InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein-Ligand Interaction Predictions.

Accurate quantification of protein-ligand interactions remains a key challenge to structure-based drug design. However, traditional machine learning (ML)-based methods based on handcrafted descriptors, one-dimensional protein sequences, and/or two-dimensional graph representations limit their capability to learn the generalized molecular interactions in 3D space. Here, we proposed a novel deep graph representation learning framework named InteractionGraphNet (IGN) to learn the protein-ligand interactions from the 3D structures of protein-ligand complexes. In IGN, two independent graph convolution modules were stacked to sequentially learn the intramolecular and intermolecular interactions, and the learned intermolecular interactions can be efficiently used for subsequent tasks. Extensive binding affinity prediction, large-scale structure-based virtual screening, and pose prediction experiments demonstrated that IGN achieved better or competitive performance against other state-of-the-art ML-based baselines and docking programs. More importantly, such state-of-the-art performance was proven from the successful learning of the key features in protein-ligand interactions instead of just memorizing certain biased patterns from data.

[1]  Xavier Barril,et al.  Extended connectivity interaction features: improving binding affinity prediction through chemical description , 2020, Bioinform..

[2]  Shengyu Zhang,et al.  TrimNet: learning molecular representation from triplet messages for biomedicine , 2020, Briefings Bioinform..

[3]  Xiaomin Luo,et al.  Pushing the boundaries of molecular representation for drug discovery with graph attention mechanism. , 2020, Journal of medicinal chemistry.

[4]  Lei Xu,et al.  DeepAtomicCharge: a new graph convolutional network-based architecture for accurate prediction of atomic charges , 2020, Briefings Bioinform..

[5]  Gisbert Schneider,et al.  Virtual Screening and Design with Machine Intelligence Applied to Pim‐1 Kinase Inhibitors , 2020, Molecular informatics.

[6]  Gisbert Schneider,et al.  Drug discovery with explainable artificial intelligence , 2020, Nature Machine Intelligence.

[7]  Chen-Yang Jia,et al.  Graph attention convolutional neural network model for chemical poisoning of honey bees' prediction. , 2020, Science bulletin.

[8]  Gaoang Wang,et al.  Beware of the generic machine learning-based scoring functions in structure-based virtual screening , 2020, Briefings Bioinform..

[9]  Xiaofeng Wang,et al.  Drug–target affinity prediction using graph neural network and contact maps , 2020, RSC advances.

[10]  Derek Jones,et al.  Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference , 2020, J. Chem. Inf. Model..

[11]  Ce Zhang,et al.  RosENet: Improving Binding Affinity Prediction by Leveraging Molecular Mechanics Energies with an Ensemble of 3D Convolutional Neural Networks , 2020, J. Chem. Inf. Model..

[12]  Derek Jones,et al.  Binding Affinity Prediction by Pairwise Function Based on Neural Network , 2020, J. Chem. Inf. Model..

[13]  Evan N. Feinberg,et al.  Improvement in ADMET Prediction with Multitask Deep Featurization. , 2020, Journal of medicinal chemistry.

[14]  Didier Rognan,et al.  LIT-PCBA: An Unbiased Data Set for Machine Learning and Virtual Screening , 2020, J. Chem. Inf. Model..

[15]  Dan Zhao,et al.  MONN: A Multi-objective Neural Network for Predicting Compound-Protein Interactions and Affinities , 2020, Cell Systems.

[16]  Emma J. Chory,et al.  A Deep Learning Approach to Antibiotic Discovery , 2020, Cell.

[17]  Nathan Brown,et al.  Dataset Augmentation Allows Deep Learning-Based Virtual Screening To Better Generalize To Unseen Target Classes, And Highlight Important Binding Interactions , 2020, bioRxiv.

[18]  Jincai Yang,et al.  Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets , 2020, Frontiers in Pharmacology.

[19]  Pascal Friederich,et al.  Neural Message Passing on High Order Paths , 2020, Mach. Learn. Sci. Technol..

[20]  Joseph A Morrone,et al.  Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach , 2019, J. Chem. Inf. Model..

[21]  Alán Aspuru-Guzik,et al.  Deep learning enables rapid identification of potent DDR1 kinase inhibitors , 2019, Nature Biotechnology.

[22]  Seongok Ryu,et al.  A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification , 2019, Chemical science.

[23]  G. Schneider,et al.  Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery. , 2019, Chemical reviews.

[24]  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..

[25]  Chao Shen,et al.  From machine learning to deep learning: Advances in scoring functions for protein–ligand docking , 2019, WIREs Computational Molecular Science.

[26]  Guo-Wei Wei,et al.  AGL-Score: Algebraic Graph Learning Score for Protein-Ligand Binding Scoring, Ranking, Docking, and Screening , 2019, J. Chem. Inf. Model..

[27]  Yuguang Mu,et al.  OnionNet: a Multiple-Layer Intermolecular-Contact-Based Convolutional Neural Network for Protein–Ligand Binding Affinity Prediction , 2019, ACS omega.

[28]  Jiayu Zhou,et al.  Graph convolutional networks for computational drug development and discovery , 2019, Briefings Bioinform..

[29]  Yongjian Li,et al.  Predicting drug–protein interaction using quasi-visual question answering system , 2019, Nature Machine Intelligence.

[30]  Viktor Hornak,et al.  Hidden bias in the DUD-E dataset leads to misleading performance of deep learning in structure-based virtual screening , 2019, PloS one.

[31]  Matthias Rarey,et al.  In Need of Bias Control: Evaluating Chemical Data for Machine Learning in Structure-Based Virtual Screening , 2019, J. Chem. Inf. Model..

[32]  Yan Li,et al.  Comparative Assessment of Scoring Functions: The CASF-2016 Update , 2018, J. Chem. Inf. Model..

[33]  Russ B. Altman,et al.  Graph Convolutional Neural Networks for Predicting Drug-Target Interactions , 2018, bioRxiv.

[34]  Hojung Nam,et al.  DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences , 2018, PLoS Comput. Biol..

[35]  Maciej Wójcikowski,et al.  Development of a protein–ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions , 2018, Bioinform..

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

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

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

[39]  Guo-Wei Wei,et al.  Integration of element specific persistent homology and machine learning for protein‐ligand binding affinity prediction , 2018, International journal for numerical methods in biomedical engineering.

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

[41]  Marta M. Stepniewska-Dziubinska,et al.  Development and evaluation of a deep learning model for protein–ligand binding affinity prediction , 2017, Bioinform..

[42]  Guo-Wei Wei,et al.  Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening , 2017, PLoS Comput. Biol..

[43]  Guo-Wei Wei,et al.  Rigidity Strengthening: A Mechanism for Protein-Ligand Binding , 2017, J. Chem. Inf. Model..

[44]  Pedro J. Ballester,et al.  Performance of machine-learning scoring functions in structure-based virtual screening , 2017, Scientific Reports.

[45]  Yang Li,et al.  Structural and Sequence Similarity Makes a Significant Impact on Machine-Learning-Based Scoring Functions for Protein-Ligand Interactions , 2017, J. Chem. Inf. Model..

[46]  Guo-Wei Wei,et al.  TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions , 2017, PLoS Comput. Biol..

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

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

[49]  Didier Rognan,et al.  Beware of Machine Learning-Based Scoring Functions - On the Danger of Developing Black Boxes , 2014, J. Chem. Inf. Model..

[50]  Tom L. Blundell,et al.  Does a More Precise Chemical Description of Protein–Ligand Complexes Lead to More Accurate Prediction of Binding Affinity? , 2014, J. Chem. Inf. Model..

[51]  Frank M. Boeckler,et al.  Evaluation and Optimization of Virtual Screening Workflows with DEKOIS 2.0 - A Public Library of Challenging Docking Benchmark Sets , 2013, J. Chem. Inf. Model..

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

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

[54]  John B. O. Mitchell,et al.  A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking , 2010, Bioinform..

[55]  J. Skolnick,et al.  Scoring function for automated assessment of protein structure template quality , 2004, Proteins.

[56]  D. Koes,et al.  Protein-Ligand Scoring with Convolutional Neural Networks , 2017, J. Chem. Inf. Model..

[57]  M. Wong,et al.  Supplementary information for “Improving AutoDock Vina using Random Forest: the growing accuracy of binding affinity prediction by the effective exploitation of larger data sets” , 2015 .