Machine Learning in Drug Discovery: A Review

Published in

Artificial Intelligence Review(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

This review provides the feasible literature on drug discovery through ML tools and techniques that are enforced in every phase of drug development to accelerate the research process and deduce the risk and expenditure in clinical trials. Machine learning techniques improve the decision-making in pharmaceutical data across various applications like QSAR analysis, hit discoveries, de novo drug architectures to retrieve accurate outcomes. Target validation, prognostic biomarkers, digital pathology are considered under problem statements in this review. ML challenges must be applicable for the main cause of inadequacy in interpretability outcomes that may restrict the applications in drug discovery. In clinical trials, absolute and methodological data must be generated to tackle many puzzles in validating ML techniques, improving decision-making, promoting awareness in ML approaches, and deducing risk failures in drug discovery.

Authors

Suresh Dara

1 papers

Swetha Dhamercherla

1 papers

S. S. Jadav

1 papers

References255 items

Computational studies of anaplastic lymphoma kinase mutations reveal common mechanisms of oncogenic activation

Application of the residue number system to reduce hardware costs of the convolutional neural network implementation

De Novo Drug Design of Targeted Chemical Libraries Based on Artificial Intelligence and Pair-Based Multiobjective Optimization

A Minimal-Input Multilayer Perceptron for Predicting Drug-Drug Interactions Without Knowledge of Drug Structure

NERDD: a web portal providing access to in silico tools for drug discovery

Machine Learning in Drug Discovery: A Review

Published in

Artificial Intelligence Review(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Suresh Dara

1 papers

Swetha Dhamercherla

1 papers

S. S. Jadav

1 papers

References255 items

Computational studies of anaplastic lymphoma kinase mutations reveal common mechanisms of oncogenic activation

Application of the residue number system to reduce hardware costs of the convolutional neural network implementation

De Novo Drug Design of Targeted Chemical Libraries Based on Artificial Intelligence and Pair-Based Multiobjective Optimization

A Minimal-Input Multilayer Perceptron for Predicting Drug-Drug Interactions Without Knowledge of Drug Structure

NERDD: a web portal providing access to in silico tools for drug discovery

Christy M Babu

1 papers

Deep learning enables rapid identification of potent DDR1 kinase inhibitors

GLORY: Generator of the Structures of Likely Cytochrome P450 Metabolites Based on Predicted Sites of Metabolism

An Introduction to Variational Autoencoders

The EMBL-EBI search and sequence analysis tools APIs in 2019

Applications of machine learning in drug discovery and development

Incorporation of biomolecules in Metal-Organic Frameworks for advanced applications

Toxicological Evaluation of SiO2 Nanoparticles by Zebrafish Embryo Toxicity Test

Hit Dexter 2.0: Machine-Learning Models for the Prediction of Frequent Hitters

Advances with support vector machines for novel drug discovery

Survey of Similarity-based Prediction of Drug-protein Interactions.

VASC: Dimension Reduction and Visualization of Single-cell RNA-seq Data by Deep Variational Autoencoder

A review of network‐based approaches to drug repositioning

Deep Learning-A Technology With the Potential to Transform Health Care.

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

Spatial Architecture and Arrangement of Tumor-Infiltrating Lymphocytes for Predicting Likelihood of Recurrence in Early-Stage Non–Small Cell Lung Cancer

Prediction of Protein Secondary Structure With Clonal Selection Algorithm and Multilayer Perceptron

Multi-omics monitoring of drug response in rheumatoid arthritis in pursuit of molecular remission

Machine Learning on Human Muscle Transcriptomic Data for Biomarker Discovery and Tissue-Specific Drug Target Identification

Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers

Genome-wide polygenic scores for common diseases identify individuals with risk equivalent to monogenic mutations

Biomarkers as drug development tools: discovery, validation, qualification and use

The rise of deep learning in drug discovery.

Significance and implications of FDA approval of pembrolizumab for biomarker-defined disease

Chemistry-First Approach for Nomination of Personalized Treatment in Lung Cancer

Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images.

A deep-learning classifier identifies patients with clinical heart failure using whole-slide images of H&E tissue

Transcriptional regulatory networks underlying gene expression changes in Huntington's disease

Deep learning based tissue analysis predicts outcome in colorectal cancer

Artificial intelligence faces reproducibility crisis.

High-Dimensional Function Approximation With Neural Networks for Large Volumes of Data

KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks

SCScore: Synthetic Complexity Learned from a Reaction Corpus

Structural absorption by barbule microstructures of super black bird of paradise feathers

Cytokine release syndrome after radiation therapy: case report and review of the literature

Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

In silico structure-based approaches to discover protein-protein interaction-targeting drugs.

The target landscape of clinical kinase drugs

DeepInteract: Deep Neural Network Based Protein-Protein Interaction Prediction Tool

Systematic interrogation of diverse Omic data reveals interpretable, robust, and generalizable transcriptomic features of clinically successful therapeutic targets

Adversarial Symmetric Variational Autoencoder

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies

MR fingerprinting Deep RecOnstruction NEtwork (DRONE)

The drug-maker's guide to the galaxy

Deep learning methods for protein torsion angle prediction

Heterogeneity Aware Random Forest for Drug Sensitivity Prediction

Dhaka: Variational Autoencoder for Unmasking Tumor Heterogeneity from Single Cell Genomic Data

Interpretable dimensionality reduction of single cell transcriptome data with deep generative models

Convolutional Neural Networks in Visual Computing: A Concise Guide

Extracting a Biologically Relevant Latent Space from Cancer Transcriptomes with Variational Autoencoders

An oral cavity squamous cell carcinoma quantitative histomorphometric-based image classifier of nuclear morphology can risk stratify patients for disease-specific survival

Is Multitask Deep Learning Practical for Pharma?

Defining a Cancer Dependency Map

In silico prediction of novel therapeutic targets using gene–disease association data

Machine-Learning-Assisted Approach for Discovering Novel Inhibitors Targeting Bromodomain-Containing Protein 4

The AI detectives.

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction

A multi‐scale convolutional neural network for phenotyping high‐content cellular images

Abstract 662: The differential association of PD-1, PD-L1, and CD8+ cells with response to pembrolizumab and presence of Merkel cell polyomavirus (MCPyV) in patients with Merkel cell carcinoma (MCC)

IntegratedMRF: random forest‐based framework for integrating prediction from different data types

Bridging the translational innovation gap through good biomarker practice

A novel framework for the identification of drug target proteins: Combining stacked auto-encoders with a biased support vector machine

Immune Network Technology on the Basis of Random Forest Algorithm for Computer-Aided Drug Design

Molecular de-novo design through deep reinforcement learning

Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent

Deep Learning Based Regression and Multiclass Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction

Automatic selection of molecular descriptors using random forest: Application to drug discovery

A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information

In situ click chemistry generation of cyclooxygenase-2 inhibitors

A machine-learning heuristic to improve gene score prediction of polygenic traits

Maximum entropy methods for extracting the learned features of deep neural networks

Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network

Integrative deep models for alternative splicing

Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness

An analysis of disease-gene relationship from Medline abstracts by DigSee

De novo Drug Design – Ye olde Scoring Problem Revisited

Deep Learning for Classification of Colorectal Polyps on Whole-slide Images

The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology

Computational methods in drug discovery

A comprehensive map of molecular drug targets

Ultrastructural Characterization of the Lower Motor System in a Mouse Model of Krabbe Disease

Open Targets: a platform for therapeutic target identification and validation

Elucidating the druggable interface of protein−protein interactions using fragment docking and coevolutionary analysis

Systematic Analysis of Drug Targets Confirms Expression in Disease-Relevant Tissues

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

A simple model predicts UGT-mediated metabolism

Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

In Silico Prediction of Volume of Distribution in Humans. Extensive Data Set and the Exploration of Linear and Nonlinear Methods Coupled with Molecular Interaction Fields Descriptors

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

Quantitative assessment of the spatial heterogeneity of tumor-infiltrating lymphocytes in breast cancer

A Landscape of Pharmacogenomic Interactions in Cancer

Deep learning for computational biology

100

Modeling Industrial ADMET Data with Multitask Networks

101

Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning

102

DeNovo: virus-host sequence-based protein-protein interaction prediction

103

Small molecules, big targets: drug discovery faces the protein–protein interaction challenge

104

ADME Properties Evaluation in Drug Discovery: Prediction of Caco-2 Cell Permeability Using a Combination of NSGA-II and Boosting

105

Comparison of Random Forest and SVM for Raw Data in Drug Discovery: Prediction of Radiation Protection and Toxicity Case Study

106

Prioritization of anticancer drugs against a cancer using genomic features of cancer cells: A step towards personalized medicine

107

Automated Tubule Nuclei Quantification and Correlation with Oncotype DX risk categories in ER+ Breast Cancer Whole Slide Images

108

DeepTox: Toxicity Prediction using Deep Learning

109

Network-based in silico drug efficacy screening

110

A new view of transcriptome complexity and regulation through the lens of local splicing variations

111

Computer Aided Drug Design: Success and Limitations.

112

ADAGE-Based Integration of Publicly Available Pseudomonas aeruginosa Gene Expression Data with Denoising Autoencoders Illuminates Microbe-Host Interactions

113

Template-based identification of protein-protein interfaces using eFindSitePPI.

114

Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases

115

Antibody-supervised deep learning for quantification of tumor-infiltrating immune cells in hematoxylin and eosin stained breast cancer samples

116

Sparse group factor analysis for biclustering of multiple data sources

117

Prediction of Druggable Proteins Using Machine Learning and Systems Biology: A Mini-Review

118

Computational prediction of protein interfaces: A review of data driven methods

119

Potential Compounds for Oral Cancer Treatment: Resveratrol, Nimbolide, Lovastatin, Bortezomib, Vorinostat, Berberine, Pterostilbene, Deguelin, Andrographolide, and Colchicine

120

Convolutional Networks on Graphs for Learning Molecular Fingerprints

121

Machine‐learning scoring functions to improve structure‐based binding affinity prediction and virtual screening

122

Development of a Drug-Response Modeling Framework to Identify Cell Line Derived Translational Biomarkers That Can Predict Treatment Outcome to Erlotinib or Sorafenib

123

Comprehensive prediction of drug-protein interactions and side effects for the human proteome

124

ZIFA: Dimensionality reduction for zero-inflated single-cell gene expression analysis

125

XenoSite server: a web-available site of metabolism prediction tool

126

Deep learning and the information bottleneck principle

127

Machine learning in computational docking

128

Human-level control through deep reinforcement learning

129

Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships

130

Improving Drug Sensitivity Prediction Using Different Types of Data

131

Beware of docking!

132

Computational Intelligence

133

Hot spots in protein-protein interfaces: towards drug discovery.

134

STRING v10: protein–protein interaction networks, integrated over the tree of life

135

Protein-protein docking: from interaction to interactome.

136

Drug repositioning by integrating target information through a heterogeneous network model

137

AS-2, a novel inhibitor of p53-dependent apoptosis, prevents apoptotic mitochondrial dysfunction in a transcription-independent manner and protects mice from a lethal dose of ionizing radiation.

138

In silico machine learning methods in drug development.

139

A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening

140

Extraction of relations between genes and diseases from text and large-scale data analysis: implications for translational research

141

Deep Learning: Methods and Applications

142

Deep learning of the tissue-regulated splicing code

143

Multi-task Neural Networks for QSAR Predictions

144

A community effort to assess and improve drug sensitivity prediction algorithms

145

Clearance mechanism assignment and total clearance prediction in human based upon in silico models.

146

Metformin promotes lifespan through mitohormesis via the peroxiredoxin PRDX-2

147

Deep learning in neural networks: An overview

148

Structure-based design of small-molecule protein-protein interaction modulators: the story so far.

149

Computational Methods in Drug Discovery

150

Auto-Encoding Variational Bayes

151

Support vector machine

152

XenoSite: Accurately Predicting CYP-Mediated Sites of Metabolism with Neural Networks

153

Protein-protein interactions as druggable targets: recent technological advances.

154

Virtual screening strategies in drug discovery: a critical review.

155

Metformin improves healthspan and lifespan in mice

156

Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules

157

Metformin Retards Aging in C. elegans by Altering Microbial Folate and Methionine Metabolism

158

Rapid discovery of a novel series of Abl kinase inhibitors by application of an integrated microfluidic synthesis and screening platform.

159

Biomedical data integration in computational drug design and bioinformatics.

160

Pattern Classification

161

Machine learning techniques and drug design.

162

ToxAlerts: A Web Server of Structural Alerts for Toxic Chemicals and Compounds with Potential Adverse Reactions

163

Combining Global and Local Measures for Structure-Based Druggability Predictions

164

Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival

165

Support Vector Regression Scoring of Receptor-Ligand Complexes for Rank-Ordering and Virtual Screening of Chemical Libraries

166

ChEMBL: a large-scale bioactivity database for drug discovery

167

The BATTLE trial: personalizing therapy for lung cancer.

168

ADME evaluation in drug discovery. 9. Prediction of oral bioavailability in humans based on molecular properties and structural fingerprints.

169

In silico structure‐activity‐relationship (SAR) models from machine learning: a review

170

A Machine Learning-Based Method To Improve Docking Scoring Functions and Its Application to Drug Repurposing

171

A machine learning approach for genome-wide prediction of morbid and druggable human genes based on systems-level data

172

Recent Advances in Fragment-Based QSAR and Multi-Dimensional QSAR Methods

173

Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces

174

De novo drug design.

175

Protein interface conservation across structure space

176

Towards consensus practices to qualify safety biomarkers for use in early drug development

177

The dynamics of drug-target interactions: drug-target residence time and its impact on efficacy and safety

178

Inclusion of Solvation and Entropy in the Knowledge-Based Scoring Function for Protein-Ligand Interactions

179

Machine learning in virtual screening.

180

Comparative analysis of machine learning methods in ligand-based virtual screening of large compound libraries.

181

SVM Model for Virtual Screening of Lck Inhibitors

182

Properties and identification of human protein drug targets

183

Prediction of survival in multiple myeloma based on gene expression profiles reveals cell cycle and chromosomal instability signatures in high-risk patients and hyperdiploid signatures in low-risk patients: a study of the Intergroupe Francophone du Myélome.

184

Prediction of drug–target interaction networks from the integration of chemical and genomic spaces

185

Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences

186

Prediction of potential drug targets based on simple sequence properties

187

Determination of drug permeability and prediction of drug absorption in Caco-2 monolayers

188

Artificial neural network models for prediction of intestinal permeability of oligopeptides

189

eHiTS: a new fast, exhaustive flexible ligand docking system.

190

Artificial intelligence approaches for rational drug design and discovery.

191

Current issues relating to drug safety especially with regard to the use of biomarkers: a meeting report and progress update.

192

Gene expression profiling and correlation with outcome in clinical trials of the proteasome inhibitor bortezomib.

193

Greedy Layer-Wise Training of Deep Networks

194

A validated gene expression model of high-risk multiple myeloma is defined by deregulated expression of genes mapping to chromosome 1.

195

On the nature of cavities on protein surfaces: Application to the identification of drug‐binding sites

196

Computational methods in developing quantitative structure-activity relationships (QSAR): a review.

197

PatchDock and SymmDock: servers for rigid and symmetric docking

198

Drug repositioning: identifying and developing new uses for existing drugs

199

A tutorial on support vector regression

200