Turewicz Michael, Frericks-Zipper Anika, Stepath Markus, Schork Karin, Ramesh Spoorti, Marcus Katrin, Eisenacher Martin
Medizinisches Proteom-Center, Ruhr University Bochum, Bochum 44801, Germany.
Center for Protein Diagnostics (PRODI), Medical Proteome Analysis, Ruhr University Bochum, Bochum 44801, Germany.
Bioinform Adv. 2021 Aug 18;1(1):vbab015. doi: 10.1093/bioadv/vbab015. eCollection 2021.
Because of the steadily increasing and already manually unmanageable total number of biomarker-related articles in biomedical research, there is a need for intelligent systems that extract all relevant information from biomedical texts and provide it as structured information to researchers in a user-friendly way. To address this, BIONDA was implemented as a free text mining-based online database for molecular biomarkers including genes, proteins and miRNAs and for all kinds of diseases. The contained structured information on published biomarkers is extracted automatically from Europe PMC publication abstracts and high-quality sources like UniProt and Disease Ontology. This allows frequent content updates.
BIONDA is freely accessible via a user-friendly web application at http://bionda.mpc.ruhr-uni-bochum.de. The current BIONDA code is available at GitHub via https://github.com/mpc-bioinformatics/bionda.
Supplementary data are available at online.
由于生物医学研究中与生物标志物相关的文章总数持续增加且已难以手动管理,因此需要智能系统从生物医学文本中提取所有相关信息,并以用户友好的方式将其作为结构化信息提供给研究人员。为解决这一问题,BIONDA被实现为一个基于文本挖掘的免费在线数据库,涵盖分子生物标志物(包括基因、蛋白质和微小RNA)以及各类疾病。所包含的已发表生物标志物的结构化信息是从欧洲PMC出版物摘要以及诸如UniProt和疾病本体等高质量来源中自动提取的。这使得内容能够频繁更新。
可通过用户友好的网络应用程序在http://bionda.mpc.ruhr-uni-bochum.de免费访问BIONDA。当前的BIONDA代码可通过https://github.com/mpc-bioinformatics/bionda在GitHub上获取。
补充数据可在网上获取。