De Novo Design of Nurr1 Agonists via Fragment-Augmented Generative Deep Learning in Low-Data Regime

Generative neural networks trained on SMILES can design innovative bioactive molecules de novo. These so-called chemical language models (CLMs) have typically been trained on tens of template molecules for fine-tuning. However, it is challenging to apply CLM to orphan targets with few known ligands. We have fine-tuned a CLM with a single potent Nurr1 agonist as template in a fragment-augmented fashion and obtained novel Nurr1 agonists using sampling frequency for design prioritization. Nanomolar potency and binding affinity of the top-ranking design and its structural novelty compared to available Nurr1 ligands highlight its value as an early chemical tool and as a lead for Nurr1 agonist development, as well as the applicability of CLM in very low-data scenarios.

[1]  G. Höfner,et al.  Development of a Potent Nurr1 Agonist Tool for In Vivo Applications , 2023, Journal of medicinal chemistry.

[2]  F. Grisoni.  Chemical language models for de novo drug design: Challenges and opportunities. , 2023, Current opinion in structural biology.

[3]  G. Schneider,et al.  Leveraging molecular structure and bioactivity with chemical language models for de novo drug design , 2023, Nature Communications.

[4]  D. Merk,et al.  Medicinal Chemistry and Chemical Biology of Nurr1 Modulators: An Emerging Strategy in Neurodegeneration. , 2022, Journal of medicinal chemistry.

[5]  M. Solinas,et al.  A straightforward synthesis of functionalized 6H-benzo[c]chromenes from 3-alkenyl chromenes by intermolecular Diels-Alder/aromatization sequence. , 2021, Organic & biomolecular chemistry.

[6]  J. Heering,et al.  Nurr1 Modulation Mediates Neuroprotective Effects of Statins , 2021, bioRxiv.

[7]  G. Schneider,et al.  Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence , 2021, Angewandte Chemie.

[8]  Tobias Brandhofer,et al.  Easy access to drug building-blocks through benzylic C-H functionalization of phenolic ethers by photoredox catalysis. , 2021, Chemical communications.

[9]  Xiaohong Cheng,et al.  Thiophene-benzothiadiazole based donor–acceptor–donor (D-A-D) bolaamphiphiles, self-assembly and photophysical properties , 2021, Supramolecular Chemistry.

[10]  David S. Wishart,et al.  Deep Generative Models Enable Navigation in Sparsely Populated Chemical Space , 2021 .

[11]  R. Barzilay,et al.  Applications of Deep Learning in Molecule Generation and Molecular Property Prediction. , 2020, Accounts of chemical research.

[12]  S. Knapp,et al.  The orphan nuclear receptor Nurr1 is responsive to non-steroidal anti-inflammatory drugs , 2020, Communications Chemistry.

[13]  Gisbert Schneider,et al.  Drug discovery with explainable artificial intelligence , 2020, Nature Machine Intelligence.

[14]  Francesca Grisoni,et al.  Generative molecular design in low data regimes , 2020, Nature Machine Intelligence.

[15]  Andrew R. Leach,et al.  ChEMBL: towards direct deposition of bioassay data , 2018, Nucleic Acids Res..

[16]  Jean-Louis Reymond,et al.  Drug Analogs from Fragment-Based Long Short-Term Memory Generative Neural Networks , 2018, J. Chem. Inf. Model..

[17]  Gisbert Schneider,et al.  Tuning artificial intelligence on the de novo design of natural-product-inspired retinoid X receptor modulators , 2018, Communications Chemistry.

[18]  Gisbert Schneider,et al.  Scaffold hopping from natural products to synthetic mimetics by holistic molecular similarity , 2018, Communications Chemistry.

[19]  Esben Jannik Bjerrum,et al.  Improving Chemical Autoencoder Latent Space and Molecular De Novo Generation Diversity with Heteroencoders , 2018, Biomolecules.

[20]  Thomas Blaschke,et al.  The rise of deep learning in drug discovery. , 2018, Drug discovery today.

[21]  Gisbert Schneider,et al.  De Novo Design of Bioactive Small Molecules by Artificial Intelligence , 2018, Molecular informatics.

[22]  Thierry Kogej,et al.  Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks , 2017, ACS central science.

[23]  Thomas Blaschke,et al.  Application of Generative Autoencoder in De Novo Molecular Design , 2017, Molecular informatics.

[24]  Alex Graves,et al.  Sequence Transduction with Recurrent Neural Networks , 2012, ArXiv.

[25]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[26]  Markus Hartenfeller,et al.  DOGS: Reaction-Driven de novo Design of Bioactive Compounds , 2012, PLoS Comput. Biol..

[27]  D. Steinhilber,et al.  Functional characterization of vitamin D responding regions in the human 5-Lipoxygenase gene. , 2007, Biochimica et biophysica acta.

[28]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[30]  H. L. Morgan.  The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service. , 1965 .