Knowledge Graphs are becoming a key instrument for biomedical knowledge discovery and modeling. These approaches rely on structured data, e.g. about related proteins or genes, and form cause-ande ect networks or { if enriched with literature data and other linked data sources { knowledge graphs. A key aspect of analysis on these graphs is the missing context. Here we present a novel semantic approach towards a context enriched Knowledge Graph for biomedical research utilizing data integration with linked data. The result is a general graph concept that can be used for graph embeddings in di erent contexts or layers.
Introduction
Biological and medical researchers considering computational approaches rely
on structured data, e.g. about related proteins or genes, see [
This and the emerging improvements on large-scale Knowledge Graphs and
machine learning approaches are the motivation for our novel approach on
semantic Knowledge Graph embeddings for biomedical research utilizing data
integration with linked open data. Several similar approaches (often in the context
of drug-repurposing) have been described like Bio2RDF [
Dorpinghaus, Jacobs et al.
The basis for generating our large-scale Knowledge Graph representation is the biomedical literature, e.g. MedLine and PubMed4. These articles or abstracts are the source for biological relations mentioned above. In addition, meta information like authors, journals, keywords (so called MeSH-Terms, Medical Subject Headings), etc. are freely available. Ontologies can be used to contextualize entities in the Knowledge Graph providing biological or medical relations (cf. 5). Every ontology will form another knowledge (sub-)graph.
Using methods of natural language processing (NLP) and text mining, we can combine and link these knowledge graphs to a giant and very dense new knowledge graph. This will meet a very general de nition of context. We can see every knowledge (sub-)graph as context to another. Biological expressions are context of the corresponding literature, authors are context of a text, named entities from ontologies found in a text are context to it or to the corresponding biological expressions.
Our overarching integration schema is based on the Biological Expression
Language6 is widely applied in biomedical domain to convert unstructured
textual knowledge into a computable form. The BEL statements that form
knowledge graphs are semantic triples that consist of concepts, functions and
relationships. Thus they can be easily added to a knowledge graph representing another
layer or context. An example for a large Alzheimer network can be found in [
In the next section we describe the novel concept of semantic graph embeddings within large-scale Knowledge Graphs. We will present several use-cases 4 See https://www.ncbi.nlm.nih.gov/pubmed/. 5 OLS, https://www.ebi.ac.uk/ols/index 6 BEL, www.openbel.org and application examples as well as the semantic interoperability layer using RDF and SPARQL. 2
Knowledge Graph architecture A Knowledge Graph is a systematic way to connect information and data to represent common knowledge. As described above, the context is the most important topic to generate knowledge or even wisdom.
We de ne knowledge graphs G = (E; R) with entities e 2 E coming from a
formal structure like an ontology O, see [
We de ne contexts C = fc1; :::; cmg as a nite, discrete set. Every node v 2 G and every edge r 2 R may have one ore more contexts c 2 C denoted by con(v) or con(r). It is also possible to set con(v) = ;. Thus we have a mapping con : E [R ! P(C). If we use a quite general approach towards context, we may set C = E. Thus every inter-ontology relation de nes context of two entities, but also the relations within an ontology can be seen as context, see gure 1 for an illustration. Here every context is identi ed as a layer (e.g. a document layer, a molecular layer, a mechanism layer, ...). This allows new connections between di erent contexts or layers: If two edges e1; e2 2 R1 are connected and e01; e02 2 R2 with con(e1) = e01 and con(e2) = e02 are not connected, we may add another edge (e1; e2) with provenance information that this connection comes from a di erent context, namely R2. Since every layer or context can be seen as a subgraph forming a surface we can denote the relation between two layers a knowledge graph embedding.
It is also possible to get the context of a subgraph Ri G which can be denominated by con(Ri) or with the notation of graph theory as the extended induced subgraph by the vertex set Ei from Ri given by Gc[Ei]. This is quite trivial if context from Ri can only be annotated to vertices in G. Then
Gc[Ei] = G[Ei] [ f(e; e0) 8e0 2 N (e); e 2 Eig Here conjEi = Gc[Ei] is the context of Ei restricted to the set of edges (relations) in the graph. The two edges e0; e00 are implicitly given by this context. It is quite easy to see that the restriction on context annotated to edges makes the problem more easy from a computational perspective. Nevertheless, context on edges is needed from a real-world perspective.
The technical design was done with respect to the microservice architecture
of SCAIView [
Jacobs et
al. l e B s a h l e B s a h
l HGNeC B s a h hasBel a tion hasBel BELRelation BELRelation BELRelation BELRelation hashBaeslEvidenc BELRelation n tio ela R L E B el B s a h el B s haHsSubgraph ha tion unc hasF ha sF un c tion for some illustrations of di erent context layers. questions can b e formulated as subgraph structures of
For the example,
semaninitial knowledge We may think of complex examples, e.g.
"Give me all pathways from A to
B in the context of
Disease
C fo cusing on clinical trials".
to of context,
networks Hyp othesis generation within medical research and digital health may lead to search which for genomic or moleculare patterns, diagnosis or build longitudinal mo dels build the basis for a multitude of predictive and p ersonalised medicine ML and
AI approaches. This information system can b e used to retrieve data by context (cohort size, settings, results, ..) and by content (imaging data, genomic or moleculare measures, ...).
For example, this system may answer questions like Give me a clinical trial to repro duce my results or to apply me literature for phenotyp e A, disease B age b etween C and my D mo del or
Here we presented a novel approach that annotates research data with context information. The result is a knowledge graph representation of data, the context graph. It contains computable statement representation (e.g. RDF or BEL). This graph allows to compare research data records from di erent sources as well as the selection of relevant data sets using graph-theoretical algorithms.