4.7 Review

Recent Advances in Machine-Learning-Based Chemoinformatics: A Comprehensive Review

Related references

Note: Only part of the references are listed.
Article Computer Science, Interdisciplinary Applications

AIMSim: An accessible cheminformatics platform for similarity operations on chemicals datasets

Himaghna Bhattacharjee et al.

Summary: The recent advances in deep learning, generative modeling, and statistical learning have led to a renewed interest in traditional cheminformatics tools and methods. This paper introduces AIMSim, an accessible cheminformatics platform for performing similarity operations on molecular datasets. AIMSim provides a unified platform to perform similarity-based tasks on molecular datasets and includes support for command-line use as well as a Graphical User Interface for code-free utilization with fully interactive plots.

COMPUTER PHYSICS COMMUNICATIONS (2023)

Article Biochemistry & Molecular Biology

NCATS Inxight Drugs: a comprehensive and curated portal for translational research

Vishal B. Siramshetty et al.

Summary: The United States has a complex regulatory scheme for marketing drugs. NCATS has developed Inxight Drugs, a web resource that integrates data from FDA, US government publications, and other sources to provide a wealth of manually curated literature data on drug ingredients and regulatory status. The database contains over 125,000 product ingredients, including approved, marketed, and investigational drugs, and is regularly updated using automated data aggregation tools.

NUCLEIC ACIDS RESEARCH (2022)

Article Chemistry, Multidisciplinary

Model agnostic generation of counterfactual explanations for molecules

Geemi P. Wellawatte et al.

Summary: A major challenge in deep learning in chemistry is the lack of interpretability, which hinders the deployment of AI models. Counterfactuals provide a rationale for model predictions and insights into chemical structures. This work demonstrates a universal model-agnostic approach that can explain predictions of any black-box model.

CHEMICAL SCIENCE (2022)

Review Biochemistry & Molecular Biology

Machine learning approaches and their applications in drug discovery and design

Sonal Priya et al.

Summary: This review focuses on several machine learning approaches used in chemoinformatics, which have shown great potential in improving drug discovery. These approaches can effectively model various physicochemical properties of drugs and have achieved good accuracy in recent years.

CHEMICAL BIOLOGY & DRUG DESIGN (2022)

Review Pharmacology & Pharmacy

Data considerations for predictive modeling applied to the discovery of bioactive natural products

Hai Tao Xue et al.

Summary: Natural products are a valuable resource for drug development, but analyzing their complex data is a challenge. Artificial intelligence techniques can help overcome this limitation. However, further work is needed in knowledge and resource development, as well as modeling considerations, limitations, and challenges.

DRUG DISCOVERY TODAY (2022)

Article Chemistry, Multidisciplinary

Machine intelligence-driven framework for optimized hit selection in virtual screening

Neeraj Kumar et al.

Summary: This article presents an advanced virtual screening framework called A-HIOT, which integrates chemical and protein space to accurately identify and optimize specific hit molecules for desired receptors. The framework demonstrates superior performance in finding optimized hits for the receptors.

JOURNAL OF CHEMINFORMATICS (2022)

Article Chemistry, Multidisciplinary

Comparison of various methods for validity evaluation of QSAR models

Shadi Shayanfar et al.

Summary: This study collected 44 QSAR models for biologically active compounds, and found that using the coefficient of determination alone is not sufficient to indicate the validity of a QSAR model. The established criteria for external validation in QSAR studies have both advantages and disadvantages that should be carefully considered.

BMC CHEMISTRY (2022)

Article Biochemical Research Methods

Do we need different machine learning algorithms for QSAR modeling? A comprehensive assessment of 16 machine learning algorithms on 14 QSAR data sets

Zhenxing Wu et al.

Summary: A study on learning QSAR models using various ML algorithms for 14 public datasets showed that rbf-SVM, rbf-GPR, XGBoost, and DNN generally perform better than other algorithms. SVM and XGBoost are recommended for regression learning on small datasets, while XGBoost is an excellent choice for large datasets. Ensemble models integrating multiple algorithms can improve prediction accuracy.

BRIEFINGS IN BIOINFORMATICS (2021)

Review Pharmacology & Pharmacy

Graph neural networks for automated de novo drug design

Jiacheng Xiong et al.

Summary: De novo drug design aims to create novel chemical entities with desired properties, with the recent popularity of data-driven methods utilizing artificial intelligence technologies like graph neural networks (GNNs). The applications of GNNs in drug design include molecule scoring, generation, optimization, and synthesis planning, with discussions on current challenges and future directions in this field.

DRUG DISCOVERY TODAY (2021)

Article Biochemistry & Molecular Biology

Adapting the DeepSARM approach for dual-target ligand design

Atsushi Yoshimori et al.

Summary: The SARM methodology is used for extracting structurally related compound series and visualizing SAR patterns, with the addition of DeepSARM for increased structural novelty. This method can be adapted for designing compounds with dual-target activity, which is equally attractive and challenging for polypharmacology-oriented drug discovery.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2021)

Article Chemistry, Multidisciplinary

Deep scaffold hopping with multimodal transformer neural networks

Shuangjia Zheng et al.

Summary: Scaffold hopping is essential in modern medicinal chemistry for designing molecules with novel scaffolds but similar biological activities to known compounds. In this study, a supervised molecule-to-molecule translation approach was used to generate hopped molecules with similar 3D structures but different 2D structures. The trained DeepHop model successfully produced molecules with improved bioactivity and high 3D similarity compared to template molecules.

JOURNAL OF CHEMINFORMATICS (2021)

Review Pharmacology & Pharmacy

Artificial intelligence in drug discovery: recent advances and future perspectives

Jose Jimenez-Luna et al.

Summary: This article reviews the current status of AI in chemoinformatics, discussing topics such as quantitative structure-activity/property relationship and structure-based modeling, de novo molecular design, and chemical synthesis prediction. The advantages and limitations of current deep learning applications are highlighted, offering a perspective on next-generation AI for drug discovery.

EXPERT OPINION ON DRUG DISCOVERY (2021)

Article Biochemistry & Molecular Biology

Systematic assessment of structure-promiscuity relationships between different types of kinase inhibitors

Huabin Hu et al.

Summary: With the increasing demand for selective kinase inhibitors, a systematic investigation was conducted to explore the structural relationship between promiscuous kinase inhibitors and other types, indicating a wider potential selectivity for promiscuous inhibitors. The majority of promiscuous inhibitors form related analogue series, while only a small portion of other types of inhibitors have structural relationships, with many of them also exhibiting multi-kinase activity.

BIOORGANIC & MEDICINAL CHEMISTRY (2021)

Article Chemistry, Multidisciplinary

Benchmarks for interpretation of QSAR models

Mariia Matveieva et al.

Summary: The interpretation of QSAR models is crucial for understanding complex processes and guiding model validation. This study develops benchmark datasets for evaluating interpretation methods of different complexity levels, proposing quantitative metrics for performance assessment. These benchmarks are applied to various models and neural networks, aiding in the evaluation and investigation of decision-making in complex black box models.

JOURNAL OF CHEMINFORMATICS (2021)

Article Chemistry, Medicinal

Improvement in ADMET Prediction with Multitask Deep Featurization

Evan N. Feinberg et al.

JOURNAL OF MEDICINAL CHEMISTRY (2020)

Review Chemistry, Multidisciplinary

Review on natural products databases: where to find data in 2020

Maria Sorokina et al.

JOURNAL OF CHEMINFORMATICS (2020)

Article Chemistry, Multidisciplinary

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

Pavel Karpov et al.

JOURNAL OF CHEMINFORMATICS (2020)

Review Pharmacology & Pharmacy

Artificial intelligence in drug discovery and development

Debleena Paul et al.

DRUG DISCOVERY TODAY (2020)

Article Biochemistry & Molecular Biology

Evaluation of QSAR Equations for Virtual Screening

Jacob Spiegel et al.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2020)

Review Chemistry, Multidisciplinary

Molecular representations in AI-driven drug discovery: a review and practical guide

Laurianne David et al.

JOURNAL OF CHEMINFORMATICS (2020)

Article Computer Science, Artificial Intelligence

Generative molecular design in low data regimes

Michael Moret et al.

NATURE MACHINE INTELLIGENCE (2020)

Review Computer Science, Artificial Intelligence

Drug discovery with explainable artificial intelligence

Jose Jimenez-Luna et al.

NATURE MACHINE INTELLIGENCE (2020)

Article Multidisciplinary Sciences

Functional random forest with applications in dose-response predictions

Raziur Rahman et al.

SCIENTIFIC REPORTS (2019)

Article Biochemistry & Molecular Biology

Network-based piecewise linear regression for QSAR modelling

Jonathan Cardoso-Silva et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2019)

Article Biochemistry & Molecular Biology

SymMap: an integrative database of traditional Chinese medicine enhanced by symptom mapping

Yang Wu et al.

NUCLEIC ACIDS RESEARCH (2019)

Article Biochemistry & Molecular Biology

ChEMBL: towards direct deposition of bioassay data

David Mendez et al.

NUCLEIC ACIDS RESEARCH (2019)

Article Computer Science, Artificial Intelligence

Descriptor Free QSAR Modeling Using Deep Learning With Long Short-Term Memory Neural Networks

Suman K. Chakravarti et al.

FRONTIERS IN ARTIFICIAL INTELLIGENCE (2019)

Article Biochemistry & Molecular Biology

DrugBank 5.0: a major update to the DrugBank database for 2018

David S. Wishart et al.

NUCLEIC ACIDS RESEARCH (2018)

Review Pharmacology & Pharmacy

Machine learning in chemoinformatics and drug discovery

Yu-Chen Lo et al.

DRUG DISCOVERY TODAY (2018)

Article Cell Biology

Identification of Estrogen Receptor a Antagonists from Natural Products via In Vitro and In Silico Approaches

Xiaocong Pang et al.

OXIDATIVE MEDICINE AND CELLULAR LONGEVITY (2018)

Review Pharmacology & Pharmacy

QSAR-Based Virtual Screening: Advances and Applications in Drug Discovery

Bruno J. Neves et al.

FRONTIERS IN PHARMACOLOGY (2018)

Article Chemistry, Multidisciplinary

Scaffold hopping from natural products to synthetic mimetics by holistic molecular similarity

Francesca Grisoni et al.

COMMUNICATIONS CHEMISTRY (2018)

Article Chemistry, Medicinal

Characterizing the Chemical Space of ERK2 Kinase Inhibitors Using Descriptors Computed from Molecular Dynamics Trajectories

Jeremy Ash et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2017)

Article Chemistry, Multidisciplinary

ChemSAR: an online pipelining platform for molecular SAR modeling

Jie Dong et al.

JOURNAL OF CHEMINFORMATICS (2017)

Article Chemistry, Multidisciplinary

Molecular de-novo design through deep reinforcement learning

Marcus Olivecrona et al.

JOURNAL OF CHEMINFORMATICS (2017)

Article Multidisciplinary Sciences

Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery

Ignacio Ponzoni et al.

SCIENTIFIC REPORTS (2017)

Article Biochemical Research Methods

3D deep convolutional neural networks for amino acid environment similarity analysis

Wen Torng et al.

BMC BIOINFORMATICS (2017)

Article Biochemistry & Molecular Biology

BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology

Michael K. Gilson et al.

NUCLEIC ACIDS RESEARCH (2016)

Review Biochemistry & Molecular Biology

Chemoinformatics: Achievements and Challenges, a Personal View

Johann Gasteiger

MOLECULES (2016)

Article Chemistry, Multidisciplinary

Large-scale ligand-based predictive modelling using support vector machines

Jonathan Alvarsson et al.

JOURNAL OF CHEMINFORMATICS (2016)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Biochemistry & Molecular Biology

Super Natural II-a database of natural products

Priyanka Banerjee et al.

NUCLEIC ACIDS RESEARCH (2015)

Article Chemistry, Medicinal

Choosing Feature Selection and Learning Algorithms in QSAR

Martin Eklund et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2014)

Article Chemistry, Multidisciplinary

TCMSP: a database of systems pharmacology for drug discovery from herbal medicines

Jinlong Ru et al.

JOURNAL OF CHEMINFORMATICS (2014)

Article Chemistry, Medicinal

Kernel-Based Partial Least Squares: Application to Fingerprint-Based QSAR with Model Visualization

Yuling An et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2013)

Article Biochemistry & Molecular Biology

TCMID: traditional Chinese medicine integrative database for herb molecular mechanism analysis

Ruichao Xue et al.

NUCLEIC ACIDS RESEARCH (2013)

Review Pharmacology & Pharmacy

Classification of scaffold-hopping approaches

Hongmao Sun et al.

DRUG DISCOVERY TODAY (2012)

Article Chemistry, Medicinal

Comparison of Random Forest and Pipeline Pilot Naive Bayes in Prospective QSAR Predictions

Bin Chen et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2012)

Review Chemistry, Medicinal

Chemoinformatics as a Theoretical Chemistry Discipline

Alexandre Varnek et al.

MOLECULAR INFORMATICS (2011)

Review Chemistry, Medicinal

Best Practices for QSAR Model Development, Validation, and Exploitation

Alexander Tropsha

MOLECULAR INFORMATICS (2010)

Article Chemistry, Medicinal

QSAR Studies of HEPT Derivatives Using Support Vector Machines

Rachid Darnag et al.

QSAR & COMBINATORIAL SCIENCE (2009)

Article Biochemistry & Molecular Biology

Computer-aided drug discovery and development (CADDD):: In silico-chemico-biological approach

I. M. Kapetanovic

CHEMICO-BIOLOGICAL INTERACTIONS (2008)

Article Chemistry, Multidisciplinary

Support vector machine for SAR/QSAR of phenethyl-amines

Bing Niu et al.

ACTA PHARMACOLOGICA SINICA (2007)

Article Biotechnology & Applied Microbiology

Relating protein pharmacology by ligand chemistry

Michael J. Keiser et al.

NATURE BIOTECHNOLOGY (2007)

Review Chemistry, Medicinal

Basic overview of chemoinformatics

Thomas Engel

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2006)

Article Chemistry, Medicinal

Melting point prediction employing k-nearest neighbor algorithms and genetic parameter optimization

Florian Nigsch et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2006)

Review Biochemical Research Methods

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

AZ Dudek et al.

COMBINATORIAL CHEMISTRY & HIGH THROUGHPUT SCREENING (2006)

Article Chemistry, Medicinal

Three-dimensional QSAR using the k-nearest neighbor method and its interpretation

S Ajmani et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2006)

Article Biochemical Research Methods

A method for quantifying and visualizing the diversity of QSAR models

S Izrailev et al.

JOURNAL OF MOLECULAR GRAPHICS & MODELLING (2004)

Article Chemistry, Medicinal

A 3D similarity method for scaffold hopping from the known drugs or natural ligands to new chemotypes

JL Jenkins et al.

JOURNAL OF MEDICINAL CHEMISTRY (2004)

Review Chemistry, Medicinal

Approaches to measure chemical similarity - A review

N Nikolova et al.

QSAR & COMBINATORIAL SCIENCE (2004)

Article Chemistry, Multidisciplinary

Robustness of biological activity spectra predicting by computer program PASS for noncongeneric sets of chemical compounds

VV Poroikov et al.

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES (2000)