Drug repurposing for COVID-19 via knowledge graph completion

Abstract

Objective To discover candidate drugs to repurpose for COVID-19 using literature-derived knowledge and knowledge graph completion methods. Methods We propose a novel, integrative, and neural network-based literature-based discovery (LBD) approach to identify drug candidates from PubMed and other COVID-19-focused research literature. Our approach relies on semantic triples extracted using SemRep (via SemMedDB). We identified an informative and accurate subset of semantic triples using filtering rules and an accuracy classifier developed on a BERT variant. We used this subset to construct a knowledge graph, and applied five state-of-the-art, neural knowledge graph completion algorithms (TransE, RotatE, DistMult, ComplEx, and STELP) to predict drug repurposing candidates. The models were trained and assessed using a time slicing approach and the predicted drugs were compared with a list of drugs reported in the literature and evaluated in clinical trials. These models were complemented by a discovery pattern-based approach. Results Accuracy classifier based on PubMedBERT achieved the best performance (F 1 = 0.854) in classifying semantic predications. Among five knowledge graph completion models, TransE outperformed others (MR = 0.923, Hits@1 = 0.417). Some known drugs linked to COVID-19 in the literature were identified, as well as others that have not yet been studied. Discovery patterns enabled identification of additional candidate drugs and generation of plausible hypotheses regarding the links between the candidate drugs and COVID-19. Among them, five highly ranked and novel drugs (paclitaxel, SB 203580, alpha 2-antiplasmin, metoclopramide, and oxymatrine) and the mechanistic explanations for their potential use are further discussed. Conclusion We showed that a LBD approach can be feasible not only for discovering drug candidates for COVID-19, but also for generating mechanistic explanations. Our approach can be generalized to other diseases as well as to other clinical questions. Source code and data are available at https://github.com/kilicogluh/lbd-covid.

Artificial intelligence for COVID-19: battling the pandemic with computational intelligence

“… Wang et al (May 2021) [160] Knowledge-graph and deep learning 25,534 peer-reviewed scientific articles 41 Connecting 41 drugs based on Benazepril, Losartan, and Amodiaquine. Zhang et al (February 2021) [161] Knowledge-graph and deep learning PubMed, LitCovid,CORD-19. The built knowledge graph has 131,355 nodes and 2,558,935 relations.…”

Using Literature Based Discovery to Gain Insights Into the Metabolomic Processes of Cardiac Arrest

“…The primary application areas of LBD have been for drug development (Hu et al, 2003;Hristovski et al, 2010;Zhang et al, 2014), drug repurposing (Ahlers et al, 2007;Baker, 2010;Deftereos et al, 2011;Cohen et al, 2014;Zhang et al, 2014;Rastegar-Mojarad et al, 2015Yang et al, 2017;Zhang et al, 2020), and adverse drug event prediction (Deftereos et al, 2011;Banerjee et al, 2014;Shang et al, 2014;Hristovski et al, 2016;Mower et al, 2016). Although we were unable to find prior studies focused specifically on applying LBD to metabolomic knowledge discovery, biochemical pathways are frequently an area of investigation for new drug development.…”

Task-Driven Knowledge Graph Filtering Improves Prioritizing Drugs for Repurposing

“…KGs have also been used in the adjacent fields of drug repurposing, like predicting interactions between drugs and genes [21], diseases and genes [5,22] or polypharmacy side effects [23]. There have also been endeavours for large-scale computational drug repurposing specifically for COVID-19 [24,25], some also involving graphs [26,27,28].…”