Efficient multi-objective molecular optimization in a continuous latent space† †Electronic supplementary information (ESI) available: Details of the desirability scaling functions, high resolution figures and detailed results of the GuacaMol benchmark. See DOI: 10.1039/c9sc01928f

We utilize Particle Swarm Optimization to optimize molecules in a machine-learned continuous chemical representation with respect to multiple objectives such as biological activity, structural constrains or ADMET properties.

[1]  Peter Ertl,et al.  Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions , 2009, J. Cheminformatics.

[2]  Alexandre Varnek,et al.  Estimation of the size of drug-like chemical space based on GDB-17 data , 2013, Journal of Computer-Aided Molecular Design.

[3]  Suresh Babu,et al.  Discovery of an Orally Available, Brain Penetrant BACE1 Inhibitor that Affords Robust CNS Aβ Reduction. , 2012, ACS medicinal chemistry letters.

[4]  Brian K. Shoichet,et al.  Virtual screening of chemical libraries , 2004, Nature.

[5]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[6]  Marwin H. S. Segler,et al.  GuacaMol: Benchmarking Models for De Novo Molecular Design , 2018, J. Chem. Inf. Model..

[7]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[8]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[9]  Evgeny Putin,et al.  Adversarial Threshold Neural Computer for Molecular de Novo Design. , 2018, Molecular pharmaceutics.

[10]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[11]  Markus Hartenfeller,et al.  Concept of Combinatorial De Novo Design of Drug‐like Molecules by Particle Swarm Optimization , 2008, Chemical biology & drug design.

[12]  John P. Overington,et al.  ChEMBL: a large-scale bioactivity database for drug discovery , 2011, Nucleic Acids Res..

[13]  Mark A. Murcko,et al.  Virtual screening : an overview , 1998 .

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

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

[16]  Thomas Blaschke,et al.  Molecular de-novo design through deep reinforcement learning , 2017, Journal of Cheminformatics.

[17]  Amedeo Caflisch,et al.  Fragment-Based de Novo Ligand Design by Multiobjective Evolutionary Optimization , 2008, J. Chem. Inf. Model..

[18]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[19]  Eduardo F. Morales,et al.  An Introduction to Reinforcement Learning , 2011 .

[20]  D. Cummins,et al.  Integrating Everything: The Molecule Selection Toolkit, a System for Compound Prioritization in Drug Discovery. , 2016, Journal of medicinal chemistry.

[21]  Frank Noé,et al.  Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations , 2018 .

[22]  Petra Schneider,et al.  Multi-objective molecular de novo design by adaptive fragment prioritization. , 2014, Angewandte Chemie.

[23]  Igor V. Tetko,et al.  ToxAlerts: A Web Server of Structural Alerts for Toxic Chemicals and Compounds with Potential Adverse Reactions , 2012, J. Chem. Inf. Model..

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

[25]  Luhua Lai,et al.  LigBuilder 2: A Practical de Novo Drug Design Approach , 2011, J. Chem. Inf. Model..

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