Binding-Site Compatible Fragment Growing Applied to the Design of β<sub>2</sub>-Adrenergic Receptor Ligands

Chevillard, Florent; Rimmer, Helena; Betti, Cecilia; Pardon, Els; Ballet, Steven; Hilten, Niek van; Steyaert, Jan; Diederich, Wibke E.; Kolb, Peter

doi:10.1021/acs.jmedchem.7b01558

Cited by 44 publications

(48 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Molecules can be constructed atom-by-atom or by combination of fragments. 13 They can be grown in the context of a binding pocket, [20][21][22][23][24] which allows for structure-based scoring, or be constructed and scored using entirely ligand-based methods. Choosing a very general representation of molecules for construction, such as atom-by-atom and bond-bybond building, allows for potentially exploring all of chemical space.…”

Section: Models For De Novo Molecular Designmentioning

confidence: 99%

GuacaMol: Benchmarking Models for de Novo Molecular Design

Brown

Fiscato

Segler

et al. 2019

J. Chem. Inf. Model.

655

883

View full text Add to dashboard Cite

De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, models for molecular design based on neural networks appeared recently and show promising results. However, the new models have not been profiled on consistent tasks, and comparative studies to well-established algorithms have only seldom been performed. To standardize the assessment of both classical and neural models for de novo molecular design, we propose an evaluation framework, GuacaMol, based on a suite of standardized benchmarks. The benchmark tasks encompass measuring the fidelity of the models to reproduce the property distribution of the training sets, the ability to generate novel molecules, the exploration and exploitation of chemical space, and a variety of single and multi-objective optimization tasks. The benchmarking open-source Python code, and a leaderboard can be found on https://benevolent.ai/guacamol.

show abstract

Section: Models For De Novo Molecular Designmentioning

confidence: 99%

GuacaMol: Benchmarking Models for de Novo Molecular Design

Brown

Fiscato

Segler

et al. 2019

J. Chem. Inf. Model.

655

883

View full text Add to dashboard Cite

show abstract

“…Chevillard et al reported the application of their "growing via merging" (GVM) workflow [58] to the design of b2adrenergic receptor antagonists.T he design process began with five core fragments that have experimentally determined b2activity.The five core fragments were docked into an X-ray structure of the receptor using DOCK3.6. [59] TheS EED program [60,61] was then used to place fragments compatible with the reductive amination reaction in the binding site (Figure 17).…”

Section: B2-adrenergic Receptor Ligandsmentioning

confidence: 99%

Automated De Novo Drug Design: Are We Nearly There Yet?

2019

View full text Add to dashboard Cite

Medicinal chemistry and, in particular, drug design have often been perceived as more of an art than a science. The many unknowns of human disease and the sheer complexity of chemical space render decision making in medicinal chemistry exceptionally demanding. Computational models can assist the medicinal chemist in this endeavour. Provided here is an overview of recent examples of automated de novo molecular design, a discussion of the concepts and computational approaches involved, and the daring prediction of some of the possibilities and limitations of drug design using machine intelligence.

show abstract

“…Another scenario in F2L is when the co-crystallization of a fragment hit commonly fails and no structural information about the binding mode is available. In these cases, alternative strategies for F2L process are required where the binding mode of a fragment can be predicted using molecular docking calculations (Kumar et al, 2012;Chevillard et al, 2018;Erlanson et al, 2019) on high-quality three-dimensional structures of the target in apo form or bound to other ligands. When neither of the latter are available, a theoretical model of the target protein can be obtained by homology modeling methods.…”

Section: Molecular Dockingmentioning

confidence: 99%