Decoupled coordinates for machine learning-based molecular fragment linking

Fleck, Markus; Müller, Michael G.; Weber, Noah; Trummer, Christopher

doi:10.1088/2632-2153/ac50fc

Cited by 1 publication

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, DeLinker was improved (DEVEL-OP) 21 by coupling it with a convolutional neural network to incorporate 3D pharmacophoric constraints into the linker design. Moreover, Fleck et al 22 incorporated the DeLinker framework with a bond−angle−torsion coordinate system to specify the relative orientation of the two fragments to be linked. Recently, the E(3)-equivariant linker design models, 23 including 3DLinker 24 and DiffLinker, 25 whose performances are independent of the initial coordinates, have been developed to generate molecular linkers that retain the spatial configuration of the two fragments.…”

Section: ■ Introductionmentioning

confidence: 99%

GRELinker: A Graph-Based Generative Model for Molecular Linker Design with Reinforcement and Curriculum Learning

Zhang,

Huang,

Xie

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Fragment-based drug discovery (FBDD) is widely used in drug design. One useful strategy in FBDD is designing linkers for linking fragments to optimize their molecular properties. In the current study, we present a novel generative fragment linking model, GRELinker, which utilizes a gated-graph neural network combined with reinforcement and curriculum learning to generate molecules with desirable attributes. The model has been shown to be efficient in multiple tasks, including controlling log P, optimizing synthesizability or predicted bioactivity of compounds, and generating molecules with high 3D similarity but low 2D similarity to the lead compound. Specifically, our model outperforms the previously reported reinforcement learning (RL) built-in method DRlinker on these benchmark tasks. Moreover, GRELinker has been successfully used in an actual FBDD case to generate optimized molecules with enhanced affinities by employing the docking score as the scoring function in RL. Besides, the implementation of curriculum learning in our framework enables the generation of structurally complex linkers more efficiently. These results demonstrate the benefits and feasibility of GRELinker in linker design for molecular optimization and drug discovery.

show abstract