期刊
JOURNAL OF CHEMICAL INFORMATION AND MODELING
卷 -, 期 -, 页码 -出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jcim.3c00395
关键词
-
NAFLDkb is a specialized knowledge base and platform for computer-aided drug design against nonalcoholic fatty liver disease (NAFLD). It provides associations of drug-related entities as individual knowledge graphs, using curated information from diverse source materials and public databases. Practical drug discovery tools, including chemical structure search, drug-likeness screening, knowledge-based repositioning, and research article annotation, are implemented in the web interface. Case studies demonstrate the clinical reliability and potential of NAFLDkb in identifying novel drug-disease associations and accelerating NAFLD drug development. NAFLDkb is freely accessible at https://www.biosino.org/nafldkb and regularly updated with the latest findings.
Nonalcoholic fatty liver disease (NAFLD) is the mostcommon chronicliver disease with a broad spectrum of histologic manifestations.The rapidly growing prevalence and the complex pathologic mechanismsof NAFLD pose great challenges for treatment development. Despitetremendous efforts devoted to drug development, there are no FDA-approvedmedicines yet. Here, we present NAFLDkb, a specialized knowledge baseand platform for computer-aided drug design against NAFLD. With multiperspectiveinformation curated from diverse source materials and public databases,NAFLDkb presents the associations of drug-related entities as individualknowledge graphs. Practical drug discovery tools that facilitate theutilization and expansion of NAFLDkb have also been implemented inthe web interface, including chemical structure search, drug-likenessscreening, knowledge-based repositioning, and research article annotation.Moreover, case studies of a knowledge graph repositioning model anda generative neural network model are presented herein, where threerepositioning drug candidates and 137 novel lead-like compounds werenewly established as NAFLD pharmacotherapy options reusing data recordsand machine learning tools in NAFLDkb, suggesting its clinical reliabilityand great potential in identifying novel drug-disease associationsof NAFLD and generating new insights to accelerate NAFLD drug development.NAFLDkb is freely accessible at https://www.biosino.org/nafldkb and will be updated periodically with the latest findings.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据