Mechanistic Knowledge

Novel Machine Learning

\displaystyle \theta(x,y) \triangleq \\ \mathbf{E}_i \left ( \mathbb{J}^{\frac{1}{2}} \left (\Phi_i^P(x_{-i}) , \Phi_i^Q(y_{-i})\right ) \right )

Problem: Can we predict the next pandemic?

Can we predict future mutations? Can we define the "edge of emergence"?

Emergenet: Generative model of emergenet rules of organization

Bio_NORAD

Validation Against IRAT Scores

Predicting diffusion rate in strain space

New metrics of immunological vulnerabilities

Who Cares?

Allows rapid reliable prediction of future mutations, variants and rank orders strains by their pandemic risk. Can target viruses BEFORE the first human infection

What is the new approach?

Learn deep generative models of emergent dependencies acoss non-colocated residue variations, which induce a biology aware metric

What are we trying to do?

Develop future-proof vaccines and countermeasures, escape-resistant to emergence of variants and zoonosis

Immunological and structural information

Chattopadhyay, Ishanu, Kevin Wu, Jin Li, and Aaron Esser-Kahn. “Emergenet: Fast Scalable Pandemic Risk Assessment of Influenza A Strains Circulating In Non-Human Hosts,” December 23, 2022. https://doi.org/10.21203/rs.3.rs-2336091/v1.