Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Aug 11:5:932665.
doi: 10.3389/frai.2022.932665. eCollection 2022.

Rare disease-based scientific annotation knowledge graph

Qian Zhu  1 , Chunxu Qu  2 , Ruizheng Liu  2 , Gunjan Vatas  3 , Andrew Clough  4 , Ðắc-Trung Nguyễn  5 , Eric Sid  2 , Ewy Mathé  1 , Yanji Xu  2
Affiliations

Rare disease-based scientific annotation knowledge graph

Qian Zhu et al. Front Artif Intell. .

Abstract

Rare diseases (RDs) are naturally associated with a low prevalence rate, which raises a big challenge due to there being less data available for supporting preclinical and clinical studies. There has been a vast improvement in our understanding of RD, largely owing to advanced big data analytic approaches in genetics/genomics. Consequently, a large volume of RD-related publications has been accumulated in recent years, which offers opportunities to utilize these publications for accessing the full spectrum of the scientific research and supporting further investigation in RD. In this study, we systematically analyzed, semantically annotated, and scientifically categorized RD-related PubMed articles, and integrated those semantic annotations in a knowledge graph (KG), which is hosted in Neo4j based on a predefined data model. With the successful demonstration of scientific contribution in RD via the case studies performed by exploring this KG, we propose to extend the current effort by expanding more RD-related publications and more other types of resources as a next step.

Keywords: PubMed; knowledge graph; natural language processing; rare disease (RD); scientific annotations.

PubMed Disclaimer

Conflict of interest statement

GV worked at HHS and is employed by GMG ArcData, LLC. AC worked at HHS and is employed by Data Decode, LLC. Ð-TN worked at NCATS and is employed by Pfizer. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
An example of exploring Adrenomyodystrophy-associated literature [A: a graph containing semantic annotations generated from the original paper for Adrenomyodystrophy; B: an expanded graph from A via one disease node of “adrenal insufficiency”; C: an expanded graph from A via one author node of “Ropers.” The attached Cypher Query 0 was applied to generate A. (B,C) can be generated by clicking the nodes circled in A, respectively].
Figure 2
Figure 2
The study workflow.
Figure 3
Figure 3
Data model and an example of information (data properties) about one article node.
Figure 4
Figure 4
Overview of EDS research collected in PubMed between 1900 and 2021. (A) Research on EDS increased over years since its first publication in 1958. (B) Number of articles on each type of EDS with the bar of the parent EDS (GARD:0006322) in red. (C) Heatmap showing multiple types of EDS (column) discussed in one article (row), in dark red indicating the disease mentioned in an article.
Figure 5
Figure 5
Discovery of alternative use of dextromethorphan for other rare diseases. (A) Dextromethorphan was widely studied for glycine encephalopathy (GE, GARD:0007219). (B) Dextromethorphan has potential usage for seven rare neurological diseases including Rett syndrome. (C) Five RDs including Ectopia pupillae and Pustular psoriasis have been studied as side effects of Dextromethorpha.
See this image and copyright information in PMC

References

    1. Amberger J. S., Bocchini C. A., Schiettecatte F., Scott A. F., Hamosh A. (2015). OMIM. org: Online Mendelian Inheritance in Man (OMIM®), an online catalog of human genes and genetic disorders. Nucl. Acids Res. 43, D789–D798. 10.1093/nar/gku1205 - DOI - PMC - PubMed
    1. Aronson A. R., Lang F.-M. (2010). An overview of MetaMap: historical perspective and recent advances. J. Am. Med. Inform. Assoc. 17, 229–236. 10.1136/jamia.2009.002733 - DOI - PMC - PubMed
    1. Chen C. L., Cheng M. H., Kuo C. F., Cheng Y. L., Li M. H., Chang C. P., et al. . (2018). Dextromethorphan attenuates NADPH oxidase-regulated glycogen synthase kinase 3β and NF-κB activation and reduces nitric oxide production in group A streptococcal infection. Antimicrob. Agents Chemotherapy 62, e02045–e02017. 10.1128/AAC.02045-17 - DOI - PMC - PubMed
    1. Gow P. J., Smallwood R., Angus P. W., Smith A., Wall A., Sewell R. B., et al. . (2000). Diagnosis of Wilson's disease: an experience over three decades. Gut 46, 415–419. 10.1136/gut.46.3.415 - DOI - PMC - PubMed
    1. Jia J., An Z., Ming Y., Guo Y., Li W., Liang Y., et al. . (2017). eRAM: encyclopedia of rare disease annotations for precision medicine. Nucl. Acids Res. 46, D937–D943. 10.1093/nar/gkx1062 - DOI - PMC - PubMed