Model Medicines Discovers New Pan-Antiviral Chemical Entity (NCE) Library, Achieving Unprecedented 66.7% Hit Rate Using Proprietary AI Platform

La Jolla, CA - Model Medicines, a leading human health company specializing in generative AI-driven drug discovery, today announced groundbreaking headline results for the creation of a validated NCE, pan-antiviral library. 

By leveraging proprietary AI technologies, Model Medicines achieved an impressive 66.7% hit rate at 10μM in discovering new chemical entities with antiviral activity as assessed in a gold-standard cell model of viral infection. Further, 46.7% of all evaluated compounds demonstrated sub-10μM IC50’s - a key threshold to identify potent drug candidates with likely therapeutic potential. These results bring the total number of compounds discovered using Model Medicines’ AI platform, GALILEOTM , to 192 across 26 targets. This also comes on the heels of the company's impressive 45.45% hit rate for its oncology program, announced in 2022.

Traditional drug discovery methods often yield hit rates of 1% - 4%, requiring the synthesis and testing of hundreds to thousands of compounds to identify a handful of potential leads. Modern AI-drug discovery hit rates ranging from 12% - 26%, for compounds evaluated at concentrations up to 100μM, have been reported by leading researchers and companies. Now, Model Medicines' AI-powered platform, GALILEOTM  has dramatically improved the efficiency of the NCE hit discovery process with its 66.7% hit rate, representing a staggering 15-fold increase compared to traditional methods and a 3-fold increase over the best-in-class AI-driven drug discovery efforts, such as those reported by Schrödinger's Therapeutics Group (2023), Zhang et al. (2012), Rahman et al. (2021), and Jain et al. (2021). Moreover, Model Medicines' sub-10 μM hit rate of 46.7% is particularly impressive, as it not only demonstrates the platform's ability to identify a high proportion of active compounds, but also underscores its precision in identifying potent, high-potential compounds. 

"Our results are not just groundbreaking for antiviral drug discovery; they represent a seismic shift in the entire landscape of pharmaceutical research and development.," said Dr. Daniel Haders, CEO and Founder at Model Medicines. "By efficiently navigating deep chemical space and accurately predicting the most promising compounds, we can significantly accelerate the development of novel, best-in-class therapeutics." 

Model Medicines' study involved the virtual screening of over 52 trillion compounds using their proprietary GALILEOTM  AI platform. The platform combines advanced machine learning algorithms, physics-based scoring, and absolute binding free energy calculations to identify compounds with the highest probability of success. From the initial screening, 15 compounds were selected for synthesis and experimental testing, resulting in 10 hits with activity at 10 μM, 7 of which exhibited a sub-10 μM IC50.

Importantly, Model Medicines' 2024 and 2022 studies only evaluated compound activity up to concentrations of 10 and 20 μM, respectively, while Schrödinger's Therapeutics Group (2023) and Rahman et al. (2021), for example, evaluated compound activity up to concentrations of 30 μM and 50μM, respectively. This suggests that Model Medicines' hit rates may be underreporting success/hit rates relative to leading studies in the field.

Sources: Schrödinger’s Therapeutics Group (2023) “Dramatically improving hit rates with a modern virtual screening workflow ”- compounds evaluated up to 30 µM. Rahman et al. (2021) “A machine learning model trained on a high-throughput antibacterial screen increases the hit rate of drug discovery ” - compounds evaluated up to 50μM. Zhang et al. (2012) “Discovery of Novel Antimalarial Compounds Enabled by QSAR-Based Virtual Screening”. Jain et al. (2021) “Hybrid In Silico Approach Reveals Novel Inhibitors of Multiple SARS-CoV-2 Variants” Dittmar et al. (2020) “Drug repurposing screens reveal FDA approved drugs active against SARS-Cov-2” Jin et al. (2020) “Structure of Mpro from SARS-CoV-2 and discovery of its inhibitors” Chen et al. (2021) “A high-throughput screen for TMPRSS2 expression identifies FDA-approved compounds that can limit SARS-CoV-2 entry” Bakowski et al. (2021) “Drug repurposing screens identify chemical entities for the development of COVID-19 interventions”

Model Medicines' study involved the virtual screening of over 52 trillion compounds using their proprietary GALILEOTM  AI platform. The platform combines advanced machine learning algorithms, physics-based scoring, and absolute binding free energy calculations to identify compounds with the highest probability of success. From the initial screening, 15 compounds were selected for synthesis and experimental testing, resulting in 10 hits with activity at 10 μM, 7 of which exhibited a sub-10 μM IC50.Importantly, Model Medicines' 2024 and 2022 studies only evaluated compound activity up to concentrations of 10 and 20 μM, respectively, while Schrödinger's Therapeutics Group (2023) and Rahman et al. (2021), for example, evaluated compound activity up to concentrations of 30 μM and 50μM, respectively. This suggests that Model Medicines' hit rates may be underreporting success/hit rates relative to leading studies in the field.

Davey Smith, MD, MAS, FACP, FIDSA, Senior Clinical Advisor to Model Medicines and a renowned infectious disease specialist at UC San Diego Health, commented on the potential impact of Model Medicines' breakthrough: "As we've seen with the devastating consequences of the COVID-19 pandemic, the world is in desperate need of a rapidly deployable, broad-spectrum antiviral that can effectively combat novel pathogens from the moment an outbreak occurs. Model Medicines' groundbreaking discovery of a new pan-antiviral chemical entity library, with an astounding 66.7% hit rate, represents a quantum leap forward in our ability to respond to viral threats on a global scale. This is not just a scientific achievement; it's a pivotal moment in our fight against infectious diseases. Model Medicines' AI-driven approach is poised to revolutionize how we develop and deploy antiviral therapeutics, potentially saving millions of lives and transforming our capacity to confront future pandemics head-on. This is the kind of paradigm-shifting breakthrough we've been waiting for, and it couldn't have come at a more critical time for global health."