From machine learning to deep learning: progress in machine intelligence for rational drug discovery.

Machine intelligence, which is normally presented as artificial intelligence, refers to the intelligence exhibited by computers. In the history of rational drug discovery, various machine intelligence approaches have been applied to guide traditional experiments, which are expensive and time-consuming. Over the past several decades, machine-learning tools, such as quantitative structure-activity relationship (QSAR) modeling, were developed that can identify potential biological active molecules from millions of candidate compounds quickly and cheaply. However, when drug discovery moved into the era of 'big' data, machine learning approaches evolved into deep learning approaches, which are a more powerful and efficient way to deal with the massive amounts of data generated from modern drug discovery approaches. Here, we summarize the history of machine learning and provide insight into recently developed deep learning approaches and their applications in rational drug discovery. We suggest that this evolution of machine intelligence now provides a guide for early-stage drug design and discovery in the current big data era.

[1]  S. Nie,et al.  Activity Prediction and Molecular Mechanism of Bovine Blood Derived Angiotensin I-Converting Enzyme Inhibitory Peptides , 2015, PloS one.

[2]  Ramesh Kakarla,et al.  Structure-activity relationship (SAR) optimization of 6-(indol-2-yl)pyridine-3-sulfonamides: identification of potent, selective, and orally bioavailable small molecules targeting hepatitis C (HCV) NS4B. , 2014, Journal of medicinal chemistry.

[3]  Mutasem O. Taha,et al.  Combining docking-based comparative intermolecular contacts analysis and k-nearest neighbor correlation for the discovery of new check point kinase 1 inhibitors , 2015, Journal of Computer-Aided Molecular Design.

[4]  Harinder Singh,et al.  QSAR based model for discriminating EGFR inhibitors and non-inhibitors using Random forest , 2015, Biology Direct.

[5]  Marlene T. Kim,et al.  Developing Enhanced Blood–Brain Barrier Permeability Models: Integrating External Bio-Assay Data in QSAR Modeling , 2015, Pharmaceutical Research.

[6]  Stephen R. Johnson,et al.  The Trouble with QSAR (or How I Learned To Stop Worrying and Embrace Fallacy) , 2008, J. Chem. Inf. Model..

[7]  Shikha Gupta,et al.  Estimating sensory irritation potency of volatile organic chemicals using QSARs based on decision tree methods for regulatory purpose , 2015, Ecotoxicology.

[8]  Alexander Golbraikh,et al.  QSAR Modeling of the Blood–Brain Barrier Permeability for Diverse Organic Compounds , 2008, Pharmaceutical Research.

[9]  Daniel Neagu,et al.  Using random forest and decision tree models for a new vehicle prediction approach in computational toxicology , 2016, Soft Comput..

[10]  Xue-wen Chen,et al.  Big Data Deep Learning: Challenges and Perspectives , 2014, IEEE Access.

[11]  Marcin J. Skwark,et al.  3D Deep Learning for Biological Function Prediction from Physical Fields , 2017, 2020 International Conference on 3D Vision (3DV).

[12]  Asad U Khan,et al.  Structure based virtual screening to discover putative drug candidates: necessary considerations and successful case studies. , 2015, Methods.

[13]  Robert P. Sheridan,et al.  Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships , 2015, J. Chem. Inf. Model..

[14]  Nitin S. Sapre,et al.  In silico de novo design of novel NNRTIs: a bio-molecular modelling approach , 2015 .

[15]  Hao Zhu,et al.  Design, synthesis and experimental validation of novel potential chemopreventive agents using random forest and support vector machine binary classifiers , 2014, Journal of Computer-Aided Molecular Design.

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

[17]  Jakub M. Tomczak,et al.  Interaction prediction in structure-based virtual screening using deep learning , 2018, Comput. Biol. Medicine.

[18]  J. Ware,et al.  First-in-Human Phase I Study of Pictilisib (GDC-0941), a Potent Pan–Class I Phosphatidylinositol-3-Kinase (PI3K) Inhibitor, in Patients with Advanced Solid Tumors , 2014, Clinical Cancer Research.

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

[20]  Juan Li,et al.  Using Deep Learning for Compound Selectivity Prediction. , 2016, Current computer-aided drug design.

[21]  Sungroh Yoon,et al.  DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction , 2017, BCB.

[22]  Hao Zhu,et al.  MCASE study of the multidrug resistance reversal activity of propafenone analogs , 2003, J. Comput. Aided Mol. Des..

[23]  Yu Wang,et al.  A comparative study of family-specific protein–ligand complex affinity prediction based on random forest approach , 2015, Journal of Computer-Aided Molecular Design.

[24]  P. Mayer,et al.  Can highly hydrophobic organic substances cause aquatic baseline toxicity and can they contribute to mixture toxicity? , 2006, Environmental toxicology and chemistry.

[25]  Marlene T. Kim,et al.  Critical Evaluation of Human Oral Bioavailability for Pharmaceutical Drugs by Using Various Cheminformatics Approaches , 2013, Pharmaceutical Research.

[26]  Antonio Lavecchia,et al.  Machine-learning approaches in drug discovery: methods and applications. , 2015, Drug discovery today.

[27]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[28]  Taravat Ghafourian,et al.  Decision trees to characterise the roles of permeability and solubility on the prediction of oral absorption. , 2015, European journal of medicinal chemistry.

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

[30]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[31]  Abhigyan Nath,et al.  Identification of human drug targets using machine-learning algorithms , 2015, Comput. Biol. Medicine.

[32]  George Hripcsak,et al.  Improving Detection of Arrhythmia Drug-Drug Interactions in Pharmacovigilance Data through the Implementation of Similarity-Based Modeling , 2015, PloS one.

[33]  Ming Wen,et al.  Deep-Learning-Based Drug-Target Interaction Prediction. , 2017, Journal of proteome research.

[34]  Andreas Bender,et al.  Recognizing Pitfalls in Virtual Screening: A Critical Review , 2012, J. Chem. Inf. Model..

[35]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[36]  Alexander Tropsha,et al.  Quantitative structure-activity relationship modeling of rat acute toxicity by oral exposure. , 2009, Chemical research in toxicology.

[37]  Marlene T. Kim,et al.  Predicting chemical ocular toxicity using a combinatorial QSAR approach. , 2012, Chemical research in toxicology.

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

[39]  Tao Wang,et al.  Quantitative structure–activity relationship: promising advances in drug discovery platforms , 2015, Expert opinion on drug discovery.

[40]  Neerja Kaushik-Basu,et al.  Inhibitors for the hepatitis C virus RNA polymerase explored by SAR with advanced machine learning methods. , 2013, Bioorganic & medicinal chemistry.

[41]  Sergey Plis,et al.  Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data. , 2016, Molecular pharmaceutics.

[42]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[43]  S. Joshua Swamidass,et al.  Modeling Epoxidation of Drug-like Molecules with a Deep Machine Learning Network , 2015, ACS central science.

[44]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[45]  Gerald M. Maggiora,et al.  On Outliers and Activity Cliffs-Why QSAR Often Disappoints , 2006, J. Chem. Inf. Model..

[46]  Mandana Behbahani,et al.  Computational prediction of anti HIV‐1 peptides and in vitro evaluation of anti HIV‐1 activity of HIV‐1 P24‐derived peptides , 2015, Journal of peptide science : an official publication of the European Peptide Society.

[47]  F. Metzger,et al.  Specific Correction of Alternative Survival Motor Neuron 2 Splicing by Small Molecules: Discovery of a Potential Novel Medicine To Treat Spinal Muscular Atrophy. , 2016, Journal of medicinal chemistry.

[48]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[49]  Narayanan Surendran,et al.  Implementation of an ADME enabling selection and visualization tool for drug discovery. , 2004, Journal of pharmaceutical sciences.

[50]  S. Robinson,et al.  CCT244747 Is a Novel Potent and Selective CHK1 Inhibitor with Oral Efficacy Alone and in Combination with Genotoxic Anticancer Drugs , 2012, Clinical Cancer Research.

[51]  George Hripcsak,et al.  3D Pharmacophoric Similarity improves Multi Adverse Drug Event Identification in Pharmacovigilance , 2015, Scientific Reports.

[52]  F Torrens,et al.  QuBiLs-MAS method in early drug discovery and rational drug identification of antifungal agents , 2015, SAR and QSAR in environmental research.

[53]  May D. Wang,et al.  DeeperBind: Enhancing Prediction of Sequence Specificities of DNA Binding Proteins , 2017 .

[54]  Alex Zhavoronkov,et al.  Applications of Deep Learning in Biomedicine. , 2016, Molecular pharmaceutics.

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

[56]  E. LaVoie,et al.  Bioisosterism: A Rational Approach in Drug Design. , 1996, Chemical reviews.