Cargando…

Combining generative artificial intelligence and on-chip synthesis for de novo drug design

Automating the molecular design-make-test-analyze cycle accelerates hit and lead finding for drug discovery. Using deep learning for molecular design and a microfluidics platform for on-chip chemical synthesis, liver X receptor (LXR) agonists were generated from scratch. The computational pipeline w...

Descripción completa

Detalles Bibliográficos
Autores principales: Grisoni, Francesca, Huisman, Berend J. H., Button, Alexander L., Moret, Michael, Atz, Kenneth, Merk, Daniel, Schneider, Gisbert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Association for the Advancement of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8195470/
https://www.ncbi.nlm.nih.gov/pubmed/34117066
http://dx.doi.org/10.1126/sciadv.abg3338
_version_ 1783706508530286592
author Grisoni, Francesca
Huisman, Berend J. H.
Button, Alexander L.
Moret, Michael
Atz, Kenneth
Merk, Daniel
Schneider, Gisbert
author_facet Grisoni, Francesca
Huisman, Berend J. H.
Button, Alexander L.
Moret, Michael
Atz, Kenneth
Merk, Daniel
Schneider, Gisbert
author_sort Grisoni, Francesca
collection PubMed
description Automating the molecular design-make-test-analyze cycle accelerates hit and lead finding for drug discovery. Using deep learning for molecular design and a microfluidics platform for on-chip chemical synthesis, liver X receptor (LXR) agonists were generated from scratch. The computational pipeline was tuned to explore the chemical space of known LXRα agonists and generate novel molecular candidates. To ensure compatibility with automated on-chip synthesis, the chemical space was confined to the virtual products obtainable from 17 one-step reactions. Twenty-five de novo designs were successfully synthesized in flow. In vitro screening of the crude reaction products revealed 17 (68%) hits, with up to 60-fold LXR activation. The batch resynthesis, purification, and retesting of 14 of these compounds confirmed that 12 of them were potent LXR agonists. These results support the suitability of the proposed design-make-test-analyze framework as a blueprint for automated drug design with artificial intelligence and miniaturized bench-top synthesis.
format Online
Article
Text
id pubmed-8195470
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher American Association for the Advancement of Science
record_format MEDLINE/PubMed
spelling pubmed-81954702021-06-24 Combining generative artificial intelligence and on-chip synthesis for de novo drug design Grisoni, Francesca Huisman, Berend J. H. Button, Alexander L. Moret, Michael Atz, Kenneth Merk, Daniel Schneider, Gisbert Sci Adv Research Articles Automating the molecular design-make-test-analyze cycle accelerates hit and lead finding for drug discovery. Using deep learning for molecular design and a microfluidics platform for on-chip chemical synthesis, liver X receptor (LXR) agonists were generated from scratch. The computational pipeline was tuned to explore the chemical space of known LXRα agonists and generate novel molecular candidates. To ensure compatibility with automated on-chip synthesis, the chemical space was confined to the virtual products obtainable from 17 one-step reactions. Twenty-five de novo designs were successfully synthesized in flow. In vitro screening of the crude reaction products revealed 17 (68%) hits, with up to 60-fold LXR activation. The batch resynthesis, purification, and retesting of 14 of these compounds confirmed that 12 of them were potent LXR agonists. These results support the suitability of the proposed design-make-test-analyze framework as a blueprint for automated drug design with artificial intelligence and miniaturized bench-top synthesis. American Association for the Advancement of Science 2021-06-11 /pmc/articles/PMC8195470/ /pubmed/34117066 http://dx.doi.org/10.1126/sciadv.abg3338 Text en Copyright © 2021 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC). https://creativecommons.org/licenses/by-nc/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license (https://creativecommons.org/licenses/by-nc/4.0/) , which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.
spellingShingle Research Articles
Grisoni, Francesca
Huisman, Berend J. H.
Button, Alexander L.
Moret, Michael
Atz, Kenneth
Merk, Daniel
Schneider, Gisbert
Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title_full Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title_fullStr Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title_full_unstemmed Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title_short Combining generative artificial intelligence and on-chip synthesis for de novo drug design
title_sort combining generative artificial intelligence and on-chip synthesis for de novo drug design
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8195470/
https://www.ncbi.nlm.nih.gov/pubmed/34117066
http://dx.doi.org/10.1126/sciadv.abg3338
work_keys_str_mv AT grisonifrancesca combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT huismanberendjh combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT buttonalexanderl combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT moretmichael combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT atzkenneth combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT merkdaniel combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign
AT schneidergisbert combininggenerativeartificialintelligenceandonchipsynthesisfordenovodrugdesign