AUTHOR=Tang Xianfang , Cai Lijun , Meng Yajie , Xu JunLin , Lu Changcheng , Yang Jialiang 

TITLE=Indicator Regularized Non-Negative Matrix Factorization Method-Based Drug Repurposing for COVID-19

JOURNAL=Frontiers in Immunology

VOLUME=Volume 11 - 2020

YEAR=2021

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2020.603615

DOI=10.3389/fimmu.2020.603615

ISSN=1664-3224

ABSTRACT=A novel coronavirus named COVID-19 has become one of the most prevalent and severe infectious diseases in human history. However, there are several vaccines and therapeutic drugs against COVID-19. Drug repurposing aims to explore new treatment strategies based on the approved drugs, which can significantly reduce time and costs than drug discovery.  In this study, we build virus-drug association datasets, which included 34 viruses, 210 drugs, and 437 confirmed related virus-drug pairs from existing literature. Besides, we developed an Indicator regularized non-negative matrix factorization method (IRNMF), which introduced the indicator matrix and Karush-Kuhn-Tucker condition into the non-negative matrix factorization algorithm. According to the 5-fold cross-validation on the virus-drug association datasets, the performance of IRNMF was better than that of other methods, and its AUC value was 0.8127. Additionally, we analyzed the case on COVID-19 infection, and our results also suggested that the IRNMF algorithm can deduce the unknown virus-drug associations.