We are an multi-disciplinary team of computational and experimental scientists focused on shortening the traditional time-to-development for antiviral drugs by integrating artificial intelligence (AI) and machine learning (ML), high-performance computing (HPC), and high-throughput experimental screening into every step of the drug design process to identify novel viral targets and develop safe and effective antiviral therapeutics.

In order to rapidly respond to key viral pathogens and their variants by developing and we have designed three Antiviral Platforms: (1) AntiSense Oligonucleotides (ASOs), (2) Small-interfering RNAs (siRNAs), and (3) Small Molecules targeting structured viral RNA knots and other viral RNA structures. These will be used to validate targets and will be developed into biotherapeutics that will be optimized for aerosolized airway delivery.

The Structural Biology Team is lead by David Eisenberg who is a world authority on structural biology and is supported by Larissa Podust, Jose Rodriguez and Todd Yeates. The Team is building on the combined structural determination capacity at UCLA and UCSD to further COVID19 drug discovery and development. In the past 5 years alone, the members of the team have deposited >200 atomic-resolution structures in the protein structure data base PDB using cutting edge techniques like X-ray diffraction, cryoEM and microED.

The Efficacy Testing Team is drawing on the latest developments in viral infection models using primary human Air Liquid Interface cultures, stem cell technologies and systems genetically engineered via CRISPR to test for safe and efficacious drug candidates in a wide variety of viral species.

We focus on the generation high quality pharmacokinetic (PK) data to help optimize drugs as antivirals and advance investigational compounds toward clinical candidacy.

The Encoded Libraries team builds combinatorial libraries and develops novel screening technology to discover ligands of predicted high-value antiviral targets. Screening output fuels machine learning models to inform virtual screening and medicinal chemistry hit expansion to optimize molecules for translation to the clinic. 

We will guide the lead selection via DMPK/penetration in advanced models, manufacturability, and formulation in collaboration with our industry partners. We will will also assess antiviral resistance with combinations of candidate molecules to enhance antiviral properties and efficacy against as many viral species as possible.

To develop and optimize potent active site and allosteric inhibitors. Also determines the potential for resistance to these protease inhibitors and develops mitigation strategies. Protease inhibitors have had a major impact on HIV and HCV therapies and developing novel protease inhibitors and understanding their potential for resistance could have great impact for SARS-CoV-2 and other future pandemics.

The Medicinal Chemistry team is made up of personnel with over 200 years of cumulative experience in medicinal chemistry, of which many were spent in the drug discovery industry – both in drug discovery as well as pre-clinical drug development. Our main focus is to transform small molecule candidates into safe and effective drugs that can be easily manufactured at scale for broad use and work against as many different viruses as possible.