Ishanu Chattopadhyay PRO
ML Data Science Biomedicine Social Science Faculty
Uncovering A Digital Twin of the Maturing Infant Microbiome
Sizemore, Nicholas, Kaitlyn Oliphant, Ruolin Zheng, Camilia R. Martin, Erika C. Claud, and Ishanu Chattopadhyay. "A digital twin of the infant microbiome to predict neurodevelopmental deficits." Science Advances 10, no. 15 (2024): eadj0400.
ishanu chattopadhyay
Nicholas Sizemore
Kaitlyn Oliphant
Erika Claud
Camilia Martin
THE PROBLEM
Can microbial assay from gut actionably
pre-empt developmental deficit?
Assuming a 1000 species ecosystem, and 1 successful experiment every day to discern a single two-way relationship, we would need 1,368 years to go through all possibilities. If we look for 3 way interactions, we would need 454,844 years
The Need for AI-accelerated Scale-up
Digital Twin Inference
The QNet Framework
Lets see an example of this approach
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." (2023). Under Review in Nature
PREEMPT
Consider how mutations in a viral genome "cross-talk"
We can infer these co-depndecies using the same approach
Q-Net
recursive forest
Each tree (model for variable) uses other variables as features
An Emergent Recursive Model
Lets go back to the Microbiome Problem
<class>_<observation_time>
<actinobacteria>_<30wk>
<clostridia>_<28wk>
construct qnet
Q-net inferred with typical patients
Q-net inferred with patients with neurodevelopmental deficit
We infer two digital twins: One for typical development, one for sub-optimal development
completely uninformative state
observed
state
Q-net inferred with typical patients
Q-net inferred with patients with neurodevelopmental deficit
Then we need to decide if an observed profile was generated by the typical model or the sub-optimal model
Risk of Time-stamped Microbial Profile to lead to Developmental Deficit
How different are the individual estimators for typical and deficit models?
Bacilli 30
typical
deficit
Coriobacteria 32
typical
deficit
Gammaproteobacteria 32
typical
deficit
All Patients
Feeding Variables added
Ability to "fill in" missing data is equivalent to making trajectory forecasts
Our risk measure is highly predictive and actionable
Which entities are most predictive?
Just add those microbes back?
No! Our results indicate that supplantations need to be patient specific
No transplantation is guaranteed to work reliably
Predicted to reduce
risk reliably
Predicted to reduce
risk reliably
Supplantation MUST be bacteroidia
Supplantation MUST be Actinobacteria
No risk-decreasing supplantation
Network Interpretations? We see clear differences between two cases
Typical
Deficit
Future
Answer the question: "what is a healthy microbiome?"
Explicit supplantation profiles that are tuned to individual ecosystems
Bioreactor experiments
By Ishanu Chattopadhyay
Predictive modeling of crime and rare phenomena using fractal nets
ML Data Science Biomedicine Social Science Faculty