☆ 4.7 Review

New avenues in artificial-intelligence- assisted drug discovery

DRUG DISCOVERY TODAY (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Chemistry, Medicinal

MLCV: Bridging Machine-Learning-Based Dimensionality Reduction and Free-Energy Calculation

Haochuan Chen et al.

Summary: The study introduces a user-friendly tool called MLCV that facilitates the use of machine-learned CVs in importance-sampling simulations through the popular Colvars module. The approach is critically tested with three case examples involving small peptides, demonstrating the effectiveness of bridging deep learning and enhanced-sampling with MD simulations through hard-coded neural networks in Colvars.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

Generating 3D molecules conditional on receptor binding sites with deep generative models

Matthew Ragoza et al.

Summary: This study presents a deep learning system for generating 3D molecular structures conditioned on a receptor binding site, using an atomic density grid representation to train a conditional variational autoencoder. The properties of the generated molecules are evaluated, showing significant changes under different conditions such as mutated receptors. Sampling and interpolation techniques are used to explore the latent space learned by the generative model, allowing for end-to-end prediction of stable bioactive molecules from protein structures with deep learning.

CHEMICAL SCIENCE (2022)

添加到收藏夹

Review Pharmacology & Pharmacy

Selection of data sets for FAIRification in drug discovery and development: Which, why, and how?

Ebtisam Alharbi et al.

Summary: Despite the intuitive value of adopting FAIR principles in academia and industry, challenges exist in resource allocation and technical implementation. Scientific and R&D leadership require reliable evidence and effective implementation mechanisms to evaluate potential benefits and remediate strategies.

DRUG DISCOVERY TODAY (2022)

添加到收藏夹

Review Chemistry, Medicinal

Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative Models

Weixin Xie et al.

Summary: This article highlights the latest developments in using deep learning techniques combined with 3D molecular generative models for de novo drug design, and discusses future research directions.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Article Chemistry, Medicinal

An In Silico Explainable Multiparameter Optimization Approach for De Novo Drug Design against Proteins from the Central Nervous System

Navneet Bung et al.

Summary: This article introduces a novel drug design method based on deep learning, which can optimize target specificity and multiple other parameters in a single step to improve the efficiency of drug design and development. The method optimizes all possible combinations of parameters, identifies molecular fragments, and designs small molecules with desired properties.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Article Chemistry, Medicinal

Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein-Ligand Scoring Functions

Chao Yang et al.

Summary: In this study, the robustness and applicability of machine-learning scoring functions were further improved by expanding the training set, developing meaningful features, using a linear empirical scoring function as the baseline, and applying extreme gradient boosting (XGBoost) with Delta-machine learning. The new scoring function demonstrated superior performance in scoring and ranking in various structure types and showed reliability and robustness in virtual screening applications.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Article Chemistry, Medicinal

TocoDecoy: A New Approach to Design Unbiased Datasets for Training and Benchmarking Machine-Learning Scoring Functions

Xujun Zhang et al.

Summary: The development of accurate machine-learning-based scoring functions for virtual screening requires unbiased and diverse datasets. However, most existing datasets may suffer from hidden biases and data insufficiency. In this study, we developed a new approach named TocoDecoy to generate unbiased and expandable datasets, and evaluated its performance compared to other datasets.

JOURNAL OF MEDICINAL CHEMISTRY (2022)

添加到收藏夹

Article Chemistry, Medicinal

On the Frustration to Predict Binding Affinities from Protein-Ligand Structures with Deep Neural Networks

Mikhail Volkov et al.

Summary: The study suggests that explicitly describing protein-ligand noncovalent interactions does not provide an advantage over using ligand or protein descriptors. Simple models already exhibit good performances, indicating that memorization dominates true learning in deep neural networks.

JOURNAL OF MEDICINAL CHEMISTRY (2022)

添加到收藏夹

Article Multidisciplinary Sciences

GEOM, energy-annotated molecular conformations for property prediction and molecular generation

Simon Axelrod et al.

Summary: Machine learning outperforms traditional approaches in molecular design. However, most ML models only predict molecular properties based on 2D chemical graphs or single 3D structures, neglecting the ensemble of 3D conformers accessible to a molecule. This article introduces a large-scale dataset, GEOM, which contains accurate conformers and experimental data annotations, aiming to facilitate the development of models predicting properties from conformer ensembles and generative models sampling 3D conformations.

SCIENTIFIC DATA (2022)

添加到收藏夹

Article Chemistry, Medicinal

RELATION: A Deep Generative Model for Structure-Based De Novo Drug Design

Mingyang Wang et al.

Summary: The paper proposes a new 3D-based generative model called RELATION, which efficiently generates novel molecules with favorable binding affinity and pharmacophore features.

JOURNAL OF MEDICINAL CHEMISTRY (2022)

添加到收藏夹

Review Biochemical Research Methods

Computationally predicting binding affinity in protein-ligand complexes: free energy-based simulations and machine learning-based scoring functions

Debby D. Wang et al.

Summary: This paper reviews two classes of methods for accurately predicting protein-ligand binding affinities: free energy-based simulations and machine learning-based scoring functions. It follows thermodynamic cycles for the former and a feature-representation taxonomy for the latter. Additionally, recent deep learning-based predictions are also discussed, with comparisons of strengths, weaknesses, and future directions for improvements.

BRIEFINGS IN BIOINFORMATICS (2021)

添加到收藏夹

Article Chemistry, Medicinal

Property-Unmatched Decoys in Docking Benchmarks

Reed M. Stein et al.

Summary: The enrichment of ligands compared to property-matched decoys is commonly used in docking library screens, but over-optimizing for enrichment alone can lead to false confidence in prospective performance. By adding decoys representing charge extrema and overall characteristics of the library being docked, one can sample molecules not represented by the ligands and property-matched decoys, improving the accuracy of future screening results.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

添加到收藏夹

Review Pharmacology & Pharmacy

Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data

Andreas Bender et al.

Summary: Artificial Intelligence (AI) has made significant progress in areas such as image and speech recognition, but faces challenges in drug discovery due to limitations in data. Future advancements require a better understanding of biological systems and the generation of more relevant data to drive AI forward in drug discovery.

DRUG DISCOVERY TODAY (2021)

添加到收藏夹

Review Pharmacology & Pharmacy

Critical assessment of AI in drug discovery

W. Patrick Walters et al.

Summary: AI has become an integral part of everyday life, with applications in various fields including drug discovery. The use of AI in drug discovery encompasses property prediction, molecule generation, image analysis, and organic synthesis planning. While machine learning methods are commonly used for predicting biological activity, the development of new molecule generation methods has the potential to explore uncharted chemical space. The continued advancement of AI in drug discovery will rely on dedicated research and progress in AI technology.

EXPERT OPINION ON DRUG DISCOVERY (2021)

添加到收藏夹

Review Pharmacology & Pharmacy

De novo molecular design and generative models

Joshua Meyers et al.

Summary: This review discusses the application of computational methods in drug discovery, focusing on molecular design strategies and de novo approaches. The methods of molecular design are categorized based on the coarseness of molecular representation, such as atom-based, fragment-based, or reaction-based paradigms. The importance of strong benchmarks, challenges in practical application, and potential opportunities for exploration and growth in the field are highlighted.

DRUG DISCOVERY TODAY (2021)

添加到收藏夹

Review Chemistry, Medicinal

Artificial Intelligence in Chemistry: Current Trends and Future Directions

Zachary J. Baum et al.

Summary: The application of artificial intelligence (AI) in the field of chemistry has grown significantly in recent years, particularly in analytical chemistry and biochemistry. Over the past two decades, there has been a rapid increase in AI-related chemistry publications.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

添加到收藏夹

Article Chemistry, Medicinal

Lin_F9: A Linear Empirical Scoring Function for Protein-Ligand Docking

Chao Yang et al.

Summary: A new scoring function Lin_F9 is introduced in this work, which achieves top scoring power among classical scoring functions in CASF-2016 benchmark test set. Parameters in Lin_F9 are obtained with a multistage fitting protocol, and it has been implemented in Smina for docking applications and further improvement of scoring functions.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

添加到收藏夹

Article Chemistry, Medicinal

Comparative Study of Deep Generative Models on Chemical Space Coverage

Jie Zhang et al.

Summary: This study introduces a novel metric based on chemical space coverage for evaluating and comparing the performance of deep molecular generative models. Experimental results show significant performance variations among different generative models when using limited training data, allowing for clear differentiation of models with stronger generalization capabilities.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

添加到收藏夹

Article Chemistry, Medicinal

Generative Models for De Novo Drug Design

Xiaochu Tong et al.

Summary: Generative models in the field of artificial intelligence have made remarkable achievements in drug design, covering various models and applications. Through generative models, compounds can be generated to expand the compound library, design compounds with specific properties, and use some publicly available tools to directly generate molecules.

JOURNAL OF MEDICINAL CHEMISTRY (2021)

添加到收藏夹

Article Biochemical Research Methods

Can machine learning consistently improve the scoring power of classical scoring functions? Insights into the role of machine learning in scoring functions

Chao Shen et al.

Summary: Research has shown that machine learning-based scoring functions outperform classical scoring functions in predicting protein-ligand binding affinity. Gradient boosting decision tree and random forest achieved the best predictions in most cases. The superiority of machine learning-based scoring functions is fully guaranteed when the training set contains sufficient similar targets.

BRIEFINGS IN BIOINFORMATICS (2021)

添加到收藏夹

Review Pharmacology & Pharmacy

Uncertainty quantification in drug design

Lewis H. Mervin et al.

Summary: Machine learning and artificial intelligence are increasingly being utilized in the drug-design process due to the development of novel algorithms, growing access to data, decreasing computation costs, and the advancement of technologies for generating chemically and biologically relevant data. While recent progress has been made in areas such as molecular de novo generation, synthetic route prediction, and property predictions, most research focuses on improving accuracy rather than quantifying uncertainty in predictions. Uncertainty quantification is becoming crucial for autonomous decision making and integrating machine learning and chemistry automation in drug design.

DRUG DISCOVERY TODAY (2021)

添加到收藏夹

Article Chemistry, Physical

Machine Learning for Molecular Simulation

Frank Noé et al.

Annual Review of Physical Chemistry (2020)

添加到收藏夹

Article Chemistry, Medicinal

Tapping on the Black Box: How Is the Scoring Power of a Machine-Learning Scoring Function Dependent on the Training Set?

Minyi Su et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

添加到收藏夹

Letter Biotechnology & Applied Microbiology

Assessing the impact of generative AI on medicinal chemistry

W. Patrick Walters et al.

NATURE BIOTECHNOLOGY (2020)

添加到收藏夹

Review Biotechnology & Applied Microbiology

Rethinking drug design in the artificial intelligence era

Petra Schneider et al.

NATURE REVIEWS DRUG DISCOVERY (2020)

添加到收藏夹

Article Biochemistry & Molecular Biology

Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions

Raquel Rodriguez-Perez et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2020)

添加到收藏夹

Editorial Material Biochemistry & Molecular Biology

Artificial intelligence in chemistry and drug design

Nathan Brown et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2020)

添加到收藏夹

Article Chemistry, Multidisciplinary

Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery

Francesco Gentile et al.

ACS CENTRAL SCIENCE (2020)

添加到收藏夹

Article Multidisciplinary Sciences

Machine learning classification can reduce false positives in structure-based virtual screening

Yusuf O. Adeshina et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

添加到收藏夹

Article Pharmacology & Pharmacy

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

Daniil Polykovskiy et al.

FRONTIERS IN PHARMACOLOGY (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation

Mario Krenn et al.

MACHINE LEARNING-SCIENCE AND TECHNOLOGY (2020)

添加到收藏夹

Review Chemistry, Multidisciplinary

QSAR without borders

Eugene N. Muratov et al.

CHEMICAL SOCIETY REVIEWS (2020)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Drug discovery with explainable artificial intelligence

Jose Jimenez-Luna et al.

NATURE MACHINE INTELLIGENCE (2020)

添加到收藏夹

Article Chemistry, Medicinal

Virtual Chemical Libraries Miniperspective

W. Patrick Walters

JOURNAL OF MEDICINAL CHEMISTRY (2019)

添加到收藏夹

Review Pharmacology & Pharmacy

The next level in chemical space navigation: going far beyond enumerable compound libraries

Torsten Hoffmann et al.

DRUG DISCOVERY TODAY (2019)

添加到收藏夹

Article Chemistry, Medicinal

In Need of Bias Control: Evaluating Chemical Data for Machine Learning in Structure-Based Virtual Screening

Jochen Sieg et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

添加到收藏夹

Article Chemistry, Medicinal

GuacaMol: Benchmarking Models for de Novo Molecular Design

Nathan Brown et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

Machine Learning of Coarse-Grained Molecular Dynamics Force Fields

Jiang Wang et al.

ACS CENTRAL SCIENCE (2019)

添加到收藏夹

Review Chemistry, Multidisciplinary

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Xin Yang et al.

CHEMICAL REVIEWS (2019)

添加到收藏夹

Review Pharmacology & Pharmacy

Deep learning in drug discovery: opportunities, challenges and future prospects

Antonio Lavecchia

DRUG DISCOVERY TODAY (2019)

添加到收藏夹

Article Biotechnology & Applied Microbiology

Deep learning enables rapid identification of potent DDR1 kinase inhibitors

Alex Zhavoronkov et al.

NATURE BIOTECHNOLOGY (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Hidden bias in the DUD-E dataset leads to misleading performance of deep learning in structure-based virtual screening

Lieyang Chen et al.

PLOS ONE (2019)

添加到收藏夹

Article Chemistry, Medicinal

Incorporating Explicit Water Molecules and Ligand Conformation Stability in Machine-Learning Scoring Functions

Jianing Lu et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Definitions, methods, and applications in interpretable machine learning

W. James Murdoch et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

添加到收藏夹

Article Chemistry, Medicinal

Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Prediction Errors for Deep Neural Networks

Isidro Cortes-Ciriano et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

添加到收藏夹

Article Chemistry, Medicinal

Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization

Izhar Wallach et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

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

Rafael Gomez-Bombarelli et al.

ACS CENTRAL SCIENCE (2018)

添加到收藏夹

Article Chemistry, Medicinal

Frechet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery

Kristina Preuer et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Multi-objective de novo drug design with conditional graph generative model

Yibo Li et al.

JOURNAL OF CHEMINFORMATICS (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Improving Scoring-Docking-Screening Powers of Protein-Ligand Scoring Functions using Random Forest

Cheng Wang et al.

JOURNAL OF COMPUTATIONAL CHEMISTRY (2017)

添加到收藏夹

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)

添加到收藏夹

Article Multidisciplinary Sciences

Comment: The FAIR Guiding Principles for scientific data management and stewardship

Mark D. Wilkinson et al.

SCIENTIFIC DATA (2016)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Learning from imbalanced data: open challenges and future directions

Bartosz Krawczyk

PROGRESS IN ARTIFICIAL INTELLIGENCE (2016)

添加到收藏夹

Review Pharmacology & Pharmacy

Machine-learning approaches in drug discovery: methods and applications

Antonio Lavecchia

DRUG DISCOVERY TODAY (2015)

添加到收藏夹

Article Chemistry, Physical

Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach

Raghunathan Ramakrishnan et al.

JOURNAL OF CHEMICAL THEORY AND COMPUTATION (2015)

添加到收藏夹

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Towards dropout training for convolutional neural networks

Haibing Wu et al.

NEURAL NETWORKS (2015)

添加到收藏夹

Article Chemistry, Medicinal

Comparative Assessment of Scoring Functions on an Updated Benchmark: 1. Compilation of the Test Set

Yan Li et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2014)

添加到收藏夹

Article Multidisciplinary Sciences

Quantum chemistry structures and properties of 134 kilo molecules

Raghunathan Ramakrishnan et al.

SCIENTIFIC DATA (2014)

添加到收藏夹

Review Biochemistry & Molecular Biology

Virtual Screening Strategies in Drug Discovery: A Critical Review

A. Lavecchia et al.

CURRENT MEDICINAL CHEMISTRY (2013)

添加到收藏夹

Article Chemistry, Medicinal

Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking

Michael M. Mysinger et al.

JOURNAL OF MEDICINAL CHEMISTRY (2012)

添加到收藏夹

Article Biochemical Research Methods

A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking

Pedro J. Ballester et al.

BIOINFORMATICS (2010)

添加到收藏夹

Article Chemistry, Multidisciplinary

970 Million Druglike Small Molecules for Virtual Screening in the Chemical Universe Database GDB-13

Lorenz C. Blum et al.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2009)

添加到收藏夹

Article Chemistry, Medicinal

On the Art of Compiling and Using 'Drug-Like' Chemical Fragment Spaces

Joerg Degen et al.

CHEMMEDCHEM (2008)

添加到收藏夹

Article Physics, Multidisciplinary

Generalized neural-network representation of high-dimensional potential-energy surfaces

Joerg Behler et al.

PHYSICAL REVIEW LETTERS (2007)

添加到收藏夹

Article Chemistry, Medicinal

Benchmarking sets for molecular docking

Niu Huang et al.

JOURNAL OF MEDICINAL CHEMISTRY (2006)

添加到收藏夹

Article Chemistry, Medicinal

The PDBbind database: Collection of binding affinities for protein-ligand complexes with known three-dimensional structures

RX Wang et al.

JOURNAL OF MEDICINAL CHEMISTRY (2004)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)

添加到收藏夹

Article Statistics & Probability

Greedy function approximation: A gradient boosting machine

JH Friedman

ANNALS OF STATISTICS (2001)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.