TY - JOUR
T1 - CLigOpt: Controllable Ligand Design Through Target-Specific Optimisation
AU - Li, Yutong
AU - da Costa Avelar, Pedro Henrique
AU - Chen, Xinyue
AU - Zhang, Li
AU - Wu, Min
AU - Tsoka, Sophia
PY - 2024/5/17
Y1 - 2024/5/17
N2 - Motivation: Key challenge in deep generative models for molecular design is to navigate random sampling of the vast molecular space, and produce promising molecules that compromise property controls across multiple chemical criteria. Fragment-based drug design (FBDD), using fragments as starting points, is an effective way to constrain chemical space and improve generation of biologically active molecules. Furthermore, optimisation approaches are often implemented with generative models to search through chemical space, and identify promising samples which satisfy specific properties. Controllable FBDD has promising potential in efficient target-specific ligand design. Results: We propose a controllable FBDD model, CLigOpt, which can generate molecules with desired properties from a given fragment pair. CLigOpt is a Variational AutoEncoder-based model which utilises co-embeddings of node and edge features to fully mine information from molecular graphs, as well as a multi-objective Controllable Generation Module to generate molecules under property controls. CLigOpt achieves consistently strong performance in generating structurally and chemically valid molecules, as evaluated across six metrics. Applicability is illustrated through ligand candidates for hDHFR and it is shown that the proportion of feasible active molecules from the generated set is increased by 10%. Molecular docking and synthesisability prediction tasks are conducted to prioritise generated molecules to derive potential lead compounds.
AB - Motivation: Key challenge in deep generative models for molecular design is to navigate random sampling of the vast molecular space, and produce promising molecules that compromise property controls across multiple chemical criteria. Fragment-based drug design (FBDD), using fragments as starting points, is an effective way to constrain chemical space and improve generation of biologically active molecules. Furthermore, optimisation approaches are often implemented with generative models to search through chemical space, and identify promising samples which satisfy specific properties. Controllable FBDD has promising potential in efficient target-specific ligand design. Results: We propose a controllable FBDD model, CLigOpt, which can generate molecules with desired properties from a given fragment pair. CLigOpt is a Variational AutoEncoder-based model which utilises co-embeddings of node and edge features to fully mine information from molecular graphs, as well as a multi-objective Controllable Generation Module to generate molecules under property controls. CLigOpt achieves consistently strong performance in generating structurally and chemically valid molecules, as evaluated across six metrics. Applicability is illustrated through ligand candidates for hDHFR and it is shown that the proportion of feasible active molecules from the generated set is increased by 10%. Molecular docking and synthesisability prediction tasks are conducted to prioritise generated molecules to derive potential lead compounds.
U2 - 10.1101/2024.03.15.585255
DO - 10.1101/2024.03.15.585255
M3 - Article
SN - 1367-4803
JO - BIOINFORMATICS
JF - BIOINFORMATICS
M1 - DOI 10.1101/2024.03.15.585255
ER -