Please use this identifier to cite or link to this item:
Title: IDentif.AI-Omicron: Harnessing an AI-Derived and Disease-Agnostic Platform to Pinpoint Combinatorial Therapies for Clinically Actionable Anti-SARS-CoV-2 Intervention
Authors: Blasiak, Agata 
Truong, Anh TL 
Wang, Peter
Hooi, Lissa 
Chye, De Hoe
Tan, Shi-Bei
You, Kui
Remus, Alexandria 
Allen, David Michael 
Chai, Louis Yi Ann 
Chan, Conrad EZ 
Lye, David CB 
Tan, Gek-Yen G
Seah, Shirley GK
Chow, Edward Kai-Hua 
Ho, Dean 
Keywords: Artificial Intelligence
Drug Discovery
Drug Combinations
Combinatorial Therapy
Issue Date: 17-Aug-2022
Citation: Blasiak, Agata, Truong, Anh TL, Wang, Peter, Hooi, Lissa, Chye, De Hoe, Tan, Shi-Bei, You, Kui, Remus, Alexandria, Allen, David Michael, Chai, Louis Yi Ann, Chan, Conrad EZ, Lye, David CB, Tan, Gek-Yen G, Seah, Shirley GK, Chow, Edward Kai-Hua, Ho, Dean (2022-08-17). IDentif.AI-Omicron: Harnessing an AI-Derived and Disease-Agnostic Platform to Pinpoint Combinatorial Therapies for Clinically Actionable Anti-SARS-CoV-2 Intervention. ACS NANO 16 (9). ScholarBank@NUS Repository.
Abstract: Nanomedicine-based and unmodified drug interventions to address COVID-19 have evolved over the course of the pandemic as more information is gleaned and virus variants continue to emerge. For example, some early therapies (e.g., antibodies) have experienced markedly decreased efficacy. Due to a growing concern of future drug resistant variants, current drug development strategies are seeking to find effective drug combinations. In this study, we used IDentif.AI, an artificial intelligence-derived platform, to investigate the drug-drug and drug-dose interaction space of six promising experimental or currently deployed therapies at various concentrations: EIDD-1931, YH-53, nirmatrelvir, AT-511, favipiravir, and auranofin. The drugs were tested in vitro against a live B.1.1.529 (Omicron) virus first in monotherapy and then in 50 strategic combinations designed to interrogate the interaction space of 729 possible combinations. Key findings and interactions were then further explored and validated in an additional experimental round using an expanded concentration range. Overall, we found that few of the tested drugs showed moderate efficacy as monotherapies in the actionable concentration range, but combinatorial drug testing revealed significant dose-dependent drug-drug interactions, specifically between EIDD-1931 and YH-53, as well as nirmatrelvir and YH-53. Checkerboard validation analysis confirmed these synergistic interactions and also identified an interaction between EIDD-1931 and favipiravir in an expanded range. Based on the platform nature of IDentif.AI, these findings may support further explorations of the dose-dependent drug interactions between different drug classes in further pre-clinical and clinical trials as possible combinatorial therapies consisting of unmodified and nanomedicine-enabled drugs, to combat current and future COVID-19 strains and other emerging pathogens.
Source Title: ACS NANO
ISSN: 1936-0851
DOI: 10.1021/acsnano.2c06366
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
IdentiAI SARS CoV 2.pdfPublished version2.99 MBAdobe PDF



Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.