Navigating Chemical Space By Interfacing Generative Artificial Intelligence and Molecular Docking

Here we report the testing and application of a simple, structure-aware framework to design target-specific screening libraries for drug development. Our approach combines advances in generative artificial intelligence (AI) with conventional molecular docking to rapidly explore chemical space conditioned on the unique physiochemical properties of the active site of a biomolecular target. As a proof-of-concept, we used our framework to construct a focused library for cyclin-dependent kinase type-2 (CDK2). We then used it to rapidly generate a library specific to the active site of the main protease (Mpro) of the SARS-CoV-2 virus, which causes COVID-19. By comparing approved and experimental drugs to compounds in our library, we also identified six drugs, namely, Naratriptan, Etryptamine, Panobinostat, Procainamide, Sertraline, and Lidamidine, as possible SARS-CoV-2 Mpro targeting compounds and, as such, potential drug repurposing candidates. To complement the open-science COVID-19 drug discovery initiatives, we make our SARS-CoV-2 Mpro library fully accessible to the research community (https://github.com/atfrank/SARS-CoV-2).

[1]  F. Svensson,et al.  Computational Chemistry on a Budget - Supporting Drug Discovery with Limited Resources. , 2020, Journal of medicinal chemistry.

[2]  Valerie J. Gillet,et al.  SPROUT: A program for structure generation , 1993, J. Comput. Aided Mol. Des..

[3]  Gerard J. P. van Westen,et al.  An exploration strategy improves the diversity of de novo ligands using deep reinforcement learning: a case for the adenosine A2A receptor , 2018, Journal of Cheminformatics.

[4]  E. Shakhnovich,et al.  SMoG: de Novo Design Method Based on Simple, Fast, and Accurate Free Energy Estimates. 1. Methodology and Supporting Evidence , 1996 .

[5]  Barry Robson,et al.  PRO_LIGAND: An approach to de novo molecular design. 1. Application to the design of organic molecules , 1995, J. Comput. Aided Mol. Des..

[6]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[7]  Pascal Bonnet,et al.  In Silico Peptide Ligation: Iterative Residue Docking and Linking as a New Approach to Predict Protein-Peptide Interactions , 2019, Molecules.

[8]  Eugene I Shakhnovich,et al.  OpenGrowth: An Automated and Rational Algorithm for Finding New Protein Ligands. , 2016, Journal of medicinal chemistry.

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

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

[11]  Gisbert Schneider,et al.  Automated De Novo Drug Design: Are We Nearly There Yet? , 2019, Angewandte Chemie.

[12]  Bhupesh Goyal,et al.  Targeting the Dimerization of the Main Protease of Coronaviruses: A Potential Broad-Spectrum Therapeutic Strategy , 2020, ACS combinatorial science.

[13]  Kwong-Sak Leung,et al.  iSyn: WebGL-Based Interactive De Novo Drug Design , 2014, 2014 18th International Conference on Information Visualisation.

[14]  R. Hilgenfeld,et al.  Crystal structure of SARS-CoV-2 main protease provides a basis for design of improved α-ketoamide inhibitors , 2020, Science.

[15]  Frits Daeyaert,et al.  A Pareto Algorithm for Efficient De Novo Design of Multi‐functional Molecules , 2017, Molecular informatics.

[16]  M. Murcko,et al.  GroupBuild: a fragment-based method for de novo drug design. , 1993, Journal of medicinal chemistry.

[17]  Rachelle J Bienstock,et al.  Computational methods for fragment-based ligand design: growing and linking. , 2015, Methods in molecular biology.

[18]  Xavier Barril,et al.  rDock: A Fast, Versatile and Open Source Program for Docking Ligands to Proteins and Nucleic Acids , 2014, PLoS Comput. Biol..

[19]  W. Howe,et al.  Computer design of bioactive molecules: A method for receptor‐based de novo ligand design , 1991, Proteins.

[20]  Eugene I. Shakhnovich,et al.  SMOG : DE NOVO DESIGN METHOD BASED ON SIMPLE, FAST, AND ACCURATE FREE ENERGY ESTIMATES. 2. CASE STUDIES IN MOLECULAR DESIGN , 1997 .

[21]  Lorenz C. Blum,et al.  Chemical space as a source for new drugs , 2010 .

[22]  Petra Schneider,et al.  Generative Recurrent Networks for De Novo Drug Design , 2017, Molecular informatics.

[23]  Valerie J. Gillet,et al.  Automated structure design in 3D , 1990 .

[24]  Saskia Preissner,et al.  SuperDRUG2: a one stop resource for approved/marketed drugs , 2017, Nucleic Acids Res..

[25]  David S. Wishart,et al.  DrugBank 5.0: a major update to the DrugBank database for 2018 , 2017, Nucleic Acids Res..

[26]  P. Roche,et al.  Chemistry‐driven Hit‐to‐lead Optimization Guided by Structure‐based Approaches , 2018, Molecular informatics.

[27]  P. Lienau,et al.  Conformational Adaption May Explain the Slow Dissociation Kinetics of Roniciclib (BAY 1000394), a Type I CDK Inhibitor with Kinetic Selectivity for CDK2 and CDK9. , 2016, ACS chemical biology.

[28]  G. V. Paolini,et al.  Quantifying the chemical beauty of drugs. , 2012, Nature chemistry.

[29]  Rolf Hilgenfeld,et al.  Coronavirus Main Proteinase (3CLpro) Structure: Basis for Design of Anti-SARS Drugs , 2003, Science.

[30]  Hans-Joachim Böhm,et al.  The computer program LUDI: A new method for the de novo design of enzyme inhibitors , 1992, J. Comput. Aided Mol. Des..

[31]  Charles C. Persinger,et al.  How to improve R&D productivity: the pharmaceutical industry's grand challenge , 2010, Nature Reviews Drug Discovery.

[32]  D. E. Clark,et al.  Virtual Screening: Is Bigger Always Better? Or Can Small Be Beautiful? , 2020, J. Chem. Inf. Model..

[33]  David Ryan Koes,et al.  ZINCPharmer: pharmacophore search of the ZINC database , 2012, Nucleic Acids Res..

[34]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.