Precision oncology and bioinformatics for the NACBR North Carolina High School teachers workshop. http://www.ncabr.org/k12/workshops/

1. Precision Oncology and the
Changing Role of Cancer
Informatics
Warren A. Kibbe, Ph.D.
Professor, Biostats & Bioinformatics
Chief Data Officer, Duke Cancer Institute
warren.kibbe@duke.edu
@wakibbe

2. Outline
• Cancer is a Grand Challenge
• Bioinformatics and Genomics in
cancer
• Precision Oncology / Precision
Medicine

3. Personal & Professional Background
• PhD in Chemistry at Caltech, Postdoc in
molecular genetics of RAS
• Cancer research for 20+ years - cancer
informatics, data science, healthcare
• Faculty in the Feinberg School of Medicine
at Northwestern for 15+ years
• Director NCI CBIIT 2013-2017; Acting NCI
Deputy Director 2016-2017
• Lost three grandparents to cancer

4. (10,000+ patient tumors and increasing)
Courtesy of P. Kuhn (USC)
2006-2015:
A Decade of Illuminating the
Underlying Causes of Primary
Untreated Tumors Omics
Characterization
Cancer is a grand challenge
• Deep biological understanding
• Advances in scientific methods
• Advances in instrumentation
• Advances in technology
• Data and computation
• Mathematical models
Cancer Research and Care generate
detailed data that is critical to
create a learning health system for cancer
Requires:

5. This redefinition has been driven by improved biological understanding

6. This change has been driven by improved technology - sequencing, imaging,
nanotech, drug developing, computing and the availability of data about
patient response to therapy

7. Changes in
Lung
Cancer

8. Health vs Disease
• What is ’normal’?
• Systematic and measurement error
• Biological heterogeneity
• Population Health

9. Team Science is critical
Clinical Trials
Biostatists
Bioinformatics
Clinical Care
Clinical Research
EHRs, Imaging, Lab Systems
Data Science
Analytics and Visualization
Open Data enhances collaboration and team science!

10. Terms/Vocabulary
• Single Nucleotide Polymorphisms –
SNPs
– Variation in a single base of DNA. In
germline human DNA, more than 50M
SNPs have been identified
– Identified and analyzed using
sequencing or array-based methods

11. Terms/Vocabulary
• Transcriptome (RNA transcripts made
in a single cell)
• Measured with expression arrays or
RNAseq

12. Terms/Vocabulary
• Methylome (methylated DNA)
• Measured using array-based
methods or methylSEQ
• Whole Genome Sequencing (WGS)
• Whole Exome Sequencing (WES)

13. Genomics
• Trying to measure changes in:
– Copy number (CNV)
– Point mutations (SNP)
– Insertions/deletions
– Methylation
• With either sequencing or arrays

14. Next Gen Sequencers

16. Assembly and identification of mutations

17. Fusions drive many pediatric cancers

20. What is Precision Medicine?

21. Precision Medicine
• Data driven prevention, screening,
treatment, survivorship decisions based
on your information
• -omics, imaging, phenotyping
• Sophisticated analysis of changes in the
genome, proteome, transcriptome,
epigenome, and evaluating those
changes for diagnosis and prediction of
response on outcomes

24. Histology + Molecular Classification

25. Breast cancer classification

26. Scale is changing!

27. How do we solve problems in Cancer
• Support and incentives for team science,
collaboration
• We need FAIR, open data
• Support open source, open science
• Support for rapid innovation

28. From HBR, June 2016
Sharing and complexity

29. Machine Learning
• Large data sets, particularly
population-based with a well-
annotated comparator set, are ideal
• Machine Learning and Deep Learning
on image features is feasible,
accurate, reproducible and scalable

31. Sebastian Thrun

32. 4/3/2017

33. Expert Systems vs Machine Learning
• In 1945, the British philosopher Gilbert
Ryle identified two kinds of knowledge—
factual, propositional knowledge that can
be ordered into rules—“knowing that.”
versus implicit, experiential, skill-based—
“knowing how.”
• Machine Learning is based on ‘learning
how’. Expert systems, or rule based
machines, are based on ‘knowing that’.

34. Human Cognition
Three kinds of learning:
• Learning that – rule-based knowledge
• Learning how – experiential knowledge
• Learning why – integrative, explanatory
knowledge

35. Machine Learning, AI
• Machine Learning
• Deep Learning
• Cognitive Computing
• Neuromorphic Computing
• Assistive Devices

36. Real World Evidence
• Needs big data!
• Needs population representation
• Need epidemiologists and
statisticians to understand the
potential biases in representation
• EHRs, NLP, Machine Learning can
power real world evidence learning
• Critical for a Learning Health
System

37. Genomics is the beginning of
precision medicine, not the end!

38. Biology and Medicine are now
data intensive enterprises
Scale is rapidly changing
Technology, data, computing and
IT are pervasive in the lab, the
clinic, in the home, and across the
population

39. Questions?
Warren Kibbe, Ph.D.
warren.kibbe@duke.edu
@wakibbe