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, Multidisciplinary
Yunjiang Zhang et al.
Summary: In drug design, developing a new rapid and generalizable drug design method is of great value. This study proposed a general model based on reinforcement learning combined with drug-target interaction to design new molecules based on different protein targets. The method used recurrent neural network molecular modeling and the drug-target affinity model as the reward function. It only required the information of a one-dimensional amino acid sequence, without the need for the three-dimensional structure and active sites of protein targets. This approach showed promising results in producing drugs similar to marketed drugs and designing molecules with better binding energy.
Article
Chemistry, Medicinal
Marco Ballarotto et al.
Summary: Generative neural networks trained on SMILES can design innovative bioactive molecules de novo. These models have usually been fine-tuned on template molecules but it is challenging to apply them to orphan targets with few known ligands.
JOURNAL OF MEDICINAL CHEMISTRY
(2023)
Review
Multidisciplinary Sciences
Anastasiia V. Sadybekov et al.
Summary: Computer-aided drug discovery has experienced a significant shift towards computational technologies for efficient ligand screening. This shift is driven by the availability of vast ligand data, abundant computing capacities, and virtual libraries of drug-like small molecules. Recent advances in deep learning predictions of ligand properties and target activities, as well as structure-based virtual screening, have the potential to reshape the drug discovery and development process. The rapid identification of diverse, potent, target-selective, and drug-like ligands to protein targets can democratize the drug discovery process, enabling cost-effective development of safer and more effective treatments.
Article
Biotechnology & Applied Microbiology
Stephen J. J. Ruberg et al.
Summary: The pharmaceutical industry and global regulators often use frequentist statistical methods for evaluation and approval of new treatments. However, Bayesian statistical approaches, which incorporate existing data, have the potential to reduce time and cost in drug development. Despite advances, these methods are underutilized due to barriers and this Perspective highlights their value and recommends approaches to address the issue.
NATURE REVIEWS DRUG DISCOVERY
(2023)
Article
Chemistry, Multidisciplinary
Yangyang Chen et al.
Summary: In this paper, a deep learning model called DeepTarget is proposed to generate novel molecules solely based on the amino acid sequence of the target protein, reducing the heavy reliance on prior knowledge. The model consists of three modules: Amino Acid Sequence Embedding, Structural Feature Inference, and Molecule Generation. The validity of the generated molecules is demonstrated through benchmark platforms and metrics such as drug-target affinity and molecular docking.
JOURNAL OF CHEMINFORMATICS
(2023)
Review
Pharmacology & Pharmacy
Edgar Lopez-Lopez et al.
Summary: Studying structure-inactivity relationships is crucial for understanding biological activity, but the lack of inactivity data limits the development and application of predictive models. The scientific community should disclose and analyze high-confidence activity data considering both 'active' and 'inactive' compounds.
DRUG DISCOVERY TODAY
(2022)
Article
Chemistry, Medicinal
Derek van Tilborg et al.
Summary: Machine learning plays a crucial role in drug discovery and chemistry. However, the effect of activity cliffs - molecules that are structurally similar but exhibit significant differences in potency - on model performance has received limited attention. In this study, we benchmarked 24 machine and deep learning approaches and found that machine learning methods based on molecular descriptors outperformed more complex deep learning methods in predicting the properties of activity cliffs. Our findings highlight the need for dedicated metrics and novel algorithms to address the limitation posed by activity cliffs in molecular machine learning models.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2022)
Article
Chemistry, Multidisciplinary
Jonas Verhellen
Summary: Computer-assisted design of small molecules has gained significant attention in both academia and industry, facilitated by the use of data-driven techniques. While deep generative models show promise in generating molecules with desired properties, they require substantial data and computational power. However, traditional techniques like graph-based genetic algorithms have proven to be efficient alternatives. The importance of exploring chemical space has been emphasized in the development of deep generative models and advanced genetic algorithms.
Article
Leah Frye et al.
Drug Discovery Today: Technologies
(2021)
Review
Chemistry, Multidisciplinary
Jose Pena-Guerrero et al.
Summary: Machine learning is transforming biomolecular interaction description and calculation, promising impact on molecular and drug design, chemical biology, among others. Chemical design proposals from algorithms may be innovative and feasible, but challenges remain in data availability, diversity, and quality, as well as in interpretability, validation, and model reuse.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2021)
Article
Biochemical Research Methods
Yuanfei Dai et al.
Summary: This paper introduces a new KG embedding framework for drug-drug interaction tasks using adversarial autoencoders to generate high-quality negative samples and train embeddings for drugs and interactions. Experimental results show significant improvements in link prediction and DDI classification tasks, outperforming competitive baselines.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Multidisciplinary Sciences
Zhenpeng Zhou et al.
SCIENTIFIC REPORTS
(2019)
Review
Chemistry, Multidisciplinary
Yudong Cao et al.
Article
Chemistry, Medicinal
Alfonso T. Garcia-Sosa
FUTURE MEDICINAL CHEMISTRY
(2019)
Article
Chemistry, Multidisciplinary
Rafael Gomez-Bombarelli et al.
ACS CENTRAL SCIENCE
(2018)
Article
Biochemical Research Methods
Letian Kuai et al.
Article
Multidisciplinary Sciences
Markus Reiher et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2017)
Review
Engineering, Electrical & Electronic
Bobak Shahriari et al.
PROCEEDINGS OF THE IEEE
(2016)
Article
Biochemistry & Molecular Biology
A. T. Garcia-Sosa et al.
CURRENT MEDICINAL CHEMISTRY
(2012)
Review
Pharmacology & Pharmacy
Masaya Orita et al.
DRUG DISCOVERY TODAY
(2010)
Article
Mathematical & Computational Biology
Yujun Wu et al.
BIOMETRICAL JOURNAL
(2008)
Article
Medicine, Research & Experimental
KJ Carroll
CONTROLLED CLINICAL TRIALS
(2003)
Review
Physics, Multidisciplinary
WH Zurek
REVIEWS OF MODERN PHYSICS
(2003)
