Large Science Models: From Biological Data to AI for Commercial Scientific Discovery

Ishanu Chattopadhyay, PhD

Asst Professor, Biomedical informatics & Computer Science

University of Kentucky

ishanu_ch@uky.edu

ALLTECH RESEARCH SHOWCASE

PAI PREEMPT MAGICS

The views, opinions and/or findings expressed are those of the author(s) and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government.

1918 onward: classical swine H1N1 persists in pigs [1,2]
1979: Eurasian avian-like swine H1N1 becomes established in European swine [2]
1998: North American triple-reassortant swine viruses emerge [3]
2008-2009: pandemic genome assembled in swine; 6 segments from North American triple-reassortant swine viruses, 2 segments (NA, M) from Eurasian avian-like swine [3]
Mar-Apr 2009: human outbreak recognized in Mexico and the U.S. [3,4]
Jun 11, 2009: WHO declares pandemic [5]

Memoli MJ, Tumpey TM, Jagger BW, Dugan VG, Sheng ZM, Qi L, Kash JC, Taubenberger JK. An early “classical” swine H1N1 influenza virus shows similar pathogenicity to the 1918 pandemic virus in ferrets and mice. Virology. 2009;393(2):338-345. doi:10.1016/j.virol.2009.08.021.
Dunham EJ, Dugan VG, Kaser EK, Perkins SE, Brown IH, Holmes EC, Taubenberger JK. Different evolutionary trajectories of European avian-like and classical swine H1N1 influenza A viruses. Journal of Virology. 2009;83(11):5485-5494. doi:10.1128/JVI.02565-08.
Smith GJD, Vijaykrishna D, Bahl J, Lycett SJ, Worobey M, Pybus OG, Ma SK, Cheung CL, Raghwani J, Bhatt S, Peiris JSM, Guan Y, Rambaut A. Origins and evolutionary genomics of the 2009 swine-origin H1N1 influenza A epidemic. Nature. 2009;459(7250):1122-1125. doi:10.1038/nature08182.
Centers for Disease Control and Prevention. Outbreak of swine-origin influenza A (H1N1) virus infection, Mexico, March-April 2009. MMWR Morb Mortal Wkly Rep. 2009;58(17):467-470.
World Health Organization. DG Statement following the meeting of the Emergency Committee. 11 June 2009.

the 2009 swine-flu pandemic

1918

1979

1998

2008

2009

Mar

Jun

ALLTECH / 19 OCT 2026

01 / WHY IT MATTERS

Emergence starts in animals

8 of 8

Segments of the 2009 pandemic genome came from viruses already circulating in swine

30 years

From the 1979 swine lineage to the first human cases in 2009

Visible in sequence data years before it was visible in people.

Timeline after Smith et al., Nature (2009); full references on slide.

Are emergence events predictable?

Building A Large Science Model

NCBI + GISAID

>400,000 HA/NA sequences

recursive forest of conditional inference trees

Sizemore, N., Oliphant, K., Zheng, R., Martin, C. R., Claud, E. C., & Chattopadhyay, I. (2024). “A digital twin of the infant microbiome to predict neurodevelopmental deficits.” Science Advances, 10(15), eadj0400. https://doi.org/10.1126/sciadv.adj0400

Wu, K., Li, F., & Chattopadhyay, I. (2026). “Emergenet: A Digital Twin of Influenza A Evolution for Vaccine Strain Forecasting and Emergence Risk Assessment.” Military Medicine, usag255. https://doi.org/10.1093/milmed/usag255

Publications

H1N1 2025 Influenza A HA

Set of conditional inference trees (CIT)
- Strict statistical guarantees: quantifies inference uncertainty
Each tree models exactly one variable as a function of potentially all other variables
Non-leaf nodes are "hyperlinked" to other trees

Recursive LSM forest: hyperlinked nodes capturing emergent macro-structures

Large Science Models

Learn the emergent constriants from data

H5N1 2025 Influenza A HA

Set of conditional inference trees (CIT)
- Strict statistical guarantees: quantifies inference uncertainty
Each tree models exactly one variable as a function of potentially all other variables
Non-leaf nodes are "hyperlinked" to other trees

Recursive LSM forest: hyperlinked nodes capturing emergent macro-structures

Large Science Models

Learn the emergent constriants from data

IRAT replication by LSM

(automated, in seconds)

\textrm{Regression Eqn.} y = 0.47x + 2.77\\ R = 0.72\\ \textrm{p-value} = 0.0001

Stamping Out the Next Pandemic Before The First Human Infection

BioNorad

MICROBIOME: Thousands of Bacterial & Fungal Species — Simultaneous Discovery of Ecological Interactions

METABOLOMICS: 100,000+ Targeted & Untargeted Molecular Features — Simultaneous Discovery of Biochemical Patterns

ONE FRAMEWORK: High-Dimensional Pattern Discovery → Prediction → Commercially Deployable AI

Generative AI For Biological Discovery

High Abundance Classes

Complex Interdependecies Exist over time and taxonomic strata

quantized output levels

Can microbial assay from gut actionably

pre-empt developmental deficit?

Study Set-up

Forecasting of class abundance variations both

in-sample (\( R^2 \ge 95\%\))

and out-of sample (\(R^2\ge 72\%\))

Understanding key drivers of risk

No transplantation is guaranteed to work reliably

Predicted to reduce

risk reliably

Predicted to reduce
risk reliably

Predicting Perturbations

Top risk drivers mapped to known pathways

Top 30 risk drivers (targeted met.)

IBD Metabolomics: Preliminary Results

Dataset from Metabolomics Workbench

Study ID	ST000923
Study Title	Longitudinal Metabolomics of the Human Microbiome in Inflammatory Bowel Disease

Institute	Broad Institute of MIT and Harvard
Last Name	Avila-Pacheco
First Name	Julian
Submit Date	2017-11-14
Num Groups	3
Total Subjects	546
Num Males	276
Num Females	270
Analysis Type Detail	LC-MS

State-of-art microbiome based Classification (~10 species) *

IBD vs UC	0.82
IBD vs CD	0.76

*Zheng, J., et al. (2024). Noninvasive, microbiome-based diagnosis of inflammatory bowel disease. Nature Medicine, 30(12), 3555–3567. https://doi.org/10.1038/s41591-024-03280-4

IBD vs non IBD

0.85

Gut-Metabolome based Classification (~36 metabolites) *

Application 2

Metabolomics

LSM model

No. parameters: 70 million
Out of sample n=150
Uses all names and unnamed metabolites (>81K features)

	AUC (out of sample)
Healthy vs IBD	96.1%
Healthy vs UC	92%
UC vs CD	99%
Healthy vs CD	99%

Metabolomics

LSM model

No. parameters: 70 million
Out of sample n=150
Uses all names and unnamed metabolites (>81K features)

	AUC (out of sample)
Healthy vs IBD	96.1%
Healthy vs UC	92%
UC vs CD	99%
Healthy vs CD	99%

Metabolomics

Insight: the discriminating hypersurface is 2d (almost 1d)

Future

Validating antigenicity predictions

Application to Equine Influenza dynamics

Corona Viruses and other emerging pathogens

Questions

Backup Slides

Lets train a machine learning model to recognize human vs swine Influenza HA proteins

High confidence generally

\textrm{Emergence Risk} = \frac{1}{\textrm{classification accuracy}}

\textrm{Emergence Risk} = \frac{1}{\textrm{classification accuracy}}

Data source: NCBI and GISAID HA sequences collected between 1999 and 2016 globally (HA protein fasta)

LSM distance \(\neq \) Edit Distance

Same sequence/strain pair, but dfferent background (times of collection)

LSM distance

Small edit distance (5-8) and large LSM distance

Measure of Emergence Potential

\rho_t(x) \triangleq -\log \min_{\begin{subarray}{c}y,z \in H^t \\ r \in L_\mathcal{H},\\s \in L_\mathcal{N}\end{subarray}} \sqrt{\theta_r\left (x^{\mathcal{H}},y^{ \mathcal{H} }\right ) \theta_{s}\left (x^{\mathcal{N}},z^{\mathcal{N}}\right )},

Neuraminidase contribution

Hemagglutinin contribution

current animal circulation

Protein-specific Lsms

Which animal strain has the highest odds of giving rise to a strain similar to the circulating humans population?

Same subtype doesnt need to pre-exist in humans
Very few observations suffice in the animal circulation
Fewer strains increase quantifiable uncertainty

Optimization Problem

\frac{\delta \theta(x,y)}{\delta y}

Which sites are driving prediction?

Estimate how LSM distances perturb as we perturb individual sites

Re-drawing the Phylogeny

LSM-distance induces a new phylogeny

phylogeny with post-2020 sequences

Large Science Models: From Biological Data to AI for Commercial Scientific Discovery

the 2009 swine-flu pandemic

Building A Large Science Model

Publications

Recursive LSM forest: hyperlinked nodes capturing emergent macro-structures

Large Science Models

Recursive LSM forest: hyperlinked nodes capturing emergent macro-structures

Large Science Models

IRAT replication by LSM

Stamping Out the Next Pandemic **Before** The First Human Infection

BioNorad

MICROBIOME: Thousands of Bacterial & Fungal Species — Simultaneous Discovery of Ecological Interactions

METABOLOMICS: 100,000+ Targeted & Untargeted Molecular Features — Simultaneous Discovery of Biochemical Patterns

ONE FRAMEWORK: High-Dimensional Pattern Discovery → Prediction → Commercially Deployable AI

Generative AI For Biological Discovery

High Abundance Classes

Complex Interdependecies Exist over time and taxonomic strata

Can microbial assay from gut actionably

pre-empt developmental deficit?

Study Set-up

Forecasting of class abundance variations both

in-sample (\( R^2 \ge 95\%\))

and out-of sample (\(R^2\ge 72\%\))

Understanding key drivers of risk

No transplantation is guaranteed to work reliably

Predicted to reduce

risk reliably

Predicted to reduce risk reliably

Predicting Perturbations

Top risk drivers mapped to known pathways

Top 30 risk drivers (targeted met.)

IBD Metabolomics: Preliminary Results

Metabolomics

Metabolomics

Metabolomics

Insight: the discriminating hypersurface is 2d (almost 1d)

Future

Questions

LSM distance \(\neq \) Edit Distance

Measure of Emergence Potential

Neuraminidase contribution

Hemagglutinin contribution

current animal circulation

Protein-specific Lsms

Which animal strain has the highest odds of giving rise to a strain similar to the circulating humans population?

Optimization Problem

Which sites are driving prediction?

Re-drawing the Phylogeny

LSM-distance induces a new phylogeny

phylogeny with post-2020 sequences

Stamping Out the Next Pandemic Before The First Human Infection

Predicted to reduce
risk reliably