SC2: Leveraging Data and Analytics for Drug Discovery

Monday, September 21, 8:00-11:00am

Effectively utilizing data can help biopharma companies better identify new potential drug candidates and develop them into effective, approved and reimbursed medicines more quickly. This potential cannot be unlocked without addressing key issues including data collection, management and integration of complex and disparate datasets; scalability; analysis and visualization tools, and identifying multiple drug targets (not just single drug targets) to work together as a network. This workshop will explore these issues and the role that data has on drug design to identify biomarkers and discover targets for potential therapies.

Outline:
8:00 – 8:10 am Organizer Remarks and Welcome

8:10 – 8:55 Big Data Visualization
Georges Grinstein, Ph.D., Professor, Computer Science Department; Director, Institute for Visualization and Perception Research; Director, Center for Biomolecular and Medical Informatics, University of Massachusetts Lowell
This presentation will focus on the roles visualization plays and can play in all steps of dealing with data (big heterogeneous data) in the drug discovery process. I will provide a review of the most valuable visualizations, discuss their advantages, constraints, best current applications and how they could potentially be used. I will then discuss where visualization is heading to help some very difficult problems.

8:55  9:25 Big Data for Drug Discovery
Nirmal Keshava, Ph.D., Senior Principal Informatics Scientist, Big Data Analytics, AstraZeneca

9:25 – 9:40 Refreshment Break

9:40 – 10:10 Data Analysis and Analytics
Mark Borowsky, Ph.D., Executive Director, Data Analysis, Novartis

10:10 – 10:40 Big Data Hardware and Infrastructure
Vassilios Pantazopoulos, Senior Manager, High Performance Computing, Pfizer

10:40 – 11:00 Q&A/Closing Comments

Instructors:

Mark Borowsky, Ph.D., Executive Director, Data Analysis, Novartis
Mark Borowsky is the Global Head of Scientific Data Analysis at the Novartis Institutes for BioMedical Research (NIBR). The SDA team builds and applies analysis capabilities – statistics, visualization, algorithm development, data mining – to answer biological questions. The team works closely with bench scientists and bioinformatics groups embedded in NIBR’s scientific departments. Prior to joining NIBR, Mark received his PhD in Biology from the Massachusetts Institute of Technology where he studied the cytoskeleton-cell membrane interface. Mark performed post-doctoral work on host-pathogen interactions at University of California at Berkeley, and then began his bioinformatics career at Incyte. There, Mark managed a microbial pathogen genome database and built a data analysis team that identified novel splice variants and full length human cDNAs for candidate drug targets. Mark then spent 5 years at the Broad Institute, where he contributed to the human genome project and initiated several projects in the Microbial Sequencing Center, focusing on drug resistant Mycobacterium tuberculosis. In his last stop before NIBR, Mark served as Director of the NextGen sequencing core at Massachusetts General Hospital and Director of Bioinformatics in the Department of Molecular Biology at MGH, where he developed both resources into highly collaborative facilities performing next generation sequencing and data analyses in diverse areas of biomedical research.

Georges Grinstein, Ph.D., Professor, Computer Science Department; Director, Institute for Visualization and Perception Research; Director, Center for Biomolecular and Medical Informatics, University of Massachusetts Lowell
Dr. Georges Grinstein is Professor of Computer Science at the University of Massachusetts Lowell, past head of its Bioinformatics and Cheminformatics Program, Co-director of its Institute for Visualization and Perception Research, and CSO of Weave Visual Analytics. He received his Ph.D. in Mathematics from the University of Rochester. His work is broad and interdisciplinary, ranging from perceptual foundations of visualization to techniques for high-dimensional visualization, with the emphasis on the modeling, visualization, and analysis of complex information systems, most often biomedical in nature. He has over 40 years in academia with extensive private consulting, over 100 research grants, products in use nationally and internationally, several patents, numerous publications in journals and conferences, a book on interactive data visualization, founded several companies, and has been the organizer or chair of national and international conferences and workshops in Computer Graphics, in Visualization, and in Data Mining. He has mentored over 30 doctoral students and hundreds of graduate students. He has been on the editorial boards of several journals in Computer Graphics and Data Mining, a member of ANSI and ISO, a NATO Expert, and a technology consultant for various public agencies. For the last ten years he has co-chaired the InfoVis and VAST contests and has been developing the open source interactive visual analytics platform called Weave.

Nirmal Keshava, Ph.D., Senior Principal Informatics Scientist, Big Data Analytics, AstraZeneca
Nirmal is an experienced big data scientist and leader that has developed innovative solutions for multi-disciplinary problems involving advanced sensor platforms and algorithms, rigorous performance evaluation, and creative visualization. His contributions have spanned biomedical image/signal processing, neuroimaging, genomics, clinical informatics, biometrics, neuroscience, and multi-modal physiology. His goal is to generate insight and value by creatively exploiting data sets of all sizes and types and to work across boundaries to achieve project and institutional goals. Nirmal‘s background in signal processing is complemented by several years of in-depth technical and management experience and collaboration with many different academic, government, and commercial partners. He has served in a variety of leadership roles and enjoy defining visions and leading teams to achieve challenging goals.

Vassilios Pantazopoulos, Senior Manager, High Performance Computing, Pfizer
Vassilios is a Senior Manager within Pfizer Research Technology where he leads the strategy, development, and implementation of next generation research computing environments for Worldwide Medicinal Chemistry and Global Biotherapeutics throughout all of Pfizer. At Pfizer, Vassilios has lead the successful development and deployment of cutting edge technologies in support of drug discovery. Technologies deployed include: cloud computing, virtualization, big data analytics, data center infrastructure, protein modelling, statistical programming, GPU computing, virtual screening, 3D modeling, and pharmacokinetics. These technologies are all being used today to run some of Pfizer’s most complex calculations supporting research and clinical programs. Vassilios combines a life science background with over 18 years of experience engineering, managing, and deploying super computing environments used to support drug discovery. He started his career as a molecular biologist at Harvard Medical School where he authored several papers in the field of immunology. He quickly transitioned into the field of bioinformatics where he developed numerous applications used in gene discovery before moving on to a start up biotech company where he lead all aspects of the IT infrastructure for a fast growing company. Vassilios holds a BS in Biology from the University of Massachusetts at Amherst and a MS in Informatics from Northeastern University with a concentration in Network Security.