Article
Clinical Neurology
Shingo Tsuji, Takeshi Hase, Ayako Yachie-Kinoshita, Taiko Nishino, Samik Ghosh, Masataka Kikuchi, Kazuro Shimokawa, Hiroyuki Aburatani, Hiroaki Kitano, Hiroshi Tanaka
Summary: This study developed a deep learning-based computational framework to identify potential drug target genes through the human protein-protein interaction network, successfully inferring new potential therapeutic target genes for Alzheimer's disease and identifying candidate-compounds for the disease.
ALZHEIMERS RESEARCH & THERAPY
(2021)
Article
Biochemical Research Methods
Qi An, Liang Yu
Summary: This study introduces a new method for predicting drug-target interactions in multiplex networks and achieves accurate results that outperform existing algorithms. Additionally, a reasonable model is proposed to address the widespread negative sampling problem, offering new insights for future research.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Liwei Liu, Qi Zhang, Yuxiao Wei, Qi Zhao, Bo Liao
Summary: BG-DTI is a learning-based framework for predicting drug-target interactions. It combines approaches based on biological features and heterogeneous networks and utilizes a graph representation learning module to learn the features representation of drugs and targets. The fusion descriptors obtained from the module are fed into a random forest classifier for DTI prediction. Evaluation results demonstrate that BG-DTI outperforms other methods.
Article
Biochemical Research Methods
Seokjin Han, Jinhee Hong, So Jeong Yun, Hee Jung Koo, Tae Yong Kim
Summary: Researchers propose a new random walk algorithm named PWN, which enhances the effectiveness of high-throughput data analysis by employing a warped network structure. PWN consistently achieves the best performance among several other known methods.
BMC BIOINFORMATICS
(2023)
Article
Biology
Lei Wang, Leon Wong, Zhan-Heng Chen, Jing Hu, Xiao-Fei Sun, Yang Li, Zhu-Hong You
Summary: Drug discovery is the process of identifying potential new compounds through biological, chemical, and pharmacological means. With the development of artificial intelligence and big data applications, a deep-learning-based prediction model was designed in this study to predict drug-target interactions (DTIs) by combining information on drug structure and protein evolution. The model achieved high prediction accuracy in different types of DTIs and can provide reliable drug candidate targets.
Article
Pharmacology & Pharmacy
Wentao Shi, Manali Singha, Gopal Srivastava, Limeng Pu, J. Ramanujam, Michal Brylinski
Summary: Computational modeling is crucial in modern drug discovery, particularly in predicting binding molecules. Pocket2Drug is a promising computational approach that uses data mining and machine learning to predict binding molecules for a given ligand binding site.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Biochemistry & Molecular Biology
Riccardo Concu, Maria Natalia Dias Soeiro Cordeiro, Martin Perez-Perez, Florentino Fdez-Riverola
Summary: This study developed a novel multi-target machine learning (MTML) quantitative structure-activity relationship (QSAR) model for predicting interactions between different drugs and enzyme targets. The model was based on a large dataset of drug-enzyme pairs and used topological drug features and artificial neural network (ANN) multi-layer perceptron (MLP). The validated model showed an overall accuracy of over 96%. To maximize its diffusion, a public and accessible web-based tool was developed for users to make their own predictions.
Article
Biochemical Research Methods
Minwoo Pak, Sangseon Lee, Inyoung Sung, Bonil Koo, Sun Kim
Summary: Drug response prediction (DRP) is crucial for precision medicine to anticipate patient reactions to drugs. While most studies use cell line transcriptome data and drug chemical structures to predict drug response, this study proposes a framework that leverages drug target interaction (DTI) information to improve deep learning-based DRP models. By computing gene perturbation scores through network propagation techniques, the framework integrates this DTI information with existing DRP models. The results show significant performance boosts, especially when dealing with unknown drugs.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Liang Yu, Mingfei Xia, Qi An
Summary: In this paper, a Network Embedding frameWork in MultIplex Network (NEWMIN) is proposed to predict synthetic drug combinations. By integrating information from multiple networks and determining their importance, several novel drug combinations have been discovered, with better performance compared to other methods.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Pharmacology & Pharmacy
Jiye Wang, Lin Luo, Qiong Ding, Zengrui Wu, Yayuan Peng, Jie Li, Xiaoqin Wang, Weihua Li, Guixia Liu, Bo Zhang, Yun Tang
Summary: This study proposed a systematic framework to discover potential therapeutic targets for vitiligo, and revealed the mechanism of kaempferide through a multi-target strategy.
FRONTIERS IN PHARMACOLOGY
(2021)
Article
Biochemical Research Methods
Nelson R. C. Monteiro, Bernardete Ribeiro, Joel P. Arrais
Summary: This study introduces a deep learning architecture model that utilizes Convolutional Neural Networks to extract representations from protein sequences and compound SMILES strings for binary classification in drug-target interaction prediction. The results demonstrate improved performance using CNNs compared to traditional descriptors.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Review
Pharmacology & Pharmacy
Shukai Gu, Huanxiang Liu, Liwei Liu, Tingjun Hou, Yu Kang
Summary: Kinases play a crucial role in cellular processes and accurate kinase-profiling prediction is vital for drug discovery. This review provides an overview of the latest advancements in machine learning and deep learning models for kinase profiling, discussing the challenges and future directions in this field.
DRUG DISCOVERY TODAY
(2023)
Review
Pharmacology & Pharmacy
Haoyang Liu, Zhiguang Fan, Jie Lin, Yuedong Yang, Ting Ran, Hongming Chen
Summary: Drug combination therapy is a common strategy for treating complex diseases. Efficient identification of appropriate drug combinations using computational methods is urgently needed due to the high cost of experimental screening. Recent studies have shown that deep learning algorithms have the flexibility to integrate multimodal data and achieve state-of-the-art performance, making deep-learning-based prediction of drug combinations an important tool in future drug discovery.
DRUG DISCOVERY TODAY
(2023)
Article
Medicine, Research & Experimental
Thomas R. Lane, Fabio Urbina, Laura Rank, Jacob Gerlach, Olga Riabova, Alexander Lepioshkin, Elena Kazakova, Anthony Vocat, Valery Tkachenko, Stewart Cole, Vadim Makarov, Sean Ekins
Summary: Overall, tuberculosis remains a major global health challenge requiring the development of new drug treatments. Machine learning approaches have been utilized to identify new active compounds and develop classification models. New models for scoring compound libraries and visualizing molecules in chemical property space have been provided.
MOLECULAR PHARMACEUTICS
(2022)
Review
Pharmacology & Pharmacy
Ke Han, Peigang Cao, Yu Wang, Fang Xie, Jiaqi Ma, Mengyao Yu, Jianchun Wang, Yaoqun Xu, Yu Zhang, Jie Wan
Summary: Drug-drug interactions are important in drug research and can cause adverse reactions in patients. Computer methods, including identifying known or predicting unknown interactions, have been used to address this issue. This review focuses on the progress of machine learning in predicting unknown drug interactions, discussing databases, methods, and challenges for further research.
FRONTIERS IN PHARMACOLOGY
(2022)