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

Overview

Journal Angew Chem Int Ed Engl

Specialty Chemistry

Date 2021 Jun 24

PMID 34165856

Citations 19

Authors

Michael Moret

Moritz Helmstadter

Francesca Grisoni

Gisbert Schneider

Daniel Merk

Affiliations

Soon will be listed here.

Abstract

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.

Citing Articles

Comparative Evaluation and Profiling of Chemical Tools for the Nuclear Hormone Receptor Family 2.

Lewandowski M, Busch R, Marschner J, Merk D ACS Pharmacol Transl Sci. 2025; .

PMID: 40046426 PMC: 7617459. DOI: 10.1021/acsptsci.4c00719.

Chemogenomics for steroid hormone receptors (NR3).

Schallmayer E, Isigkeit L, Elson L, Muller S, Knapp S, Marschner J Commun Chem. 2025; 8(1):29.

PMID: 39900826 PMC: 11790914. DOI: 10.1038/s42004-025-01427-z.

Automated design of multi-target ligands by generative deep learning.

Isigkeit L, Hormann T, Schallmayer E, Scholz K, Lillich F, Ehrler J Nat Commun. 2024; 15(1):7946.

PMID: 39261471 PMC: 11390726. DOI: 10.1038/s41467-024-52060-8.

A High-Quality Photoswitchable Probe that Selectively and Potently Regulates the Transcription Factor RORγ.

Reynders M, Willems S, Marschner J, Wein T, Merk D, Thorn-Seshold O Angew Chem Int Ed Engl. 2024; 63(49):e202410139.

PMID: 39248642 PMC: 11586699. DOI: 10.1002/anie.202410139.

Chemical language modeling with structured state space sequence models.

Ozcelik R, de Ruiter S, Criscuolo E, Grisoni F Nat Commun. 2024; 15(1):6176.

PMID: 39039051 PMC: 11263548. DOI: 10.1038/s41467-024-50469-9.

References

Ertl P, Schuffenhauer A . Cheminformatics analysis of natural products: lessons from nature inspiring the design of new drugs. Prog Drug Res. 2008; 66:217, 219-35. DOI: 10.1007/978-3-7643-8595-8_4. View

Yuan W, Jiang D, Nambiar D, Liew L, Hay M, Bloomstein J . Chemical Space Mimicry for Drug Discovery. J Chem Inf Model. 2017; 57(4):875-882. PMC: 5802964. DOI: 10.1021/acs.jcim.6b00754. View

Newman D, Cragg G . Natural Products as Sources of New Drugs over the Nearly Four Decades from 01/1981 to 09/2019. J Nat Prod. 2020; 83(3):770-803. DOI: 10.1021/acs.jnatprod.9b01285. View

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

Awale M, Sirockin F, Stiefl N, Reymond J . Drug Analogs from Fragment-Based Long Short-Term Memory Generative Neural Networks. J Chem Inf Model. 2019; 59(4):1347-1356. DOI: 10.1021/acs.jcim.8b00902. View

Walters W, Barzilay R . Applications of Deep Learning in Molecule Generation and Molecular Property Prediction. Acc Chem Res. 2020; 54(2):263-270. DOI: 10.1021/acs.accounts.0c00699. View

Hochreiter S, Schmidhuber J . Long short-term memory. Neural Comput. 1997; 9(8):1735-80. DOI: 10.1162/neco.1997.9.8.1735. View

Schwaller P, Petraglia R, Zullo V, Nair V, Haeuselmann R, Pisoni R . Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy. Chem Sci. 2021; 11(12):3316-3325. PMC: 8152799. DOI: 10.1039/c9sc05704h. View

Asimus S, Palmer R, Albayaty M, Forsman H, Lundin C, Olsson M . Pharmacokinetics, pharmacodynamics and safety of the inverse retinoic acid-related orphan receptor γ agonist AZD0284. Br J Clin Pharmacol. 2020; 86(7):1398-1405. PMC: 7319014. DOI: 10.1111/bcp.14253. View

10.

Moret M, Helmstadter M, Grisoni F, Schneider G, Merk D . Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence*. Angew Chem Int Ed Engl. 2021; 60(35):19477-19482. PMC: 8457062. DOI: 10.1002/anie.202104405. View

11.

Ertl P, Roggo S, Schuffenhauer A . Natural product-likeness score and its application for prioritization of compound libraries. J Chem Inf Model. 2007; 48(1):68-74. DOI: 10.1021/ci700286x. View

12.

Grisoni F, Schneider G . Molecular Scaffold Hopping via Holistic Molecular Representation. Methods Mol Biol. 2021; 2266:11-35. DOI: 10.1007/978-1-0716-1209-5_2. View

13.

Yang X, Zhang J, Yoshizoe K, Terayama K, Tsuda K . ChemTS: an efficient python library for molecular generation. Sci Technol Adv Mater. 2018; 18(1):972-976. PMC: 5801530. DOI: 10.1080/14686996.2017.1401424. View

14.

Merk D, Friedrich L, Grisoni F, Schneider G . De Novo Design of Bioactive Small Molecules by Artificial Intelligence. Mol Inform. 2018; 37(1-2). PMC: 5838524. DOI: 10.1002/minf.201700153. View

15.

Schmidhuber J . Deep learning in neural networks: an overview. Neural Netw. 2014; 61:85-117. DOI: 10.1016/j.neunet.2014.09.003. View

16.

Kojetin D, Burris T . REV-ERB and ROR nuclear receptors as drug targets. Nat Rev Drug Discov. 2014; 13(3):197-216. PMC: 4865262. DOI: 10.1038/nrd4100. View

17.

Sanchez-Lengeling B, Aspuru-Guzik A . Inverse molecular design using machine learning: Generative models for matter engineering. Science. 2018; 361(6400):360-365. DOI: 10.1126/science.aat2663. View

18.

Rodrigues T, Reker D, Schneider P, Schneider G . Counting on natural products for drug design. Nat Chem. 2016; 8(6):531-41. DOI: 10.1038/nchem.2479. View

19.

Bento A, Gaulton A, Hersey A, Bellis L, Chambers J, Davies M . The ChEMBL bioactivity database: an update. Nucleic Acids Res. 2013; 42(Database issue):D1083-90. PMC: 3965067. DOI: 10.1093/nar/gkt1031. View

20.

Solt L, Burris T . Action of RORs and their ligands in (patho)physiology. Trends Endocrinol Metab. 2012; 23(12):619-27. PMC: 3500583. DOI: 10.1016/j.tem.2012.05.012. View