Using predicate and provenance information from a knowledge graph for drug efficacy screening

Abstract

BackgroundBiomedical knowledge graphs have become important tools to computationally analyse the comprehensive body of biomedical knowledge. They represent knowledge as subject-predicate-object triples, in which the predicate indicates the relationship between subject and object. A triple can also contain provenance information, which consists of references to the sources of the triple (e.g. scientific publications or database entries). Knowledge graphs have been used to classify drug-disease pairs for drug efficacy screening, but existing computational methods have often ignored predicate and provenance information. Using this information, we aimed to develop a supervised machine learning classifier and determine the added value of predicate and provenance information for drug efficacy screening. To ensure the biological plausibility of our method we performed our research on the protein level, where drugs are represented by their drug target proteins, and diseases by their disease proteins.ResultsUsing random forests with repeated 10-fold cross-validation, our method achieved an area under the ROC curve (AUC) of 78.1% and 74.3% for two reference sets. We benchmarked against a state-of-the-art knowledge-graph technique that does not use predicate and provenance information, obtaining AUCs of 65.6% and 64.6%, respectively. Classifiers that only used predicate information performed superior to classifiers that only used provenance information, but using both performed best.ConclusionWe conclude that both predicate and provenance information provide added value for drug efficacy screening.Electronic supplementary materialThe online version of this article (10.1186/s13326-018-0189-6) contains supplementary material, which is available to authorized users.

Identifying disease trajectories with predicate information from a knowledge graph

“…The EKP can be run on a reasonably-powered server, requiring an 8-core processor and 60GB of memory as a minimum. It has previously been used in pre-clinical research for drug efficacy screening [ 13 ], prioritizing existing drugs as repurposing candidates for autosomal dominant polycystic kidney disease [ 25 ], and pathway enrichment [ 26 ].…”

“…The first method constructed so-called metapaths [5], where the sequence of predicates in an indirect path was used as single feature. The second method, which we refer to as split paths, considered each predicate in the indirect paths as a separate feature [13]. Each method was tested both with and without directional information of predicates.…”

“…Instead, most methods analyze the network topology of proteins [ 12 ]. However, we have recently shown that analyses that are performed on protein knowledge graphs benefit from predicate information [ 13 ].…”

“…we have recently shown that analyses that are performed on protein knowledge graphs benefit from predicate information [13].…”

A Knowledge Graph of Combined Drug Therapies Using Semantic Predications From Biomedical Literature: Algorithm Development (Preprint)

“…One of the most important tasks is to identify the exact relationship between a drug and disease, especially for "treatment." Many information retrieval techniques and methods have been used to approach this problem based on predefined rules [12,13] or natural language processing [14][15][16][17][18][19] combined with machining learning [17][18][19]. Although predefined rules offer promising precision from biomedical texts, they are insufficient and perform poorly when parsing big data due to the noisy and variable syntactic structures within large-scale scientific texts.…”