Computational drug repurposing based on electronic health records: a scoping review

Abstract

Computational drug repurposing methods adapt Artificial intelligence (AI) algorithms for the discovery of new applications of approved or investigational drugs. Among the heterogeneous datasets, electronic health records (EHRs) datasets provide rich longitudinal and pathophysiological data that facilitate the generation and validation of drug repurposing. Here, we present an appraisal of recently published research on computational drug repurposing utilizing the EHR. Thirty-three research articles, retrieved from Embase, Medline, Scopus, and Web of Science between January 2000 and January 2022, were included in the final review. Four themes, (1) publication venue, (2) data types and sources, (3) method for data processing and prediction, and (4) targeted disease, validation, and released tools were presented. The review summarized the contribution of EHR used in drug repurposing as well as revealed that the utilization is hindered by the validation, accessibility, and understanding of EHRs. These findings can support researchers in the utilization of medical data resources and the development of computational methods for drug repurposing.

Drug repurposing for viral cancers: A paradigm of machine learning, deep learning, and virtual screening‐based approaches

“…There are multiple web-based and computational tools available based on different data types and approaches for cancer-specific and viral cancer-specific drug repurposing. [111][112][113] The widely used data types consist of chemical structures of drugs, 114 their physiochemical properties, 115 genomic profiles, 116 and molecular targets. 117 Recently developed computational analytical tools make use of omics data types such as drug induced perturbagen profiles [118][119][120] obtained from patients suffering from one of viral cancers or simulation responses.…”

“…There are multiple web‐based and computational tools available based on different data types and approaches for cancer‐specific and viral cancer‐specific drug repurposing 111–113 . The widely used data types consist of chemical structures of drugs, 114 their physiochemical properties, 115 genomic profiles, 116 and molecular targets 117 .…”

Drug Repurposing at the Interface of Melanoma Immunotherapy and Autoimmune Disease

“…In this current scenario, the time and cost of drug development have been significantly reduced, with the risk of failure reduced due to the advancement of bioinformatics/cheminformatics tools, the availability of huge biological and structural databases in drug repositioning and artificial intelligence technology leads to enormous acceleration of the drug repurposing process. Approaches and applications of AI and machine learning have been recently published in some excellent reviews [ 147 , 148 , 149 , 150 , 151 ].…”

Repurposing ketamine to treat cocaine use disorder: integration of artificial intelligence‐based prediction, expert evaluation, clinical corroboration and mechanism of action analyses

“…These approaches can be broadly categorized into network-based models [18,19], structure-based approaches [20,21] and artificial intelligence (AI)-based approaches [22,23]. While these methods generate many repurposing signals, there have also been many repurposing drug candidates that have failed in clinical trial testing due to lack of efficacy [11,24]. Thus, candidate drugs should undergo additional vetting prior to being tested in a clinical trial, which can be accomplished by integrating data from electronic health records (EHR) and input from experts in pharmacology and biomedical research [25].…”