Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence**

Michael Moret, Moritz Helmstädter, Francesca Grisoni, Gisbert Schneider (Corresponding author), Daniel Merk (Corresponding author)

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

5 Downloads (Pure)


Chemical language models enable de novo drug design without the requirement for explicit molecular construction rules. While such models have been applied to generate novel compounds with desired bioactivity, the actual prioritization and selection of the most promising computational designs remains challenging. Herein, we leveraged the probabilities learnt by chemical language models with the beam search algorithm as a model-intrinsic technique for automated molecule design and scoring. Prospective application of this method yielded novel inverse agonists of retinoic acid receptor-related orphan receptors (RORs). Each design was synthesizable in three reaction steps and presented low-micromolar to nanomolar potency towards RORγ. This model-intrinsic sampling technique eliminates the strict need for external compound scoring functions, thereby further extending the applicability of generative artificial intelligence to data-driven drug discovery.

Originele taal-2Engels
Pagina's (van-tot)19477-19482
Aantal pagina's6
TijdschriftAngewandte Chemie - International Edition
Nummer van het tijdschrift35
StatusGepubliceerd - 23 aug 2021

Bibliografische nota

Publisher Copyright:
© 2021 The Authors. Angewandte Chemie International Edition published by Wiley-VCH GmbH


Duik in de onderzoeksthema's van 'Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence**'. Samen vormen ze een unieke vingerafdruk.

Citeer dit