Drug target discovery using knowledge graph embeddings

Abstract

The field of drug discovery has entered a plateau stage lately. It is increasingly more expensive and time-demanding to introduce new drugs into the market. One of the main reasons is the slow progress in finding novel targets for drug candidates and the lack of insight in terms of the associated mechanisms of action. Current works in this area mainly utilise different chemical, genetic and proteomic methods, which are limited in terms of the scalability of experimentation and the scope of studied drugs and targets per experiment. This is mainly due to their dependency on laboratory experiments and available physical resource. This has led to an increasing importance of computational methods for the identification of candidate drug targets. In this work, we introduce a novel computational approach for predicting drug target proteins. We approach the problem as a link prediction task on knowledge graphs. We process drug and target information as a knowledge graph of interconnected drugs, proteins, disease, pathways and other relevant entities. We then apply knowledge graph embedding (KGE) models over this data to enable scoring drug-target associations, where we employ a customised version of state-of-the-art KGE model ComplEx. We generate a benchmarking dataset based on KEGG database to train and evaluate our method. Our experiments show that our method achieves best results in comparison to other traditional KGE models. Specifically, the method predicts drug target links with mean reciprocal rank (MRR) of 0.78 and Hits@10 of 0.88. This provides a promising basis for further experimentation and comparisons with domain-specific predictive models.

Building a knowledge graph to enable precision medicine

“…CORD-19 was able to empower data-driven medicine during the pandemic by facilitating the development of neural search engines for healthcare workers 64,65 and provided insights into drug repurposing targets 66 . Collectively, these knowledge graphs have lent themselves to a variety of scientific discoveries 67,68 , methodological innovations [69][70][71] and biomedical benchmarking 31,35,72 . Large-scale knowledge graphs have facilitated fruitful research across a variety of problems faced by the biomedical community.…”

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges

“…In any case, it is profoundly reliant upon the experience of the specialists. Knowledge graph embeddings can be used to deal with these issues [7] [267]. A knowledge graph can be created based on a genetic approach by combining different genes and their associations for a particular disease.…”

Biomedical Text Link Prediction for Drug Discovery: A Case Study with COVID-19

“…Training link prediction models on entire SemNet data yields low evaluation scores, particularly when the domain of interest is a novel, lesser-connected entity, such as COVID-19. Thus, domain specific subgraphs are utilized in link prediction training to improve evaluation scores [22].…”