Context mining and graph queries on giant biomedical knowledge graphs

Abstract

Contextual information is widely considered for NLP and knowledge discovery in life sciences since it highly influences the exact meaning of natural language. The scientific challenge is not only to extract such context data, but also to store this data for further query and discovery approaches. Classical approaches use RDF triple stores, which have serious limitations. Here, we propose a multiple step knowledge graph approach using labeled property graphs based on polyglot persistence systems to utilize context data for context mining, graph queries, knowledge discovery and extraction. We introduce the graph-theoretic foundation for a general context concept within semantic networks and show a proof of concept based on biomedical literature and text mining. Our test system contains a knowledge graph derived from the entirety of PubMed and SCAIView data and is enriched with text mining data and domain-specific language data using Biological Expression Language. Here, context is a more general concept than annotations. This dense graph has more than 71M nodes and 850M relationships. We discuss the impact of this novel approach with 27 real-world use cases represented by graph queries. Storing and querying a giant knowledge graph as a labeled property graph is still a technological challenge. Here, we demonstrate how our data model is able to support the understanding and interpretation of biomedical data. We present several real-world use cases that utilize our massive, generated knowledge graph derived from PubMed data and enriched with additional contextual data. Finally, we show a working example in context of biologically relevant information using SCAIView.

Knowledge Graph: A Survey

“…Their work suggests that Semantic web technologies can significantly improve the efficiency and effectiveness of the drug discovery process and help identify new drug targets, repurpose existing drugs, and manage and analyse complex data. [16] presented an analysis of COVID-19 Knowledge Graph construction and applications. The study reviewed various methods and techniques for constructing knowledge graphs, including rule-based systems, machine-learning algorithms, and hybrid approaches.…”

Hypergraph-based data modeling for binary classification

“…Up to our knowledge, no research targeting exactly the same topic has been already published in the relevant literature. On the other hand, hypergraphs have been widely used in research on properties of social, collaboration, or biological networks [3,5,17]. In particular, they have been applied for many application scenarios, including clustering and community detection, [1,3,18], modeling virus spreading networks [4], exploring biomedical knowledge graphs [17], finding genes which are central in host response to viral infection [5], or prediction for e-commerce [6].…”

“…On the other hand, hypergraphs have been widely used in research on properties of social, collaboration, or biological networks [3,5,17]. In particular, they have been applied for many application scenarios, including clustering and community detection, [1,3,18], modeling virus spreading networks [4], exploring biomedical knowledge graphs [17], finding genes which are central in host response to viral infection [5], or prediction for e-commerce [6]. The proposed hypergraph-based data representation and importance rating models are mainly inspired by research presented in [1,2,6].…”

Hypergraph-based importance assessment for binary classification data

“…To the authors' knowledge, no research directly addressing this specific problem has already been published in the relevant literature. However, hypergraphs have already been widely used in machine learning, particularly in research on properties of social, collaboration, or biological networks [2,4,24]. They have been applied for many application scenarios, including clustering and community detection [3,4,25], modeling virus spreading networks [1], exploring biomedical knowledge graphs [24], finding genes which are central in host response to viral infection [2], or prediction for e-commerce [5].…”

“…However, hypergraphs have already been widely used in machine learning, particularly in research on properties of social, collaboration, or biological networks [2,4,24]. They have been applied for many application scenarios, including clustering and community detection [3,4,25], modeling virus spreading networks [1], exploring biomedical knowledge graphs [24], finding genes which are central in host response to viral infection [2], or prediction for e-commerce [5]. Attention should also be paid to recent developments in hypergraph neural networks [12,13,26], and hypergraph signal processing [16,27].…”