set of disconnected fragments, our model places missing atoms in between and designs a molecule incorporating all the initial fragments. Unlike previous approaches that are only able to connect pairs of molecular fragments, our method can link an arbitrary number of fragments. Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments. We demonstrate that DiffLinker outperforms other methods on the standard datasets, generating more diverse and synthetically accessible molecules. We experimentally test our method in real-world applications, showing that it can successfully generate valid linkers conditioned on target protein pockets.
AB - Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically relevant candidate drug molecules. In this work, we propose DiffLinker, an E(3)-equivariant three-dimensional conditional diffusion model for molecular linker design. Given a set of disconnected fragments, our model places missing atoms in between and designs a molecule incorporating all the initial fragments. Unlike previous approaches that are only able to connect pairs of molecular fragments, our method can link an arbitrary number of fragments. Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments. We demonstrate that DiffLinker outperforms other methods on the standard datasets, generating more diverse and synthetically accessible molecules. We experimentally test our method in real-world applications, showing that it can successfully generate valid linkers conditioned on target protein pockets.
UR - http://www.scopus.com/inward/record.url?scp=85190105797&partnerID=8YFLogxK
U2 - 10.1038/s42256-024-00815-9
DO - 10.1038/s42256-024-00815-9
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85190105797
SN - 2522-5839
JO - Nature Machine Intelligence
JF - Nature Machine Intelligence
ER -