Suppr超能文献

哮喘知识图谱:利用公共数据库和科学文献挖掘哮喘-环境交互作用的知识图谱。

AsthmaKGxE: An asthma-environment interaction knowledge graph leveraging public databases and scientific literature.

机构信息

TicLab, College of Engineering and Architecture, International University of Rabat, Morocco; Alqualsadi, Rabat IT Center, ENSIAS, Mohammed V University in Rabat, Morocco.

TicLab, College of Engineering and Architecture, International University of Rabat, Morocco; Faculty of Engineering, University of Leeds, United Kingdom.

出版信息

Comput Biol Med. 2022 Sep;148:105933. doi: 10.1016/j.compbiomed.2022.105933. Epub 2022 Aug 2.

Abstract

MOTIVATION

Asthma is a complex heterogeneous disease resulting from intricate interactions between genetic and non-genetic factors related to environmental and psychosocial aspects. Discovery of such interactions can provide insights into the pathophysiology and etiology of asthma. In this paper, we propose an asthma knowledge graph (KG) built using a hybrid methodology for graph-based modeling of asthma complexity with a focus on environmental interactions. Using a heterogeneous set of public sources, we construct a genetic and pharmacogenetic asthma knowledge graph. The construction of this KG allowed us to shed more light on the lack of curated resources focused on environmental influences related to asthma. To remedy the lack of environmental data in our KG, we exploit the biomedical literature using state-of-the-art natural language processing and construct the first Asthma-Environment interaction catalog incorporating a continuously updated ensemble of environmental, psychological, nutritional and socio-economic influences. The catalog's most substantiated results are then integrated into the KG.

RESULTS

The resulting environmentally rich knowledge graph "AsthmaKGxE" aims to provide a resource for several potential applications of artificial intelligence and allows for a multi-perspective study of asthma. Our insight extraction results indicate that stress is the most frequent asthma association in the corpus, followed by allergens and obesity. We contend that studying asthma-environment interactions in more depth holds the key to curbing the complexity and heterogeneity of asthma.

AVAILABILITY

A user interface to browse and download the extracted catalog as well as the KG are available at http://asthmakgxe.moreair.info/. The code and supplementary data are available on github (https://github.com/ChaiAsaad/MoreAIRAsthmaKGxE).

摘要

动机

哮喘是一种复杂的异质疾病,由遗传和非遗传因素与环境和社会心理方面相关的复杂相互作用导致。发现这些相互作用可以深入了解哮喘的病理生理学和病因。在本文中,我们提出了一种使用混合方法构建的哮喘知识图(KG),该方法侧重于环境相互作用,基于图的方法对哮喘的复杂性进行建模。使用一组异构的公共资源,我们构建了一个遗传和药物遗传学哮喘知识图。该 KG 的构建使我们更深入地了解缺乏针对与哮喘相关的环境影响的精心策划资源的问题。为了弥补我们 KG 中环境数据的不足,我们利用最先进的自然语言处理技术从生物医学文献中挖掘信息,并构建了第一个包含不断更新的环境、心理、营养和社会经济影响的综合集合的哮喘-环境相互作用目录。该目录最有根据的结果随后被整合到 KG 中。

结果

生成的富含环境信息的知识图“哮喘 KGxE”旨在为人工智能的几个潜在应用提供资源,并允许从多个角度研究哮喘。我们的见解提取结果表明,在语料库中,压力是最常见的哮喘关联,其次是过敏原和肥胖。我们认为,更深入地研究哮喘与环境的相互作用是控制哮喘复杂性和异质性的关键。

可用性

可在 http://asthmakgxe.moreair.info/ 浏览和下载提取目录以及 KG 的用户界面。代码和补充数据可在 github(https://github.com/ChaiAsaad/MoreAIRAsthmaKGxE)上获得。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验