Advancing Drug Discovery via Artificial Intelligence.

Drug discovery and development are among the most important translational science activities that contribute to human health and wellbeing. However, the development of a new drug is a very complex, expensive, and long process which typically costs 2.6 billion USD and takes 12 years on average. How to decrease the costs and speed up new drug discovery has become a challenging and urgent question in industry. Artificial intelligence (AI) combined with new experimental technologies is expected to make the hunt for new pharmaceuticals quicker, cheaper, and more effective. We discuss here emerging applications of AI to improve the drug discovery process.

[1]  Woody Sherman,et al.  AutoQSAR: an automated machine learning tool for best-practice quantitative structure-activity relationship modeling. , 2016, Future medicinal chemistry.

[2]  S. Lynch,et al.  A comparison of physical properties, screening procedures and a human efficacy trial for predicting the bioavailability of commercial elemental iron powders used for food fortification. , 2007, International journal for vitamin and nutrition research. Internationale Zeitschrift fur Vitamin- und Ernahrungsforschung. Journal international de vitaminologie et de nutrition.

[3]  Alexander G. Dossetter,et al.  A statistical analysis of in vitro human microsomal metabolic stability of small phenyl group substituents, leading to improved design sets for parallel SAR exploration of a chemical series. , 2010, Bioorganic & medicinal chemistry.

[4]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

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

[6]  Kit-Kay Mak,et al.  Artificial intelligence in drug development: present status and future prospects. , 2019, Drug discovery today.

[7]  Shuguang Yuan,et al.  New Binding Sites, New Opportunities for GPCR Drug Discovery. , 2019, Trends in biochemical sciences.

[8]  Pritish Narayanan,et al.  Equivalent-accuracy accelerated neural-network training using analogue memory , 2018, Nature.

[9]  A. Dinnyés,et al.  Drug Discovery Models and Toxicity Testing Using Embryonic and Induced Pluripotent Stem-Cell-Derived Cardiac and Neuronal Cells , 2012, Stem cells international.

[10]  Matthias Rarey,et al.  Machine Learning in Drug Discovery , 2018, Journal of Chemical Information and Modeling.

[11]  Friedrich Rippmann,et al.  Coupling Matched Molecular Pairs with Machine Learning for Virtual Compound Optimization , 2017, J. Chem. Inf. Model..

[12]  U. Ryde,et al.  Predicting Relative Binding Affinity Using Nonequilibrium QM/MM Simulations. , 2018, Journal of chemical theory and computation.

[13]  George Khelashvili,et al.  A Machine Learning Approach for the Discovery of Ligand-Specific Functional Mechanisms of GPCRs , 2019, Molecules.

[14]  Ola Spjuth,et al.  A confidence predictor for logD using conformal regression and a support-vector machine , 2018, Journal of Cheminformatics.

[15]  J. Kazius,et al.  Derivation and validation of toxicophores for mutagenicity prediction. , 2005, Journal of medicinal chemistry.

[16]  Amedeo Caflisch,et al.  Protein structure-based drug design: from docking to molecular dynamics. , 2018, Current opinion in structural biology.

[17]  U. Ryde.  QM/MM Calculations on Proteins. , 2016, Methods in enzymology.

[18]  Günter Klambauer,et al.  DeepTox: Toxicity Prediction using Deep Learning , 2016, Front. Environ. Sci..

[19]  Alán Aspuru-Guzik,et al.  Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC) , 2017 .

[20]  Frank Glorius,et al.  A robustness screen for the rapid assessment of chemical reactions , 2013, Nature Chemistry.

[21]  Piotr Zielenkiewicz,et al.  Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field , 2015, Journal of Cheminformatics.

[22]  I. Fernández-Ruíz.  Artificial intelligence to improve the diagnosis of cardiovascular diseases , 2019, Nature Reviews Cardiology.

[23]  Andy Liaw,et al.  Demystifying Multitask Deep Neural Networks for Quantitative Structure-Activity Relationships , 2017, J. Chem. Inf. Model..

[24]  J. Bailar,et al.  Toxicity Testing in the 21st Century: A Vision and a Strategy , 2010, Journal of toxicology and environmental health. Part B, Critical reviews.

[25]  Yin-Jia Zhang,et al.  The potential for machine learning in hybrid QM/MM calculations. , 2018, The Journal of chemical physics.

[26]  Tristan Aumentado-Armstrong,et al.  Latent Molecular Optimization for Targeted Therapeutic Design , 2018, ArXiv.

[27]  L. Dardenne,et al.  Empirical Scoring Functions for Structure-Based Virtual Screening: Applications, Critical Aspects, and Challenges , 2018, Front. Pharmacol..

[28]  Richard N. Zare,et al.  Optimizing Chemical Reactions with Deep Reinforcement Learning , 2017, ACS central science.

[29]  Regina Barzilay,et al.  Prediction of Organic Reaction Outcomes Using Machine Learning , 2017, ACS central science.

[30]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[31]  Masakazu Sekijima,et al.  Improved Method of Structure-Based Virtual Screening via Interaction-Energy-Based Learning , 2019, J. Chem. Inf. Model..

[32]  Leroy Cronin,et al.  Networking chemical robots for reaction multitasking , 2018, Nature Communications.

[33]  Gianni De Fabritiis,et al.  KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks , 2018, J. Chem. Inf. Model..

[34]  Alán Aspuru-Guzik,et al.  Inverse molecular design using machine learning: Generative models for matter engineering , 2018, Science.

[35]  Connor W. Coley,et al.  Machine Learning in Computer-Aided Synthesis Planning. , 2018, Accounts of chemical research.

[36]  Jacob D. Durrant,et al.  NNScore 2.0: A Neural-Network Receptor–Ligand Scoring Function , 2011, J. Chem. Inf. Model..

[37]  Joseph Gomes,et al.  MoleculeNet: a benchmark for molecular machine learning† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02664a , 2017, Chemical science.

[38]  Sourav Das,et al.  Binding Affinity Prediction with Property-Encoded Shape Distribution Signatures , 2010, J. Chem. Inf. Model..

[39]  Christian Tyrchan,et al.  Matched Molecular Pair Analysis in Short: Algorithms, Applications and Limitations , 2016, Computational and structural biotechnology journal.

[40]  N. Codella,et al.  The role of public challenges and data sets towards algorithm development, trust, and use in clinical practice. , 2019, Seminars in cutaneous medicine and surgery.

[41]  Izhar Wallach,et al.  AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery , 2015, ArXiv.

[42]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[43]  O. Anatole von Lilienfeld,et al.  Quantum Machine Learning in Chemical Compound Space , 2018 .

[44]  Robert Petryszak,et al.  UniChem: a unified chemical structure cross-referencing and identifier tracking system , 2013, Journal of Cheminformatics.

[45]  K. Palczewski,et al.  Exploring a new ligand binding site of G protein-coupled receptors† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c8sc01680a , 2018, Chemical science.

[46]  P D Karp,et al.  Pathway Databases: A Case Study in Computational Symbolic Theories , 2001, Science.

[47]  Gregory W. Kauffman,et al.  Extraction of tacit knowledge from large ADME data sets via pairwise analysis. , 2011, Bioorganic & medicinal chemistry.

[48]  J. Kapur,et al.  Governance of automated image analysis and artificial intelligence analytics in healthcare. , 2019, Clinical Radiology.

[49]  Ruben Abagyan,et al.  Advances in GPCR modeling evaluated by the GPCR Dock 2013 assessment: meeting new challenges. , 2014, Structure.

[50]  Connor W. Coley,et al.  SCScore: Synthetic Complexity Learned from a Reaction Corpus , 2018, J. Chem. Inf. Model..

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

[52]  D. Coomans,et al.  The application of linear discriminant analysis in the diagnosis of thyroid diseases , 1978 .

[53]  Paul Voosen,et al.  The AI detectives. , 2017, Science.

[54]  T. Andrýsek.  Impact of physical properties of formulations on bioavailability of active substance: current and novel drugs with cyclosporine. , 2003, Molecular immunology.

[55]  Rickey E. Carter,et al.  Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram , 2019, Nature Medicine.

[56]  Xiaomin Luo,et al.  Artificial intelligence in drug design , 2018, Science China Life Sciences.

[57]  Naz Chaibakhsh,et al.  Application of Artificial Neural Network for Yield Prediction of Lipase-Catalyzed Synthesis of Dioctyl Adipate , 2009, Applied biochemistry and biotechnology.

[58]  G. Sathe,et al.  Automated synthesis of gene fragments. , 1981, Science.

[59]  Marwin H. S. Segler,et al.  Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction. , 2017, Chemistry.

[60]  Kenneth M Merz,et al.  A Mixed QM/MM Scoring Function to Predict Protein-Ligand Binding Affinity. , 2010, Journal of chemical theory and computation.

[61]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[62]  R. B. Merrifield.  Automated synthesis of peptides. , 1965, Science.

[63]  Johannes Kirchmair,et al.  Hit Dexter 2.0: Machine-Learning Models for the Prediction of Frequent Hitters , 2019, J. Chem. Inf. Model..

[64]  Derek T. Ahneman,et al.  Predicting reaction performance in C–N cross-coupling using machine learning , 2018, Science.

[65]  Leroy Cronin,et al.  Controlling an organic synthesis robot with machine learning to search for new reactivity , 2018, Nature.

[66]  Paul Richardson,et al.  A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow , 2018, Science.

[67]  Fumihito Arai,et al.  Intelligent Image-Activated Cell Sorting , 2018, Cell.

[68]  Jean-Louis Reymond,et al.  Polypharmacology Browser PPB2: Target Prediction Combining Nearest Neighbors with Machine Learning , 2018, J. Chem. Inf. Model..

[69]  Anthony P. F. Cook,et al.  Computer‐aided synthesis design: 40 years on , 2012 .

[70]  Matthias Rarey,et al.  On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment Spaces , 2008, ChemMedChem.

[71]  Conrad C. Huang,et al.  UCSF Chimera, MODELLER, and IMP: an integrated modeling system. , 2012, Journal of structural biology.

[72]  Ruifeng Liu,et al.  vNN Web Server for ADMET Predictions , 2017, Front. Pharmacol..

[73]  Bowen Liu,et al.  Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models , 2017, ACS central science.

[74]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[75]  R. K. Tripathy,et al.  Artificial intelligence-based classification of breast cancer using cellular images , 2014 .

[76]  Heike Schönherr,et al.  Profound methyl effects in drug discovery and a call for new C-H methylation reactions. , 2013, Angewandte Chemie.

[77]  Li Zhang,et al.  Predicting the cytotoxicity of chemicals using ensemble learning methods and molecular fingerprints , 2019, Journal of applied toxicology : JAT.

[78]  Károly Héberger,et al.  Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? , 2015, Journal of Cheminformatics.

[79]  Rita Melo,et al.  Less Exploited GPCRs in Precision Medicine: Targets for Molecular Imaging and Theranostics , 2018, Molecules.

[80]  Qi Wei,et al.  Artificial intelligence in medical imaging of the liver , 2019, World journal of gastroenterology.

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

[82]  Andrew G. Leach,et al.  Matched molecular pairs as a guide in the optimization of pharmaceutical properties; a study of aqueous solubility, plasma protein binding and oral exposure. , 2006, Journal of medicinal chemistry.

[83]  Inho Choi,et al.  Computer Aided Drug Design: Success and Limitations. , 2016, Current pharmaceutical design.

[84]  Sepp Hochreiter,et al.  Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional Networks , 2019, J. Chem. Inf. Model..

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

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

[87]  Pierre Baldi,et al.  Learning to Predict Chemical Reactions , 2011, J. Chem. Inf. Model..

[88]  Felix A Faber,et al.  Machine Learning Energies of 2 Million Elpasolite (ABC_{2}D_{6}) Crystals. , 2015, Physical review letters.

[89]  R. Friesner,et al.  Relative Binding Affinity Prediction of Charge-Changing Sequence Mutations with FEP in Protein–Protein Interfaces , 2019, Journal of molecular biology.

[90]  Yang Li,et al.  PotentialNet for Molecular Property Prediction , 2018, ACS central science.

[91]  Cheng Wang,et al.  Improving scoring‐docking‐screening powers of protein–ligand scoring functions using random forest , 2017, J. Comput. Chem..

[92]  Pijush Samui,et al.  Utilization of a least square support vector machine (LSSVM) for slope stability analysis , 2011 .

[93]  Claudio N. Cavasotto,et al.  Homology modeling in drug discovery: current trends and applications. , 2009, Drug discovery today.

[94]  Leroy Cronin,et al.  Organic synthesis in a modular robotic system driven by a chemical programming language , 2019, Science.

[95]  Yvonne Will,et al.  Toxicology Strategies for Drug Discovery: Present and Future. , 2016, Chemical research in toxicology.

[96]  Philipp Marquetand,et al.  Machine Learning for Organic Synthesis: Are Robots Replacing Chemists? , 2018, Angewandte Chemie.

[97]  Daniel J. Warner,et al.  WizePairZ: A Novel Algorithm to Identify, Encode, and Exploit Matched Molecular Pairs with Unspecified Cores in Medicinal Chemistry , 2010, J. Chem. Inf. Model..

[98]  George Papadatos,et al.  ChEMBL web services: streamlining access to drug discovery data and utilities , 2015, Nucleic Acids Res..

[99]  Tomas Mikolov,et al.  Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets , 2015, NIPS.

[100]  Andy Liaw,et al.  Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships , 2016, J. Chem. Inf. Model..

[101]  S. Taranejoo,et al.  A stacked neural network approach for yield prediction of propylene polymerization , 2009 .

[102]  Piotr Dittwald,et al.  Efficient Syntheses of Diverse, Medicinally Relevant Targets Planned by Computer and Executed in the Laboratory , 2018 .

[103]  Jed A. Fuhrman,et al.  Proteorhodopsins: an array of physiological roles? , 2008, Nature Reviews Microbiology.