Machine-learning approaches in drug discovery: methods and applications.

During the past decade, virtual screening (VS) has evolved from traditional similarity searching, which utilizes single reference compounds, into an advanced application domain for data mining and machine-learning approaches, which require large and representative training-set compounds to learn robust decision rules. The explosive growth in the amount of public domain-available chemical and biological data has generated huge effort to design, analyze, and apply novel learning methodologies. Here, I focus on machine-learning techniques within the context of ligand-based VS (LBVS). In addition, I analyze several relevant VS studies from recent publications, providing a detailed view of the current state-of-the-art in this field and highlighting not only the problematic issues, but also the successes and opportunities for further advances.

• Publication year

  2015

• Venue

  Drug Discovery Today

• Publication date

  2015-03-01

• Fields of study

  Chemistry, Medicine, Computer Science

• Identifiers
  DOI 10.1016/j.drudis.2014.10.012PMID 25448759
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Pattern Classification

  2021cited by this paper
• Machine Learning Methods in Chemoinformatics for Drug Discovery

  2014cited by this paper
• Activity cliffs in drug discovery: Dr Jekyll or Mr Hyde?

  2014cited by this paper
• BASICS OF ARTIFICIAL NEURAL NETWORK

  2014cited by this paper
• Active learning with support vector machines

  2014cited by this paper
• Machine learning methods in chemoinformatics

  2014cited by this paper
• Virtual screening strategies in drug discovery: a critical review.

  2013cited by this paper
• Computational Profiling of Bioactive Compounds Using a Target-Dependent Composite Workflow

  2013cited by this paper
• In Silico Target Predictions: Defining a Benchmarking Data Set and Comparison of Performance of the Multiclass Naïve Bayes and Parzen-Rosenblatt Window

  2013cited by this paper
• A multidimensional analysis of machine learning methods performance in the classification of bioactive compounds

  2013cited by this paper
• EnzML: multi-label prediction of enzyme classes using InterPro signatures

  2012cited by this paper
• Prediction of Activity Cliffs Using Support Vector Machines

  2012cited by this paper
• Compound activity prediction using models of binding pockets or ligand properties in 3D.

  2012cited by this paper
• Network analysis has diverse roles in drug discovery.

  2012cited by this paper
• Using self-organizing maps to accelerate similarity search.

  2012cited by this paper
• Predicting the mechanism of phospholipidosis

  2012cited by this paper
• Exploring activity cliffs in medicinal chemistry.

  2012cited by this paper
• Intelligent control based on wavelet decomposition and neural network for predicting of human trajectories with a novel vision-based robotic

  2011cited by this paper
• Ligand-based virtual screening procedure for the prediction and the identification of novel β-amyloid aggregation inhibitors using Kohonen maps and Counterpropagation Artificial Neural Networks.

  2011cited by this paper
• Activity-Aware Clustering of High Throughput Screening Data and Elucidation of Orthogonal Structure-Activity Relationships

  2011cited by this paper
• Combined SVM-based and docking-based virtual screening for retrieving novel inhibitors of c-Met.

  2011cited by this paper
• Enhancing the Accuracy of Chemogenomic Models with a Three-Dimensional Binding Site Kernel

  2011cited by this paper
• StructRank: A New Approach for Ligand-Based Virtual Screening

  2011cited by this paper
• Classifying Molecules Using a Sparse Probabilistic Kernel Binary Classifier

  2011cited by this paper
• Binary Classification of Aqueous Solubility Using Support Vector Machines with Reduction and Recombination Feature Selection

  2011cited by this paper
• Classification of Cytochrome P450 Inhibitors and Noninhibitors Using Combined Classifiers

  2011cited by this paper
• Large-Scale Learning of Structure-Activity Relationships Using a Linear Support Vector Machine and Problem-Specific Metrics

  2011cited by this paper
• Visualizing the drug target landscape.

  2010cited by this paper
• Assessing Synthetic Accessibility of Chemical Compounds Using Machine Learning Methods

  2010cited by this paper
• Combining Machine Learning and Pharmacophore-Based Interaction Fingerprint for in Silico Screening

  2010cited by this paper
• Predicting Phospholipidosis Using Machine Learning

  2010cited by this paper
• A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking

  2010cited by this paper
• Current Trends in Ligand-Based Virtual Screening: Molecular Representations, Data Mining Methods, New Application Areas, and Performance Evaluation

  2010cited by this paper
• Ranking Chemical Structures for Drug Discovery: A New Machine Learning Approach

  2010cited by this paper
• Ligand-Based Virtual Screening Using Bayesian Networks

  2010cited by this paper
• Brainstorming: weighted voting prediction of inhibitors for protein targets

  2010cited by this paper
• Influence Relevance Voting: An Accurate And Interpretable Virtual High Throughput Screening Method

  2009cited by this paper
• Ligand Prediction for Orphan Targets Using Support Vector Machines and Various Target-Ligand Kernels Is Dominated by Nearest Neighbor Effects

  2009cited by this paper
• Machine learning in virtual screening.

  2009cited by this paper
• GPU Accelerated Support Vector Machines for Mining High-Throughput Screening Data

  2009cited by this paper
• Similarity‐Based Virtual Screening with a Bayesian Inference Network

  2009cited by this paper
• Target discovery from data mining approaches.

  2009cited by this paper
• In Silico Prediction of Aqueous Solubility: The Solubility Challenge

  2009cited by this paper
• Bayesian Model Averaging for Ligand Discovery

  2009cited by this paper
• Computational intelligence approaches for pattern discovery in biological systems

  2008cited by this paper
• Naïve Bayes Classification Using 2D Pharmacophore Feature Triplet Vectors

  2008cited by this paper
• 2D QSAR and similarity studies on cruzain inhibitors aimed at improving selectivity over cathepsin L.

  2008cited by this paper
• Ligand-Target Prediction Using Winnow and Naive Bayesian Algorithms and the Implications of Overall Performance Statistics

  2008cited by this paper
• Protein-ligand interaction prediction: an improved chemogenomics approach

  2008cited by this paper
• Support-Vector-Machine-Based Ranking Significantly Improves the Effectiveness of Similarity Searching Using 2D Fingerprints and Multiple Reference Compounds

  2008cited by this paper
• Gradual in Silico Filtering for Druglike Substances

  2008cited by this paper
• Chemical substructures that enrich for biological activity

  2008cited by this paper
• Straightforward recursive partitioning model for discarding insoluble compounds in the drug discovery process.

  2008cited by this paper
• Virtual screening of GPCRs: An in silico chemogenomics approach

  2008cited by this paper
• A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification

  2008cited by this paper
• Machine Learning for In Silico Virtual Screening and Chemical Genomics: New Strategies

  2008cited by this paper
• Why Are Some Properties More Difficult To Predict than Others? A Study of QSPR Models of Solubility, Melting Point, and Log P

  2008cited by this paper
• Predicting human liver microsomal stability with machine learning techniques.

  2008cited by this paper
• Atomic Property Fields: Generalized 3D Pharmacophoric Potential for Automated Ligand Superposition, Pharmacophore Elucidation and 3D QSAR

  2007cited by this paper
• ADME Evaluation in Drug Discovery, 8. The Prediction of Human Intestinal Absorption by a Support Vector Machine

  2007cited by this paper
• Supervised Consensus Scoring for Docking and Virtual Screening

  2007cited by this paper
• Molecular similarity analysis in virtual screening: foundations, limitations and novel approaches.

  2007cited by this paper
• Applications of artificial neural networks in medical science.

  2007cited by this paper
• Benchmarking of QSAR Models for Blood-Brain Barrier Permeation

  2007cited by this paper
• Ligand-Based Virtual Screening by Novelty Detection with Self-Organizing Maps

  2007cited by this paper
• Comparison of shape-matching and docking as virtual screening tools.

  2007cited by this paper
• One- to Four-Dimensional Kernels for Virtual Screening and the Prediction of Physical, Chemical, and Biological Properties

  2007cited by this paper
• Prediction of Ion Channel Activity Using Binary Kernel Discrimination

  2007cited by this paper
• Virtual screening in drug discovery -- a computational perspective.

  2007cited by this paper
• Melting Point Prediction Employing k-Nearest Neighbor Algorithms and Genetic Parameter Optimization

  2006cited by this paper
• The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM

  2006cited by this paper
• Collaborative Filtering on a Family of Biological Targets

  2006cited by this paper
• Toward physics of the mind: Concepts, emotions, consciousness, and symbols

  2006cited by this paper
• The Pharmacophore Kernel for Virtual Screening with Support Vector Machines

  2006cited by this paper
• EGFR Activation and Ultraviolet Light-Induced Skin Carcinogenesis

  2006cited by this paper
• An empirical comparison of supervised learning algorithms

  2006cited by this paper
• Combinatorial QSAR Modeling of P-Glycoprotein Substrates

  2006cited by this paper
• Classification Tree Models for the Prediction of Blood-Brain Barrier Passage of Drugs

  2006cited by this paper
• Prediction of estrogen receptor agonists and characterization of associated molecular descriptors by statistical learning methods.

  2006cited by this paper
• QSAR analysis of phenolic antioxidants using MOLMAP descriptors of local properties.

  2006cited by this paper
• The state of play in machine/environment interactions

  2006cited by this paper
• Three-Dimensional QSAR Using the k-Nearest Neighbor Method and Its Interpretation

  2006cited by this paper
• In silico human and rat Vss quantitative structure-activity relationship models.

  2006cited by this paper
• On Outliers and Activity Cliffs-Why QSAR Often Disappoints

  2006cited by this paper
• Toxicity-Indicating Structural Patterns

  2006cited by this paper
• Applications of Self-Organizing Neural Networks in Virtual Screening and Diversity Selection

  2006cited by this paper
• Kernel-based methods for hyperspectral image classification

  2005cited by this paper
• k Nearest Neighbors QSAR Modeling as a Variational Problem: Theory and Applications

  2005cited by this paper
• Kohonen Artificial Neural Network and Counter Propagation Neural Network in Molecular Structure-Toxicity Studies

  2005cited by this paper
• kappa Nearest neighbors QSAR modeling as a variational problem: theory and applications.

  2005cited by this paper
• Virtual Screening of Molecular Databases Using a Support Vector Machine

  2005cited by this paper
• PostDOCK: a structural, empirical approach to scoring protein ligand complexes.

  2005cited by this paper
• Classifying “Kinase Inhibitor‐Likeness” by Using Machine‐Learning Methods

  2005cited by this paper
• SOM of SOMs: Self-organizing Map Which Maps a Group of Self-organizing Maps

  2005cited by this paper
• Searching techniques for databases of two- and three-dimensional chemical structures.

  2005cited by this paper
• A study on the influence of molecular properties in the psychoactivity of cannabinoid compounds

  2005cited by this paper
• A recursive-partitioning model for blood–brain barrier permeation

  2005cited by this paper
• Graph kernels for chemical informatics

  2005cited by this paper
• Approaches to target class combinatorial library design.

  2004cited by this paper
• Applying data mining techniques to library design, lead generation and lead optimization.

  2004cited by this paper

• A unified survey on drug-target interaction and binding affinity prediction: Models, representations, and challenges.

  2026cites this paper
• THE AI REVOLUTION IN PHARMACEUTICALS: INNOVATIONS, CHALLENGES, AND FUTURE PROSPECTS – AN OVERVIEW

  2026cites this paper
• HVLGAN: hybrid hierarchical scaled attention-enabled latent model for structure-based drug discovery.

  2026cites this paper
• Explainable machine learning for early diagnosis of esophageal cancer: A feature-enriched Light Gradient Boosting Machine framework with Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretations

  2026cites this paper
• Discovery of New HER2 Inhibitors via Computational Docking, Pharmacophore Modeling, and Machine Learning

  2025cites this paper
• Integration of Machine Learning and Automated Synthesis for Accelerated Drug and Material Research

  2025cites this paper
• Machine Learning-Based Bioactivity Prediction and Descriptor-Guided Rational Design of Amyloid-β Aggregation Inhibitors.

  2025cites this paper
• Prompt-based multimodal representation learning for drug repurposing

  2025cites this paper
• Optimizing Quantum Data Embeddings for Ligand-Based Virtual Screening

  2025cites this paper
• An evaluation of Roluperidone as a promising repurposing candidate for Alzheimer’s Disease: A Computational Investigation

  2025cites this paper
• DTGHAT: multi-molecule heterogeneous graph transformer based on multi-molecule graph for drug-target identification

  2025cites this paper
• Generation of appropriate protein structures for virtual screening using AlphaFold3 predicted protein–ligand complexes

  2025cites this paper
• Machine Learning & Deep Learning Tools in Pharmaceutical Sciences: A Comprehensive Review

  2025cites this paper
• Artificial intelligence in natural products research.

  2025cites this paper
• Therapeutic Evaluation of Gut Microbiota-Derived Metabolites (GMDM) through Computational Approaches: A Narrative Review

  2025cites this paper
• Research progress on new techniques and methods for identifying active ingredients in traditional Chinese medicine.

  2025cites this paper
• Machine Learning Guided Design of Nerve‐On‐A‐Chip Platforms with Promoted Neurite Outgrowth

  2025cites this paper
• The pipeline for in silico prediction of target genes and target metabolic pathways for small molecules, using chelidonic acid as an example

  2025cites this paper
• Enhancing predictive modeling with XGBoost-engineered probabilities and deep neural networks: A hybrid approach for building reliable kinase inhibition QSAR models.

  2025cites this paper
• Molecular Modeling and Analysis of Cannabinoid and Cannabinoid-like Molecules Combining K-Means Clustering with Pearson Correlation and PCA

  2025cites this paper
• MetAP DB and Metal-FP: a database and fingerprint framework for advancing metal-based drug discovery

  2025cites this paper
• Research Progress on Virtual Screening Design Techniques for Small Molecule Inhibitors of JAK3 Kinase

  2025cites this paper
• Identifying novel drug targets with computational precision.

  2025cites this paper
• Protein Structure–Function Relationship: A Kernel-PCA Approach for Reaction Coordinate Identification

  2025cites this paper
• Computational discovery of novel PI3KC2α inhibitors using structure-based pharmacophore modeling, machine learning and molecular dynamic simulation.

  2025cites this paper
• Rapid traversal of vast chemical space using machine learning-guided docking screens

  2025cites this paper
• The Impact of AI Adoption on R&D Productivity: Evidence from Chinese Pharmaceutical Manufacturing Industry

  2025cites this paper
• Machine Learning‐Driven Discovery of Structurally Related Natural Products as Activators of the Cardiac Calcium Pump SERCA2a

  2025cites this paper
• Quality by digital design to accelerate sustainable medicines development.

  2025cites this paper
• Device-level nonlinearity and temporal memory in optoelectronic reservoir computing

  2025cites this paper
• Rethinking Representation Complexity in Drug–Target Prediction via Supervised Vector Quantization

  2025cites this paper
• Docking-Based Classification of SGLT2 Inhibitors

  2025cites this paper
• Prediction of Drug-Induced Nephrotoxicity Using Chemical Information and Transcriptomics Data

  2025cites this paper
• Leveraging viral genome sequences and machine learning models for identification of potentially selective antiviral agents

  2025cites this paper
• Machine Learning-Enhanced Single-Particle Tracking for Rapid Screening of Tumor Immunomodulatory Drugs.

  2025cites this paper
• Cross-Modality Controlled Molecule Generation with Diffusion Language Model

  2025cites this paper
• Novel graph neural network reveals binding mechanisms and environmental risks of PAHs interaction with estrogen receptor B.

  2025cites this paper
• Machine learning in antiviral drug design.

  2025cites this paper
• Pharmacoinformatics in Drug-Excipient Interactions.

  2025cites this paper
• Machine learning-based virtual screening and density functional theory characterisation of natural inhibitors targeting mutant PBP2x in Streptococcus pneumoniae

  2025cites this paper
• Identification of potential anti-biofilm agents targeting LasR in Pseudomonas aeruginosa through machine learning-driven screening, molecular docking, and dynamics simulations

  2025cites this paper
• Predicting Active Antimicrobial Compounds Using Machine Learning

  2025cites this paper
• Accelerating Pharma Innovation by Ai with Computational Models

  2025cites this paper
• Integrating Artificial Intelligence into Drug Development and Manufacturing: Advancements and Challenges

  2025cites this paper
• From Apo to Ligand-Bound: Unraveling PPARγ-LBD Conformational Shifts via Advanced Molecular Dynamics

  2025cites this paper
• Leveraging AlphaFold2 structural space exploration for generating drug target structures in structure-based virtual screening

  2025cites this paper
• A Review on Progress and Potential of Machine Learning and AI in Pharmaceutical Development

  2025cites this paper
• Artificial intelligence in anti-obesity drug discovery: unlocking next-generation therapeutics.

  2025cites this paper
• On the application of artificial intelligence in virtual screening

  2025cites this paper
• Efficient Hybrid-Robust Approach for Cancer Biomarker Discovery Using Omics Data

  2025cites this paper
• High-throughput computational screening for lead discovery and development.

  2025cites this paper
• Fs‐Pinns: Fractional Spectrally Adapted Physics‐Informed Neural Networks for Fractional Partial Differential Equations

  2025cites this paper
• Virtual screening and experimental validation of small-molecule compounds targeting AR in prostate cancer.

  2025cites this paper
• Drug Repurposing as an Effective Drug Discovery Strategy: A Critical Review

  2025influential citation
• Artificial intelligence in preclinical research: enhancing digital twins and organ-on-chip to reduce animal testing.

  2025cites this paper
• AMFGNN: an adaptive multi-view fusion graph neural network model for drug prediction

  2025cites this paper
• Artificial Intelligence in Natural Product Drug Discovery: Current Applications and Future Perspectives

  2025cites this paper
• Virtual screening: hope, hype, and the fine line in between

  2025cites this paper
• Optimizing drug synergy prediction through categorical embeddings in deep neural networks

  2025cites this paper
• The Current Landscape of AI Application in Healthcare: A Review

  2025cites this paper
• Targeting Ferroptosis in Rare Neurological Disorders Including Pediatric Conditions: Innovations and Therapeutic Challenges

  2025cites this paper
• Computational Landscape in Drug Discovery: From AI/ML Models to Translational Application

  2025influential citation
• Does Hessian Data Improve the Performance of Machine Learning Potentials?

  2025cites this paper
• Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World

  2025cites this paper
• Predicting the Student's Perceptions of Multi-Domain Environmental Factors in a Norwegian School Building: Machine Learning Approach

  2025cites this paper
• Developing a mobile application with geo-analytic tools to perform real estate valuation within smart cities

  2025cites this paper
• PLASMOpred: A Machine Learning-Based Web Application for Predicting Antimalarial Small Molecules Targeting the Apical Membrane Antigen 1–Rhoptry Neck Protein 2 Invasion Complex

  2025cites this paper
• Large language models for Alzheimer's disease drug discovery

  2025cites this paper
• Design and Application of Triangular Composition Descriptors for Predicting the Physicochemical Properties of Hydrocarbon Mixtures

  2025cites this paper
• Unraveling the ecotoxicity of micro(nano)plastics loaded with environmental pollutants using ensemble machine learning.

  2025cites this paper
• In silico screening of a designed focused chemical space identifies novel alkyl hydrazides as potent HDAC11 inhibitors

  2025cites this paper
• Neural Network Models for Prediction of Biological Activity using Molecular Dynamics Data: A Case of Photoswitchable Peptides

  2025cites this paper
• Integrative IoT Solution for Heatstroke: Machine Learning Enhancement and Healthcare Application

  2025cites this paper
• Predictive modeling of asthma drug properties using machine learning and topological indices in a MATLAB based QSPR study

  2025cites this paper
• Artificial intelligence (AI) in drug design and discovery: A comprehensive review

  2025cites this paper
• Harnessing AI-driven reverse docking in drug discovery: a comprehensive review of opportunities, challenges, and emerging trends

  2025cites this paper
• MultiTox: A sequence-based stacked ensemble model for multiclass protein toxin classification.

  2025cites this paper
• AI-Integrated QSAR Modeling for Enhanced Drug Discovery: From Classical Approaches to Deep Learning and Structural Insight

  2025cites this paper
• Improving Machine Learning Classification Predictions through SHAP and Features Analysis Interpretation

  2025cites this paper
• Machine Learning-Driven Prediction of TLR4 Binding Affinity: A Comprehensive Molecular Feature Analysis for Drug Discovery

  2025cites this paper
• The dawn of animal-free safety: A comprehensive review of new approach methodologies in 21st century toxicology

  2025cites this paper
• Current strategies to address data scarcity in artificial intelligence-based drug discovery: A comprehensive review

  2024cites this paper
• Advancing drug discovery with deep attention neural networks.

  2024cites this paper
• Future Prospects and Recent Advancements in Machine Learning for Assessing the Service Life and Durability of Reinforced Concrete Buildings

  2024cites this paper
• Top 20 Influential AI-Based Technologies in Chemistry

  2024cites this paper
• Exploring Innovation: Artificial Intelligence (AI) in Pharmacy

  2024cites this paper
• Identifying Substructures That Facilitate Compounds to Penetrate the Blood–Brain Barrier via Passive Transport Using Machine Learning Explainer Models

  2024cites this paper
• Breast Cancer Drugs Screening Model Based on Graph Convolutional Network and Ensemble Method

  2024cites this paper
• Unlocking the potential of generative AI in drug discovery.

  2024cites this paper
• Leveraging Artificial Intelligence for Synergies in Drug Discovery: From Computers to Clinics.

  2024cites this paper
• Navigating the frontier of drug-like chemical space with cutting-edge generative AI models.

  2024cites this paper
• Exploring the Molecular Terrain: A Survey of Analytical Methods for Biological Network Analysis

  2024cites this paper
• Artificial Intelligence (AI) and Alternative Variables (AV) in Drug Discovery: A Promising Alliance.

  2024cites this paper
• A review of deep learning algorithms for modeling drug interactions

  2024cites this paper
• Exploring machine learning for untargeted metabolomics using molecular fingerprints

  2024cites this paper
• Integrative computational approaches for discovery and evaluation of lead compound for drug design

  2024cites this paper
• Protein characteristics substantially influence the propensity of activity cliffs among kinase inhibitors

  2024cites this paper
• Robust Calibration For Improved Weather Prediction Under Distributional Shift

  2024cites this paper
• In silico approaches which are used in pharmacy

  2024cites this paper
• Integrating chemistry knowledge in large language models via prompt engineering

  2024cites this paper