Ishanu Chattopadhyay PRO
ML Data Science Biomedicine Social Science Faculty
Ishanu Chattopadhyay
Emergenet: Forecasting future mutations and emergence events
University of Chicago
Feb 7 2023
what are we trying to do?
Aaron Esser-Kahn
Predicting emergence events in specific viral species
Rank ordering animal strains on their pandemic risk
Meaningfully exploit current biosurveillance capacity
Step towards formulating escape-resistant vaccines
what are we trying to do?
How is it done today?
Lack of validation
How are we doing it?
Learn an instrinsic distance between genomic sequences
How are we doing it?
Prediction of dominant strains in seasonal Flu Epidemics
Estimating published IRAT scores from the Emergenet
Estimating published IRAT scores from the Emergenet
SARS-CoV2
Future
- Validation of viability of predicted mutations
- Neutralization assays to validate plausability of escape resistant vaccines
- Predict how and when variants arise
- Extend analysis to SARS-CoV2
The e-distance Metric: Why Is This a Natural Metric?
\textrm{items } X_1, X_2, \cdots , X_{i-1},X_{i+1}, \cdots, X_N
a
b
c
d
e
X_i
Similar opinion vectors can spontaneously switch:
Our intrinsic metric quantifies the odds of this spontaneous switch
\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 )
Emergenet_Darpa_Amy_Jenkins_Feb2023_ishanu
By Ishanu Chattopadhyay
Emergenet_Darpa_Amy_Jenkins_Feb2023_ishanu
Opinion dynamics and belief shift using recursive decision forests
