Presentation Aug 5, 2022

1. School of Data Science &
Novo Nordisk
Phil Bourne, Dean
1
UNIVERSITY OF VIRGINIA
AUG. 5, 2022

2. A Quick Overview
• Who we are
• How we view data science
• Our approach to applying data science
• A couple of examples that touch diabetes research
• What we bring to the table
2

3. Discover the 1st school of data science in the nation
3
Founded in 2019 through the largest
gift in the history of the University of
Virginia, the School of Data Science
positions the university and our
community to play a leading role in
the global digital future.
Our Mission
CATALYZE discovery through leading
edge, interdisciplinary research.
EDUCATE a diverse workforce to be
responsible practitioners and leaders in
an increasingly data-driven society.
SERVE our community, our nation, and
our world by using data science to
advance the common good.

4. 4
New School, New Space

5. 5
Transcending Boundaries
We aim to be a school without walls,
committed to innovation and collaboration, and
our new building will reflect this philosophy.
Open, collaborative spaces will transcend
traditional boundaries and spark
interdisciplinary connections between learners,
researchers and innovators. The four-story
facility will include adaptive classrooms, faculty
offices, collaborative meeting spaces, and
research areas. Public spaces will be open to
the University and broader communities alike.

6. 6

7. M.S. in Data Science
7
Fostering Explorers
The School of Data Science is committed to teaching and
practicing responsible data science for the common good.
Our goal is to educate students in data science throughout
their academic journey and as lifelong learners, from
undergraduate to professional.
62
MSDS, Residential (full-time)
M.S. in Data Science
116
MSDS, Online (part-time)
Ph.D. in Data Science
12
Inaugural class starts Fall 2022
Minor in Data Science
327
2022-2023

8. How we view data science …
8

9. 9
New “4+1” Pedagogical Model
Data scientists apply their skills in many
different fields and must possess a core set
of tools and foundational knowledge about
data and the methods used to learn from it.
At the School of Data Science, we group
these skills into four areas—analytics, design,
value, and systems —which are applied to
practice.
Students are exposed to ideas in each of
these domains, preparing them to skillfully
and responsibly address real-world issues.

10. 1
0
Furthering Discovery
The School of Data Science pursues high-impact
research to further discovery, share knowledge
and transform society. Through their research,
our faculty and students are building a better
world in a variety of ways.
DEMOCRACY
Investigating how
terrorist groups
recruit women
through propaganda
and examining risk
for extremist violence.
EDUCATION
Helping economically
disadvantaged,
underrepresented
populations pursue
pathways that have a
higher probability of
leading them to
success.
HEALTH & MEDICINE
Precision medicine
Brain science
Imaging
Drug discovery
Multi-scale modeling
Diabetes research
Ethics
Microbiome
Healthcare
economics
Biostatistics
.
CYBERSECURITY
Detecting broad-
spectrum cyber
threats almost
immediately after
they are launched—
research made
possible through a
grant from the
Department of
Defense.
ENVIRONMENT
Using NASA data
collected aboard the
International Space
Station to examine
and develop
responses to climate
change in the
Shenandoah National
Forest and beyond.
BUSINESS
Discovering what
makes a job interview
successful for both
the candidate and the
recruiter and learning
how to mitigate bias
in the recruiting
process.

11. Our approach to applying data science …
11

12. Let’s breakdown one success story to see what
happened and why
https://medium.com/proteinqure/welcome-into-the-fold-bbd3f3b19fdd

14. Google’s DeepMind’s AlphaFold2 makes gigantic leap in solving protein structures

15. AlphaFold2
Numerical optimization – differential programming
Overall gradient descent trained to win CASP
Jumper et al.., 2021. Nature, 596 (7873),
pp.583-589
Transformer models using attention
Geometry invariant to
translation/rotation

16. Logistics Behind the Win
● Nothing fundamentally new from an AI perspective
● Data Integration
● Collaboration not competition
● Engineering challenge beyond most labs
● Compute power beyond most labs
● Team size beyond most labs
● Worked with protein structure specialists

17. 17

18. https://en.wikipedia.org/wiki/Jim_Gray_(computer_scientist)
https://www.microsoft.com/en-us/research/wp-
content/uploads/2009/10/Fourth_Paradigm.pdf
https://twitter.com/aip_publishing/status/856825353645559808
Of course this was all predicted
by smart people ..

19. Model
Transportability
Horizontal
Integration
Multi-scale
Integration
human
mouse
zebrafish
DNA
Gene/Protein
Network
Cell
Tissue
Organ
Body
Population
CNV SNP methylation
3D structure Gene
expression Proteomics
Metabolomics
Metabolic
Signaling
transduction
Gene
regulation
Hepatic Myoepithelial Erythrocyte
Epithelial Muscle Nervous
Liver Kidney Pancreas Heart
Physiologically based
pharmacokinetics
GWAS
Population
dynamics
Microbiota
From Harnessing Big Data for Systems Pharmacology 2017
https://doi.org/10.1146/annurev-pharmtox-010716-104659
Current roadblocks are more cultural than technical
The Fifth Paradigm: Integration Across Scales?

20. Gohlke et al. 2022
https://onlinelibrary.wiley.com/doi/10.1002/ctm2.726
Real World Evidence for Preventive Effects of Statins on
Cancer Incidence: A Transatlantic Analysis
EHR
Animal Models
Pathways

21. A couple of examples that touch diabetes
research …
21

22. Artificial Intelligence/ Machine Learning in Medicine
Recognition of microscopic GI patterns and key disease drivers
Artificial Intelligence
powered disease insights
Highest
Activation
Lowest
Activation
Key:
Sana Syed

23. 23

24. 24

25. Possible Interactions?
25
● Student capstone projects
● Visiting fellows
● Faculty collaborations
● PhD mentorship