Biomedical Knowledge Graph (BiomedKG)

Context:
- It can be created by a BiogMedKG Creation Task (supported by a BioMedKG creation system).
- It can reference Biomedical Literature, including scientific literature and clinical data literature.
- It can support Biomedical Tasks, such as: Drug Discovery, Disease Understanding, Personalized Medicine, and other Healthcare Applications.
- It can support complex queries over connected Biomedical Data, and provide a structured representation of knowledge.
- It can be associated to a Biomedical Ontology.
- …
Example(s):
- BioKG.
- Watson's Medicine KG.
- Knowlife, (P Ernst, A Siu, G Weikum - BMC bioinformatics, 2015).
- DRKG, focused on drug discovery (Zeng, Tu, et al., 2022).
- …
Counter-Example(s):
- Government KG, such as OpenGov's KG.
- Legal KG.
See: Cinical Knowledge Extraction, Clinical Research KG.

References

(Cenikj et al., 2023) ⇒ Gjorgjina Cenikj, Lidija Strojnik, Risto Angelski, Nives Ogrinc, Barbara Koroušić Seljak, and Tome Eftimov. (2023). “From Language Models to Large-scale Food and Biomedical Knowledge Graphs.” In: Scientific reports, 13(1).
- QUOTE: ... Knowledge about the interactions between dietary and biomedical factors is scattered throughout uncountable research articles in an unstructured form (e.g., text, images, etc.) and requires automatic structuring so that it can be provided to medical professionals in a suitable format. Various biomedical knowledge graphs exist, however, they require further extension with relations between food and biomedical entities. ...
- … A Knowledge Graph (KG) is a type of KB, where knowledge is stored in the form of entities characterized by some attributes, and relations connecting the entities. ...

(H. Fei et al., 2021) ⇒ H. Fei, Y. Ren, Y. Zhang, D. Ji, X. Liang. (2021). “Enriching contextualized language model from knowledge graph for biomedical information extraction.", Briefings in Bioinformatics, Oxford Academic, 22(5), bbaa294. [doi:10.1093/bib/bbaa294]
- ABSTRACT: ... We then propose to enrich a contextualized language model by integrating a large scale of biomedical knowledge graphs (namely, BioKGLM). In order to effectively encode knowledge, we explore a three-stage training procedure and introduce different fusion strategies to facilitate knowledge injection. Experimental results on multiple tasks show that BioKGLM consistently outperforms state-of-the-art extraction models. A further analysis proves that BioKGLM can capture the underlying relations between biomedical knowledge concepts, which are crucial for BioIE. ...
- QUOTE: ... We inject a large amount of biomedical knowledge graph information during such post-training procedure. In order to better inject biomedical knowledge, we consider different injection. ...

(A. Harnoune et al., 2021) ⇒ A. Harnoune, M. Rhanoui, M. Mikram, S. Yousfi, et al. (2021). “BERT based clinical knowledge extraction for biomedical knowledge graph construction and analysis.", Computer Methods and Programs in Biomedicine, Elsevier, 208, 106207. [doi:10.1016/j.cmpb.2021.106207]
- QUOTE: "… and analysis of a biomedical knowledge graph from textual data represented by clinical notes, to do this we compare the important versions of BERT in the biomedical domain and we …"

(A. Waagmeester et al., 2020) ⇒ A. Waagmeester, G. Stupp, S. Burgstaller-Muehlbacher, et al. (2020). “Wikidata as a knowledge graph for the life sciences.", Elife, eLife Sciences Publications, 9, e52614. [doi:10.7554/eLife.52614]
- QUOTE: "… enriching the biomedical knowledge graph within Wikidata, both … representative biomedical use cases on how Wikidata can … knowledge graph that epitomizes the FAIR principles. …"
(D. Chang et al., 2020) ⇒ D. Chang, I. Balažević, C. Allen, D. Chawla, et al. (2020). “Benchmark and best practices for biomedical knowledge graph embeddings.", Proceedings of the National Academy of Sciences, NCBI. [doi:10.1101/2020.02.27.968735]
- QUOTE: ... A recent family of models called knowledge graph embeddings have shown promising… in the biomedical domain. We train several state-of-the-art knowledge graph embedding models…"
(A. Rossanez et al., 2020) ⇒ A. Rossanez, J.C. Dos Reis, et al. (2020). “KGen: a knowledge graph generator from biomedical scientific literature.", BMC Medical Informatics and Decision Making, 20, 300. [doi:10.1186/s12911-020-01245-9]
- QUOTE: ... In this sense, we may consider an ontology-linked knowledge graph (KG) = (\… We introduce our KGen (a shorthand for Knowledge Graph Generation) method and tool…"

(S. Sang et al., 2018) ⇒ S. Sang, Z. Yang, X. Liu, L. Wang, H. Lin, J. Wang, et al. (2018). “GrEDeL: A knowledge graph embedding based method for drug discovery from biomedical literatures.", IEEE, Conference Proceedings, 1248-1253. [doi:10.1109/BIBM.2018.8513284]
- QUOTE: "Firstly, a biomedical knowledge graph… biomedical knowledge graph constructed in this work differentiates semantic types of entities. Secondly, we proposed to use the knowledge graph…"

(P. Ernst et al., 2015) ⇒ P. Ernst, A. Siu, G. Weikum. (2015). “Knowlife: a versatile approach for constructing a large knowledge graph for biomedical sciences.", BMC Bioinformatics, Springer, 16(1), 157. [doi:10.1186/s12859-015-0848-7]
- QUOTE: ... Biomedical knowledge bases (KB’s) have become important assets in life sciences. Prior work on KB construction has three major limitations. First, most biomedical KBs…"