Keynote Speeches
(1) Title: Obstacles and Options for Big-Data
Applications in Biomedicine: The role of standards and normalizations
Christopher G. Chute, MD, DrPH
Professor of Medical Informatics,
Mayo Clinic College of Medicine, and IHI Fellow,
University of Minnesota, MN
Abstract
Advances in computing
capabilities are palpably evident throughout many industries manifest by
unprecedented, large-scale data integration and inferencing. Branded as
“big-data” in many
cases, the question of whether such techniques can leverage advances in
biomedicine and clinical
practice are obvious. High-throughput clinical analytics, synthesizing
genomic and clinical
attributes of a particular patient, portends predictive models that can
directly influence
clinical care decisions. However, to make this widely shared vision
practical and scalable,
barriers attributable to data heterogeneity dominate. Methods and strategies
to increase the
comparability and consistency of healthcare related data will be discussed.
Biography
Dr. Chute received his undergraduate and medical training at Brown
University, internal medicine residency at Dartmouth, and doctoral training
in Epidemiology at Harvard. He is Board Certified in Internal Medicine, and
a Fellow of the American College of Physicians, the American College of
Epidemiology, and the American College of Medical Informatics. He became
founding Chair of Biomedical Informatics at Mayo in 1988, stepping down
after 20 years in that role. He is now Professor of Medical Informatics and
Section Head. He is PI on a large portfolio of research including the
HHS/Office of the National Coordinator (ONC) SHARP (Strategic Health IT
Advanced Research Projects) on Secondary EHR Data Use, the ONC Beacon
Community (Co-PI), the LexGrid projects, Mayo’s CTSA Informatics, and
several NIH grants including one of the eMERGE centers from NGHRI, which
focus upon genome wide association studies against shared phenotypes derived
from electronic medical records. Dr. Chute serves as Vice Chair of the Mayo
Clinic Data Governance for Health Information Technology Standards, and on
Mayo’s enterprise IT Oversight Committee. He is presently Chair, ISO Health
Informatics Technical Committee (ISO TC215) and Chairs the World Health
Organization (WHO) ICD-11 Revision. He also serves on the Health Information
Technology Standards Committee for the Office of the National Coordinator in
the US DHHS, and the HL7 Advisory Board. Recently held positions include
Chair of the Biomedical Computing and Health Informatics study section at
NIH, Chair of the Board of the HL7/FDA/NCI/CDISC BRIDG project, on the Board
of the Clinical Data Interchange Standards Consortium (CDISC), ANSI Health
Information Standards Technology Panel (HITSP) Board member, Chair of the US
delegation to ISO TC215 for Health Informatics, Convener of Healthcare
Concept Representation WG3 within the (TC215), Co-chair of the HL7
Vocabulary Committee, Chair of the International Medical Informatics
Association (IMIA) WG6 on Medical Concept Representation, American Medical
Informatics Association (AMIA) Board member, and multiple other NIH
biomedical informatics study sections as chair or member.
(2) Protein Structure Determination On Demand
Prof. Ming Li
Canada Research Chair in Bioinformatics
School of Computer Science
University of Waterloo
Abstract
Protein structure prediction by computers at best may serve as a
screening method, and the current high-throughput protein structure
determination methods are costly and will never exhaust all proteins. A
complementary approach is "protein structure determination on demand", say
in a week. We will discuss two approaches that would realize this goal:
automatic protein structure determination using NMR data and mass
spectrometry data.
Biography
Ming Li is a Canada Research Chair in Bioinformatics and a University
Professor at the University of Waterloo. He is a fellow of the Royal Society
of Canada, ACM, and IEEE. He is a recipient of E.W.R. Steacie Fellowship
Award in 1996, the 2001 Killam Fellowship, and the 2010 Killam Prize.
Together with Paul Vitanyi they have co-authored the book "An Introduction
to Kolmogorov Complexity and Its Applications". He is a co-managing editor
of Journal of Bioinformatics and Computational Biology.
(3) The CellOrganizer Project: An Open Source
System to Learn Image-derived Models of Subcellular Organization over Time
and Space
Prof.
Robert F. Murphy
Lane Center for Computational Biology and Department of Biological Sciences
Carnegie Mellon University, Pittsburgh, Pennsylvania, USA
and
Faculty of Biology and Freiburg Institute for Advanced Studies
Albert Ludwig University of Freiburg,
Freiburg, Germany
Abstract
The CellOrganizer project (http://cellorganizer.org) provides open source tools for
learning generative models of cell organization directly from images and for
synthesizing cell images (or other representations) from one or more of
those models. Model learning captures variation among cells in a collection
of images. Images used for model learning and instances synthesized
from models can be two- or three-dimensional static images or movies.
Current components of CellOrganizer can learn models of cell shape, nuclear
shape, chromatin texture, vesicular organelle number, size, shape and
position, and microtubule distribution.
These models can be conditional upon each other: for example, for a
given synthesized cell instance, organelle position will be dependent upon
the cell and nuclear shape of that instance.
The models can be parametric, in which a choice is made about an
explicit form to represent a particular structure, or non-parametric, in
which distributions are learned empirically.
One of the main uses of the system is in support of cell simulations:
models learned from separate experiments can be combined into one or more
synthetic cell instances that are output in a form compatible with cell
simulation engines such as MCell, Virtual Cell and Smoldyn.
Another important application of the system is in comparison of
target patterns and perturbagen effects in high content screening and
analysis. This is currently done
using numerical features, but these are difficult to compare across
different microscope systems or cell types since features can be affected by
changes in more than one aspect of cell organization. More robust
comparisons can be made using generative model parameters, since these can
distinguish effects on cell size or shape from effects on organelle pattern.
Ultimately, it is anticipated that collaborative efforts by many groups will
enable creation of image-derived generative models that permit accurate
modeling of cell behaviors, and that can be used to drive experimentation to
improve them through active learning.
Biography
Robert F. Murphy
is the Ray and Stephanie Lane Professor of Computational Biology and
Professor of Biological Sciences, Biomedical Engineering, and Machine
Learning at Carnegie Mellon University, and Director (Department Head) of
the Lane Center for Computational Biology in the School of Computer Science.
He is also Honorary Professor of Biology at the Albert Ludwig
University of Freiburg, Germany, a Fellow of the
American Institute for Medical and Biological Engineering, and the recipient
of an Alexander von Humboldt Foundation Senior Research Award. He is
Past-President of the International Society for Advancement of Cytometry,
and is a member of the National Advisory General Medical Sciences Council
and the NIH Council of Councils.
He has published over 190 research papers in the areas of cell and
computational biology.
Dr. Murphy’s career has centered on combining fluorescence-based cell
measurement methods with quantitative and computational methods. In the mid
1990’s, his group pioneered the application of machine learning methods to
high-resolution fluorescence microscope images depicting subcellular
location patterns. His current
research interests include image-derived models of cell organization and
active machine learning approaches to experimental biology.
(4) Protein 3D Structure from Genomic Sequences and Application to Cancer
Genomics
Chris Sander
Director, Computational Biology Center
Memorial Sloan-Kettering Cancer Center
New York City
Abstract
Amino acid covariation in proteins, extracted from the evolutionary sequence
record, can be used to fold proteins, including transmembrane proteins.
Addressing a fundamental challenge in computational molecular biology, a new
prediction method (EVold) applies a maximum entropy approach to infer
evolutionary couplings between sequence positions from correlated mutations
in the multiple sequence alignment of a protein family. When translated to
distance constraints, such residue-residue couplings are sufficient to
generate good all-atom models of proteins from different fold classes,
ranging in size from 50 to more than 300 residues. We use the technique to
predict previously unknown 3D structures of large transmembrane proteins of
biomedical interest, from their sequences alone. We show how the method can
plausibly predict oligomerization, functional sites, and conformational
changes in transmembrane proteins. Project co-leader: Debora Marks, Harvard
Medical School; co-authors (alphabetical): Lucy Colwell, Thomas Hopf, Andrea
Pagnani, Burkhard Rost, Robert Sheridan, Riccardo Zecchina. See
http://bit.ly/tob48p (PDF) and
www.evfold.org. The discovered
evolutionary couplings provide insight into essential interactions
constraining protein evolution and, with the rapid rise in large-scale
sequencing, are likely to facilitate a comprehensive survey of the universe
of protein structures by a combination computational and experimental
technology. Applications to cancer genomics relate to the interpretation of
the functional impact of cancer-related mutations and the design of targeted
therapeutics.
Biography
Chris Sander is acknowledged as an initiating leader in the field of
computational biology, an interdisciplinary field that aims to solve
important problems in biology using techniques of mathematics, physics,
engineering, and computer science. He is Head of the Computational Biology
Center at Memorial Sloan Kettering Cancer Center and Tri-Institutional
professor at Rockefeller and Cornell Universities.
Sander's current research interests are in computational genomics and
systems biology, with a focus on network pharmacology and the development of
targeted combinatorial therapy in cancer. His group uses the results of
high-throughput sequencing to compute protein 3D structures and functional
sites; and studies the regulation of gene expression by small RNAs. In 2012,
he is active in the International Cancer Genomics Consortium, the NIH Cancer
Genome Atlas Project, the NCI Integrative Cancer Biology Program and a
leader in the bioPAX and PathwayCommons community
efforts to create an open-source information resource for biological
pathways. He has published more than 250 peer-reviewed articles in physics
and biology (http://bit.ly/Uk990K) with an h-index of 100.
Previously, Sander co-founded the research section of the European
Bioinformatics Institute in Cambridge, England, and was founding chair of
the department of Biocomputing at the European Molecular Biology Laboratory
in Heidelberg. He is a Fellow of the International Society for Computational
Biology.
|
