Deep learning for molecular generation.

De novo drug design aims to generate novel chemical compounds with desirable chemical and pharmacological properties from scratch using computer-based methods. Recently, deep generative neural networks have become a very active research frontier in de novo drug discovery, both in theoretical and in experimental evidence, shedding light on a promising new direction of automatic molecular generation and optimization. In this review, we discussed recent development of deep learning models for molecular generation and summarized them as four different generative architectures with four different optimization strategies. We also discussed future directions of deep generative models for de novo drug design.

[1]  Peter S Kutchukian,et al.  De novo design: balancing novelty and confined chemical space , 2010, Expert opinion on drug discovery.

[2]  Alán Aspuru-Guzik,et al.  Reinforced Adversarial Neural Computer for de Novo Molecular Design , 2018, J. Chem. Inf. Model..

[3]  Sepp Hochreiter,et al.  Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery , 2018, J. Chem. Inf. Model..

[4]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

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

[6]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

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

[9]  David Ryan Koes,et al.  Protein-Ligand Scoring with Convolutional Neural Networks , 2016, Journal of chemical information and modeling.

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

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

[12]  Jürgen Schmidhuber,et al.  Transfer learning for Latin and Chinese characters with Deep Neural Networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[13]  Pavlo O. Dral,et al.  Quantum chemistry structures and properties of 134 kilo molecules , 2014, Scientific Data.

[14]  George Papadatos,et al.  The ChEMBL bioactivity database: an update , 2013, Nucleic Acids Res..

[15]  Nikos Komodakis,et al.  Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Cícero Nogueira dos Santos,et al.  Boosting Docking-Based Virtual Screening with Deep Learning , 2016, J. Chem. Inf. Model..

[17]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[18]  Luhua Lai,et al.  LigBuilder: A Multi-Purpose Program for Structure-Based Drug Design , 2000 .

[19]  Alexei A. Efros,et al.  Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[20]  Ben Glocker,et al.  Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks , 2017, MICCAI.

[21]  Sergio Gomez Colmenarejo,et al.  Hybrid computing using a neural network with dynamic external memory , 2016, Nature.

[22]  Y. Ip,et al.  Signal transduction by the c-Jun N-terminal kinase (JNK)--from inflammation to development. , 1998, Current opinion in cell biology.

[23]  Wannian Zhang,et al.  Fragment Informatics and Computational Fragment‐Based Drug Design: An Overview and Update , 2013, Medicinal research reviews.

[24]  Sergey Nikolenko,et al.  druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico. , 2017, Molecular pharmaceutics.

[25]  Koji Tsuda,et al.  ChemTS: an efficient python library for de novo molecular generation , 2017, Science and technology of advanced materials.

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

[27]  David Rogers,et al.  Extended-Connectivity Fingerprints , 2010, J. Chem. Inf. Model..

[28]  Gordon M. Crippen,et al.  Prediction of Physicochemical Parameters by Atomic Contributions , 1999, J. Chem. Inf. Comput. Sci..

[29]  Yibo Li,et al.  Multi-objective de novo drug design with conditional graph generative model , 2018, Journal of Cheminformatics.

[30]  Ryan G. Coleman,et al.  ZINC: A Free Tool to Discover Chemistry for Biology , 2012, J. Chem. Inf. Model..

[31]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[32]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[33]  Christophe Boesch,et al.  The origin of malignant malaria , 2009, Proceedings of the National Academy of Sciences.

[34]  Rachel Schreiber,et al.  Analysis of Transcription of theStaphylococcus aureus Aerobic Class Ib and Anaerobic Class III Ribonucleotide Reductase Genes in Response to Oxygen , 2001, Journal of bacteriology.

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

[36]  Markus Hartenfeller,et al.  De novo drug design. , 2010, Methods in molecular biology.

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

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

[39]  Arthur J. Olson,et al.  AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading , 2009, J. Comput. Chem..

[40]  Nikos Komodakis,et al.  GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders , 2018, ICANN.

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

[42]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[43]  Huikun Zhang,et al.  Machine Learning Consensus Scoring Improves Performance Across Targets in Structure-Based Virtual Screening , 2017, J. Chem. Inf. Model..

[44]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[45]  E H Cook,et al.  Primary Structure of the Human Platelet Serotonin 5‐HT2A Receptor: Identity with Frontal Cortex Serotonin 5‐HT2A Receptor , 1994, Journal of neurochemistry.

[46]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[47]  Dmitry Vetrov,et al.  Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery. , 2018, Molecular pharmaceutics.

[48]  Andrey Kazennov,et al.  The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology , 2016, Oncotarget.

[49]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

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

[52]  Olexandr Isayev,et al.  Deep reinforcement learning for de novo drug design , 2017, Science Advances.

[53]  Jean Ponce,et al.  Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[54]  B. Madras,et al.  History of the Discovery of the Antipsychotic Dopamine D2 Receptor: A Basis for the Dopamine Hypothesis of Schizophrenia , 2013, Journal of the history of the neurosciences.

[55]  Gisbert Schneider,et al.  Computer-based de novo design of drug-like molecules , 2005, Nature Reviews Drug Discovery.

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

[57]  Igor V. Tetko,et al.  How Accurately Can We Predict the Melting Points of Drug-like Compounds? , 2014, J. Chem. Inf. Model..

[58]  J. Woodgett,et al.  Mitogen inactivation of glycogen synthase kinase-3 beta in intact cells via serine 9 phosphorylation. , 1994, The Biochemical journal.