The IDentif.AI-x pandemic readiness platform: Rapid prioritization of optimized COVID-19 combination therapy regimens

Abstract

IDentif.AI-x, a clinically actionable artificial intelligence platform, was used to rapidly pinpoint and prioritize optimal combination therapies against COVID-19 by pairing a prospective, experimental validation of multi-drug efficacy on a SARS-CoV-2 live virus and Vero E6 assay with a quadratic optimization workflow. A starting pool of 12 candidate drugs developed in collaboration with a community of infectious disease clinicians was first narrowed down to a six-drug pool and then interrogated in 50 combination regimens at three dosing levels per drug, representing 729 possible combinations. IDentif.AI-x revealed EIDD-1931 to be a strong candidate upon which multiple drug combinations can be derived, and pinpointed a number of clinically actionable drug interactions, which were further reconfirmed in SARS-CoV-2 variants B.1.351 (Beta) and B.1.617.2 (Delta). IDentif.AI-x prioritized promising drug combinations for clinical translation and can be immediately adjusted and re-executed with a new pool of promising therapies in an actionable path towards rapidly optimizing combination therapy following pandemic emergence.

IDentif.AI-Omicron: Harnessing an AI-Derived and Disease-Agnostic Platform to Pinpoint Combinatorial Therapies for Clinically Actionable Anti-SARS-CoV-2 Intervention

“…This is in line with previous reports of the synergistic interaction of molnupiravir and high-concentration FPV in a hamster model. − Thus, further exploration of the potential of EIDD-1931/FPV is warranted, but for clinical use the pharmacokinetics and pharmacodynamics of FPV should be further optimized. Finally, aligned with our previous study, we detected a dose-dependent interaction between EIDD-1931 and RDV . As an oral version of RDV is under development, this drug combination may also be of interest for broad deployment.…”

“…We additionally tested EIDD-1931 interactions with polymerase inhibitorsremdesivir (RDV) and FPV. Combining EIDD-1931 at EC 20 concentration with low concentrations of RDV resulted in dose-dependent improvement of the antiviral effects to 23.7 ± 8.5% inhibition (Table ), aligned with the previous studies . EIDD-1931/FPV at Level 2 concentrations yielded only 4.3 ± 4.4% inhibition (Figure B), in line with the results from the IDentif.AI analysis which did not detect any interaction between the two drugs.…”

“…Fifty combinatorial drug treatments were designed and experimentally tested to efficiently investigate the interaction space of the six drugs . When tested in monotherapy at Levels 1 and 2, the maximum %Inhibition achieved by any drug was 43.6 ± 13.2, recorded for EIDD-1931 at Level 2.…”

“…Throughout the course of the pandemic, several notable antiviral drug combination approaches have been proposed for COVID-19. For example, our previous research demonstrated that pairing remdesivir with Kaletra improved remdesivir’s antiviral efficacy 6.5 times and that EIDD-1931 (active substance of molnupiravir) can serve as a backbone of anti-SARS-CoV-2 drug combinations. , Particularly, EIDD-1931 with remdesivir demonstrated a favorable interaction, which was independently demonstrated in a traditional screening process . In December 2021, an oral combinatorial treatment, Paxlovid, received U.S. Food and Drug Administration (FDA) Emergency Use Authorization (EUA), followed by equivalent approvals in United Kingdom and European Union .…”

“…It additionally informs about the most optimal drug ratios. IDentif.AI has been demonstrated as a pandemic readiness platform, , in vivo validated for combination optimization in tuberculosis, and clinically validated for treatment personalization in oncology . This current work, which uses candidate therapies against the B.1.1.529 (Omicron) variant of SARS-CoV-2 has made advances from prior work.…”