Title: Artificial intelligence in the prediction of protein–ligand interactions: recent advances and future directions

Journal Article · · Briefings in Bioinformatics
ORCiD logo [1];  [2];  [3]; ORCiD logo [1]
  1. Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, 65211, USA
  2. Department of Biochemistry, University of Missouri, Columbia, MO, 65211, USA
  3. Department of Biochemistry, University of Missouri, Columbia, MO, 65211, USA, Department of Chemistry, University of Missouri, Columbia, MO, 65211, USA
+ Show Author Affiliations

Abstract New drug production, from target identification to marketing approval, takes over 12 years and can cost around $2.6 billion. Furthermore, the COVID-19 pandemic has unveiled the urgent need for more powerful computational methods for drug discovery. Here, we review the computational approaches to predicting protein–ligand interactions in the context of drug discovery, focusing on methods using artificial intelligence (AI). We begin with a brief introduction to proteins (targets), ligands (e.g. drugs) and their interactions for nonexperts. Next, we review databases that are commonly used in the domain of protein–ligand interactions. Finally, we survey and analyze the machine learning (ML) approaches implemented to predict protein–ligand binding sites, ligand-binding affinity and binding pose (conformation) including both classical ML algorithms and recent deep learning methods. After exploring the correlation between these three aspects of protein–ligand interaction, it has been proposed that they should be studied in unison. We anticipate that our review will aid exploration and development of more accurate ML-based prediction strategies for studying protein–ligand interactions.

Research Organization:
Donald Danforth Plant Science Center, St. Louis, MO (United States); University of Missouri, Columbia, MO (United States)
Sponsoring Organization:
National Institutes of Health (NIH); National Science Foundation (NSF); USDOE; USDOE Advanced Research Projects Agency - Energy (ARPA-E); USDOE Office of Science (SC), Biological and Environmental Research (BER)
Grant/Contract Number:
AR0001213; SC0020400; SC0021303
OSTI ID:
1833439
Journal Information:
Briefings in Bioinformatics, Journal Name: Briefings in Bioinformatics Journal Issue: 1 Vol. 23; ISSN 1467-5463
Publisher:
Oxford University PressCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (131)

PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints journal December 2010
Computational Prediction of DrugTarget Interactions Using Chemical, Biological, and Network Features journal September 2014
A Random Forest Model for Predicting Allosteric and Functional Sites on Proteins journal January 2016
Toward a “Structural BLAST”: Using structural relationships to infer function: Toward a “Structural BLAST” journal February 2013
Ligand binding to proteins: The binding landscape model journal October 1997
Improved protein-ligand docking using GOLD journal August 2003
Binding MOAD (Mother Of All Databases) journal June 2005
Combination of deep neural network with attention mechanism enhances the explainability of protein contact prediction journal February 2021
Protein-ligand interaction databases: advanced tools to mine activity data and interactions on a structural level: Protein-ligand interaction databases journal July 2014
Protein secondary structure prediction based on position-specific scoring matrices 1 1Edited by G. Von Heijne journal September 1999
Knowledge-based scoring function to predict protein-ligand interactions journal January 2000
Two algorithms for constructing a Delaunay triangulation journal June 1980
Docking and scoring with ICM: the benchmarking results and strategies for improvement journal May 2012
FRED and HYBRID docking performance on standardized datasets journal June 2012
A comparative study of family-specific protein–ligand complex affinity prediction based on random forest approach journal December 2014
Predicting binding poses and affinities for protein - ligand complexes in the 2015 D3R Grand Challenge using a physical model with a statistical parameter estimation journal September 2016
Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges journal August 2018
Computational methods and tools for binding site recognition between proteins and small molecules: from classical geometrical approaches to modern machine learning strategies journal October 2019
Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches journal December 2020
Software for molecular docking: a review journal January 2017
POCKET: A computer graphies method for identifying and displaying protein cavities and their surrounding amino acids journal December 1992
SURFNET: A program for visualizing molecular surfaces, cavities, and intermolecular interactions journal October 1995
Effect of data standardization on neural network training journal August 1996
Identification and mapping of small-molecule binding sites in proteins: computational tools for structure-based drug design journal March 2002
Ligand binding: functional site location, similarity and docking journal June 2003
LIGSITE: automatic and efficient detection of potential small molecule-binding sites in proteins journal December 1997
Structure-based virtual screening: an overview journal October 2002
Machine learning and ligand binding predictions: A review of data, methods, and obstacles journal June 2020
Supervised machine learning techniques to predict binding affinity. A study for cyclin-dependent kinase 2 journal December 2017
Development of a machine-learning model to predict Gibbs free energy of binding for protein-ligand complexes journal September 2018
Exploring the computational methods for protein-ligand binding site prediction journal January 2020
A review on compound-protein interaction prediction methods: Data, format, representation and model journal January 2021
Druggable pockets and binding site centric chemical space: a paradigm shift in drug discovery journal August 2010
Innovation in the pharmaceutical industry: New estimates of R&D costs journal May 2016
COVID-19: Discovery, diagnostics and drug development journal January 2021
CryptoSite: Expanding the Druggable Proteome by Characterization and Prediction of Cryptic Binding Sites journal February 2016
A comparison of ligand based virtual screening methods and application to corticotropin releasing factor 1 receptor journal June 2009
Extreme learning machine: Theory and applications journal December 2006
Structure-based systems biology for analyzing off-target binding journal April 2011
Binding site comparison for function prediction and pharmaceutical discovery journal April 2014
Drug discovery and development: Role of basic biological research journal November 2017
Designing ligands to bind proteins journal November 2005
Binding Affinity Prediction by Pairwise Function Based on Neural Network journal April 2020
Baseline Model for Predicting Protein–Ligand Unbinding Kinetics through Machine Learning journal November 2020
Improved Protein–Ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference journal March 2021
Ollivier Persistent Ricci Curvature-Based Machine Learning for the Protein–Ligand Binding Affinity Prediction journal March 2021
Protein–Ligand Scoring with Convolutional Neural Networks journal April 2017
K DEEP : Protein–Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks journal January 2018
Pyrimidine-Based Inhibitors of Dynamin I GTPase Activity: Competitive Inhibition at the Pleckstrin Homology Domain journal December 2016
OnionNet: a Multiple-Layer Intermolecular-Contact-Based Convolutional Neural Network for Protein–Ligand Binding Affinity Prediction journal September 2019
graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes journal March 2020
Predicting Protein−Ligand Binding Affinities Using Novel Geometrical Descriptors and Machine-Learning Methods journal January 2004
Physics-Based Scoring of Protein−Ligand Complexes:  Enrichment of Known Inhibitors in Large-Scale Virtual Screening journal November 2005
SFCscore RF : A Random Forest-Based Scoring Function for Improved Affinity Prediction of Protein–Ligand Complexes journal June 2013
Binding Affinity Prediction for Protein–Ligand Complexes Based on β Contacts and B Factor journal November 2013
Structural Studies of the Resistance of Influenza Virus Neuramindase to Inhibitors journal April 2002
Glide:  A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking Accuracy journal March 2004
The PDBbind Database:  Methodologies and Updates journal June 2005
Chemical genetics: ligand-based discovery of gene function journal November 2000
Trends in Risks Associated With New Drug Development: Success Rates for Investigational Drugs journal February 2010
Chemical space and biology journal December 2004
Docking and scoring in virtual screening for drug discovery: methods and applications journal November 2004
The druggable genome journal September 2002
Highly accurate protein structure prediction with AlphaFold journal July 2021
Improving detection of protein-ligand binding sites with 3D segmentation journal March 2020
A machine learning approach towards the prediction of protein–ligand binding affinity based on fundamental molecular properties journal January 2018
A threading-based method (FINDSITE) for ligand-binding site prediction and functional annotation journal December 2007
Artificial intelligence in drug discovery: recent advances and future perspectives journal April 2021
Thermodynamics of Protein–Ligand Interactions: History, Presence, and Future Aspects journal January 2004
FINDSITE: a combined evolution/structure-based approach to protein function prediction journal March 2009
Drug–target interaction prediction: databases, web servers and computational models journal August 2015
Protein–ligand binding residue prediction enhancement through hybrid deep heterogeneous learning of sequence and structure data journal February 2020
DeepSurf: a surface-based deep learning approach for the prediction of ligand binding sites on proteins journal January 2021
Prediction of drug-target interaction networks from the integration of chemical and genomic spaces journal June 2008
Predicting small ligand binding sites in proteins using backbone structure journal October 2008
Supervised prediction of drug–target interactions using bipartite local models journal July 2009
LIBRUS: combined machine learning and homology information for sequence-based ligand-binding residue prediction journal September 2009
EasyMIFs and SiteHound: a toolkit for the identification of ligand-binding sites in protein structures journal September 2009
Roll: a new algorithm for the detection of protein pockets and cavities with a rolling probe sphere journal October 2009
DoGSiteScorer: a web server for automatic binding site prediction, analysis and druggability assessment journal May 2012
Predicting drug-target interactions using restricted Boltzmann machines journal June 2013
Protein–ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment journal August 2013
Improved protein–ligand binding affinity prediction by using a curvature-dependent surface-area model journal February 2014
Automatic generation of bioinformatics tools for predicting protein–ligand binding sites journal November 2015
Recognizing metal and acid radical ion-binding sites by integrating ab initio modeling with template-based transferals journal July 2016
Development and evaluation of a deep learning model for protein–ligand binding affinity prediction journal May 2018
DeepDTA: deep drug–target binding affinity prediction journal September 2018
From genomics to chemical genomics: new developments in KEGG journal January 2006
BindingDB: a web-accessible database of experimentally determined protein-ligand binding affinities journal January 2007
LigASite a database of biologically relevant binding sites in proteins with known apo-structures journal December 2007
Binding MOAD, a high-quality protein ligand database journal December 2007
BioLiP: a semi-manually curated database for biologically relevant ligand–protein interactions journal October 2012
Recent improvements to Binding MOAD: a resource for protein–ligand binding affinities and structures journal November 2014
sc-PDB: a 3D-database of ligandable binding sites—10 years on journal October 2014
PubChem Substance and Compound databases journal September 2015
COACH-D: improved protein–ligand binding sites prediction with refined ligand-binding poses through molecular docking journal May 2018
PrankWeb: a web server for ligand binding site prediction and visualization journal May 2019
Twilight zone of protein sequence alignments journal February 1999
A novel statistical ligand-binding site predictor: application to ATP-binding sites journal February 2005
Improving quality of ligand-binding site prediction with Bayesian optimization conference November 2017
Designing Template-Free Predictor for Targeting Protein-Ligand Binding Sites with Classifier Ensemble and Spatial Clustering journal July 2013
Predicting Protein-Ligand Binding Site Using Support Vector Machine with Protein Properties journal November 2013
A Sequence-Based Dynamic Ensemble Learning System for Protein Ligand-Binding Site Prediction journal September 2016
Multiple diverse ligands binding at a single protein site: A matter of pre-existing populations journal February 2002
Principles of early drug discovery: Principles of early drug discovery journal February 2011
Computational Methods in Drug Discovery journal December 2013
Protein Metal Binding Residue Prediction Based on Neural Networks journal February 2005
Cscore: a Simple yet Effective Scoring Function for Protein–Ligand Binding Affinity Prediction Using Modified cmac Learning Architecture journal December 2011
Calculation of Protein-Ligand Binding Affinities journal June 2007
Development of a Machine Learning Method to Predict Membrane Protein-Ligand Binding Residues Using Basic Sequence Information journal January 2015
Improvements to Platt's SMO Algorithm for SVM Classifier Design journal March 2001
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity journal January 2021
Identification of ATP binding residues of a protein from its primary sequence journal January 2009
LigandRFs: random forest ensemble to identify ligand-binding residues from sequence information alone journal December 2014
Multicore and GPU algorithms for Nussinov RNA folding journal July 2014
BgN-Score and BsN-Score: Bagging and boosting based ensemble neural networks scoring functions for accurate binding affinity prediction of protein-ligand complexes journal February 2015
Machine-learning scoring functions for identifying native poses of ligands docked to known and novel proteins journal April 2015
PocketPicker: analysis of ligand binding-sites with shape descriptors journal March 2007
Protein ligand-specific binding residue predictions by an ensemble classifier journal November 2016
Predicting protein-ligand binding residues with deep convolutional neural networks journal February 2019
Pocket-Based Drug Design: Exploring Pocket Space journal November 2012
Integrating data selection and extreme learning machine to predict protein-ligand binding site journal January 2016
ANGLOR: A Composite Machine-Learning Algorithm for Protein Backbone Torsion Angle Prediction journal October 2008
Beta Atomic Contacts: Identifying Critical Specific Contacts in Protein Binding Interfaces journal April 2013
Virtual screening with AutoDock: theory and practice journal April 2010
Improved Prediction of Protein Ligand-Binding Sites Using Random Forests journal December 2011
Deep Learning in Drug Target Interaction Prediction: Current and Future Perspectives journal April 2021
Pred-binding: large-scale protein–ligand binding affinity prediction journal February 2016
RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features journal December 2020
AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks journal November 2020
Artificial Intelligence in Drug Design journal October 2018

Similar Records

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
binding affinity
binding pose
binding site
deep learning
drug discovery
machine learning
protein–ligand interaction