The Anatomy of SARS-CoV-2 BioMedical Literature: Introducing the CovidX Network Algorithm for Drug Repurposing Recommendation (Preprint)

Abstract

BACKGROUND Driven by the desperate time and the dire need racing to discover an antiviral drug to save our fellow humans, we explored the landscape of the SARS-CoV-2 Biomedical publications to satisfy the following objectives. OBJECTIVE (1) identify off-label drugs that may bring benefit for the COVID-19 pandemic, (2) present a ranking algorithm called CovidX, to recommend existing drugs for potential repurposing, and (3) validate the literature-based outcome with drug knowledge available in clinical trials. METHODS To achieve such objectives, we applied Natural Language Processing (NLP) techniques to identify drugs and linked entities (e.g., disease, gene, protein, chemical compounds, etc.). When such entities are linked, they form a map that can be further explored using Network Science tools. The ranking algorithm we present is based on a notion which we called "diversity". A diversity score for a given drug can is calculated by measuring how "diverse" a drug is connected to various biological entities (regardless of the cardinality of actual instances in each category). The algorithm validates the ranking and awards those drugs that are currently being investigated in open clinical trials. RESULTS From the analyzed biomedical literature, the algorithm identified 30 possible drug candidates for repurposing, ranked them accordingly, and validated the ranking outcomes against evidence from clinical trials. CONCLUSIONS The ranking shows both consistency and promise in identifying drugs that can be repurposed. We believe, however, the full treatment to be a multifaceted, adjuvant approach where multiple drugs may be needed to be taken at the same time.