MONN: A Multi-objective Neural Network for Predicting Compound-Protein Interactions and Affinities

Summary Computational approaches for understanding compound-protein interactions (CPIs) can greatly facilitate drug development. Recently, a number of deep-learning-based methods have been proposed to predict binding affinities and attempt to capture local interaction sites in compounds and proteins through neural attentions (i.e., neural network architectures that enable the interpretation of feature importance). Here, we compiled a benchmark dataset containing the inter-molecular non-covalent interactions for more than 10,000 compound-protein pairs and systematically evaluated the interpretability of neural attentions in existing models. We also developed a multi-objective neural network, called MONN, to predict both non-covalent interactions and binding affinities between compounds and proteins. Comprehensive evaluation demonstrated that MONN can successfully predict the non-covalent interactions between compounds and proteins that cannot be effectively captured by neural attentions in previous prediction methods. Moreover, MONN outperforms other state-of-the-art methods in predicting binding affinities. Source code for MONN is freely available for download at https://github.com/lishuya17/MONN .

[1]  Narcis Fernandez-Fuentes,et al.  Small molecule inhibitors of RAS-effector protein interactions derived using an intracellular antibody fragment , 2018, Nature Communications.

[2]  Michael Schroeder,et al.  PLIP: fully automated protein–ligand interaction profiler , 2015, Nucleic Acids Res..

[3]  Jianyang Zeng,et al.  DeepCPI: A Deep Learning-based Framework for Large-scale in silico Drug Screening , 2019, Genom. Proteom. Bioinform..

[4]  Juho Rousu,et al.  Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors , 2017, PLoS Comput. Biol..

[5]  Freddie R Salsbury,et al.  Molecular dynamics simulations of protein dynamics and their relevance to drug discovery. , 2010, Current opinion in pharmacology.

[6]  Bowen Zhou,et al.  Attentive Pooling Networks , 2016, ArXiv.

[7]  Michael K. Gilson,et al.  BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology , 2015, Nucleic Acids Res..

[8]  Ping Zhang,et al.  Interpretable Drug Target Prediction Using Deep Neural Representation , 2018, IJCAI.

[9]  Katsuhiko Ishiguro,et al.  Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks , 2019, ArXiv.

[10]  David Ryan Koes,et al.  Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking Exercise , 2013, J. Chem. Inf. Model..

[11]  Amanda J Price,et al.  Fragment-based drug discovery and its application to challenging drug targets. , 2017, Essays in biochemistry.

[12]  Jun Sese,et al.  Compound‐protein interaction prediction with end‐to‐end learning of neural networks for graphs and sequences , 2018, Bioinform..

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[15]  James Inglese,et al.  High Throughput Screening (HTS) Techniques: Applications in Chemical Biology , 2008 .

[16]  Tapio Pahikkala,et al.  Fast Kronecker Product Kernel Methods via Generalized Vec Trick , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Yongdong Zhang,et al.  Drug-target interaction prediction: databases, web servers and computational models , 2016, Briefings Bioinform..

[18]  K. Wüthrich.  Protein structure determination in solution by nuclear magnetic resonance spectroscopy. , 1989, Science.

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

[20]  Arzucan Özgür,et al.  DeepDTA: deep drug–target binding affinity prediction , 2018, Bioinform..

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

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

[23]  Di Wu,et al.  DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks , 2018, bioRxiv.

[24]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[25]  Sjors H W Scheres,et al.  Cryo-EM: A Unique Tool for the Visualization of Macromolecular Complexity. , 2015, Molecular cell.

[26]  Jung-Woo Ha,et al.  Dual Attention Networks for Multimodal Reasoning and Matching , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[28]  Ulrich Rester,et al.  From virtuality to reality - Virtual screening in lead discovery and lead optimization: a medicinal chemistry perspective. , 2008, Current opinion in drug discovery & development.

[29]  António J. M. Ribeiro,et al.  Protein-ligand docking in the new millennium--a retrospective of 10 years in the field. , 2013, Current medicinal chemistry.

[30]  Russ B Altman,et al.  Graph Convolutional Neural Networks for Predicting Drug-Target Interactions , 2019, J. Chem. Inf. Model..

[31]  J. Gower,et al.  Minimum Spanning Trees and Single Linkage Cluster Analysis , 1969 .

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

[33]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[34]  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..

[35]  Daniel Kuhn,et al.  Combining Global and Local Measures for Structure-Based Druggability Predictions , 2012, J. Chem. Inf. Model..

[36]  Gebhard F. X. Schertler,et al.  Ligand channel in pharmacologically stabilized rhodopsin , 2018, Proceedings of the National Academy of Sciences.

[37]  Michael M. Mysinger,et al.  Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking , 2012, Journal of medicinal chemistry.

[38]  Renxiao Wang,et al.  The PDBbind database: collection of binding affinities for protein-ligand complexes with known three-dimensional structures. , 2004, Journal of medicinal chemistry.

[39]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[40]  I. Kola,et al.  Can the pharmaceutical industry reduce attrition rates? , 2004, Nature Reviews Drug Discovery.

[41]  Seongok Ryu,et al.  Predicting Drug-Target Interaction Using a Novel Graph Neural Network with 3D Structure-Embedded Graph Representation , 2019, J. Chem. Inf. Model..

[42]  S. Henikoff,et al.  Amino acid substitution matrices from protein blocks. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[43]  Li Xing,et al.  Dual Inhibition of TYK2 and JAK1 for the Treatment of Autoimmune Diseases: Discovery of (( S)-2,2-Difluorocyclopropyl)((1 R,5 S)-3-(2-((1-methyl-1 H-pyrazol-4-yl)amino)pyrimidin-4-yl)-3,8-diazabicyclo[3.2.1]octan-8-yl)methanone (PF-06700841). , 2018, Journal of medicinal chemistry.

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

[45]  Renxiao Wang,et al.  The PDBbind database: methodologies and updates. , 2005, Journal of medicinal chemistry.

[46]  Richard D. Taylor,et al.  Improved protein–ligand docking using GOLD , 2003, Proteins.

[47]  D I Svergun,et al.  Determination of domain structure of proteins from X-ray solution scattering. , 2001, Biophysical journal.

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