Pharmaceutical companies are undergoing a digital transformation. By experimenting with new initiatives, they are positioned to play a role in the revolution of healthcare. This transformation is driven by data from internal and external sources, including
both -omic data and that from digital devices. Bio-IT World WEST, part of Molecular Medicine Tri-Conference, brings together all the stakeholders involved in this transformation. Your registration includes the option to
track-hop to the other programs at the Molecular Med TRI-CON as well as the Hackathon, plenary keynote, exhibit/poster hall, and more!
Every facet of healthcare and medicine now generates and has access to enormous amounts of data from across sources, organizations, and the world. The pharmaceutical industry plays a key role in driving informatics for translational research
and precision medicine. The 12th Annual Digitalization of Pharma R&D conference will discuss the challenges related to integrating, analyzing, and interpreting data from clinical trials, sequencing, electronic health records,
and wearables. We will discuss informatics strategy for entire organizations from business goals to infrastructure and storage projects. Special attention will be paid to artificial intelligence, machine learning, natural language processing, and
how companies are integrating these tools into their informatics infrastructure. Join informatics experts from pharma, biotech, and biomedical research communities to discuss these challenges and real-world examples of informatics projects driving
precision medicine.
Final Agenda
Monday, March 2
10:30 Conference Program Registration Open
(please see Keynote pages for details)
11:45 Organizer’s Opening Remarks
Cindy Crowninshield, RDN, LDN, HHC, Executive Event Director, Cambridge Healthtech Institute
11:50 Chairperson’s Remarks
Allison Proffitt, Editorial Director, Bio-IT World
11:55 Keynote Introduction, Benchling
Ashoka Rajendra, Head, Product, Registry, Inventory, Benchling
12:10 pm KEYNOTE PRESENTATION: The AI Bubble and the Emerging Thinking Economy
Pietro Michelucci, PhD, Director, Human Computation Institute
This presentation presents a realistic assessment of the “AI bubble” – where there is value, where there is hype, and how human-in-the-loop computing gives us futuristic AI capabilities today that co-evolve with AI technology and even
help improve AI.
12:40 PANEL DISCUSSION: Data Quality in Human Computation Systems
Is today’s artificial intelligence fervor based on hype or is it happening? We’ve seen some amazing results from AI-based systems, fueled by increases in processing speed that render traditional applications finally practicable. At the same
time, powerful new techniques are emerging including fruitful human/AI partnerships and recent successes based on combining crowdsourcing with machine learning. These new methods dovetail nicely with special challenges posed by precision medicine,
often entailing complex interdependencies among data acquisition, analysis, privacy, and ethics. That said, they also introduce a new set of challenges as we navigate issues of transparency, trust, and reliability where automated systems are involved.
This panel will discuss recent work in online collective systems that combine human and machine-based information processing in the biomedical space, how these systems could be applied to precision medicine, and how to avoid some of the potential
pitfalls associated with these approaches. We also discuss an information processing ecosystem designed to accelerate precision medicine research while mitigating associated complexity and resource needs.
Moderator:
Allison Proffitt, Editorial Director, Bio-IT World
Panelists: Jennifer Couch, PhD, Chief, Structural Biology and Molecular Applications Branch, Division of Cancer Biology and Citizen
Science Coordinator, National Cancer Institute
Devin
Krotman, Director, IBM Watson AI XPRIZE
Vani
Mandava, Director, Data Science Outreach, Microsoft Research
Pietro Michelucci, PhD, Director, Human Computation Institute
Ginger Tsueng, PhD, Scientific
Outreach Project Manager, Department of Integrative, Structural and Computational Biology, The Scripps Research Institute
1:30 Bio-IT World WEST Luncheon Presentation: Accelerating the Exchange of Data in Healthcare and Life Sciences
Fred Lee, MD, MPH, Head of Health Care, Life Sciences Business Development, AWS Data Exchange, AWS
Predictive models and algorithms in healthcare and life sciences (HCLS) have emerged from the combination of patient data and advanced analytics. With machine learning and AI technologies becoming commoditized, scalable access to patient data now throttles
the build of such predictive analytics. We will discuss how the AWS Data Exchange, as a digital marketplace for data, addresses this ‘data bottleneck’ by accelerating data exchange in a regulatory compliant, economically sustainable, and
cloud-native manner.
2:05 Session Break
2:20 Chairperson’s Remarks
Alan S. Louie, PhD, Research Director, Life Sciences, IDC Health Insights
2:25 Running Too Fast with AI, Pitfalls of Bad Data
Faisal Khan, PhD, Executive Director, Advanced Analytics and AI, AstraZeneca
The use of artificial intelligence and data science approaches and technologies is experiencing explosive growth in the pharmaceutical industry. The plethora of opportunities provide an exciting range of applications to explore. However, as the field
has grown, many folks are employing and leveraging AI without keeping in mind the rigors required for good science, including preparing the data and how it’s analyzed. At the end of the data, it’s still garbage in/garbage out.
2:55 Building Data Science Teams for Pharma – Myths and Realities
Mustaqhusain Kazi, Head of Personalized Healthcare, Pharma Informatics, Genetech
It is hoped that combining real-world data with sophisticated statistical and machine learning algorithms could lead to realizing the dream of personalized healthcare. In order to make this dream a reality, data scientists need to embrace organizational
data and methodological complexities not commonly encountered elsewhere. In this talk, the speaker would share his experiences in building data science teams ready to tackle the challenge of delivering personalized healthcare for everyone.
3:25 Leveraging Omics for Discovery and Development of New Drugs
Howard J. Jacob, PhD, Vice President and Head, Genomic Research, Drug Discovery Science & Technology, Distinguished Research Fellow, Abbvie
3:55 Lightweight, Practical Cross-Domain Metadata
Chris Dwan, Senior
Technologist and Independent Life Sciences Consultant
It is increasingly clear that robust metadata management is one of the keys to unlocking the potential of biomedical data. Creating and enforcing usable standards for this metadata without stifling innovation and productivity or violating compliance requirements
is a crucial balancing act with both technical and non-technical components. This talk will discuss real-world examples of metadata systems in use for sequencing, sample management, clinical phenotypes, diagnostic reports, and even analytical provenance
chains from computational pipelines.
4:25 Refreshment Break and Transition to Plenary Keynote
4:35 Welcome Remarks
Cindy Crowninshield, RDN, LDN, HHC, Executive Event Director, Cambridge Healthtech Institute
4:45 PLENARY KEYNOTE INTRODUCTION
Thomas Westerling-Bui, PhD, Senior Scientist, Regional Business Development, Aiforia
5:00 PLENARY KEYNOTE PRESENTATION: High-Performance Medicine
Eric Topol, MD, Founder and Director, Scripps Research Translational Institute (SRTI); Author, Deep Medicine: How Artificial Intelligence
Can Make Healthcare Human Again
6:00 Grand Opening Reception in the Exhibit Hall with Poster Viewing, Speed Networking, Book Signing, and Meetup Group
7:30 End of Day
Tuesday, March 3
7:30 am Registration Open and Morning Coffee
(please see Keynote pages for details)
8:00 Organizer’s Remarks
Cindy Crowninshield, RDN, LDN, HHC, Executive Event Director, Cambridge Healthtech Institute
8:05 NEW: Chairperson’s Remarks
Annastasiah Mudiwa Mhaka, PhD, Founder and Principal, Mawambo Lifesciences; Co-Founder, Convenor and Former President, Alliance for AI in Healthcare (AAIH)
8:10 Keynote Sponsor Introduction
Vasu Rangadass, President, CEO, L7 Informatics, Inc.
8:25 KEYNOTE PRESENTATION: AI and Big Data Strategies in Accelerating Clinical Research for Faster Rare Disease Cures
Harsha Rajasimha, MS, PhD, Founder, Jeeva Informatics Solutions, Inc.; Founder and Chairman, IndoUSrare; Co-Director, Rare Diseases Systems
Biology Initiative, George Mason University
After losing a child to a rare congenital disease, Dr. Rajasimha became determined to apply his clinical genomics data research experience to develop solutions to help accelerate clinical research leading to faster cures for rare disease. Dr. Rajasimha
will discuss his efforts in fostering collaborative bridges between patient advocacy groups and researchers in the USA and their counterparts in India to help accelerate clinical research, trials, and therapy access across borders. The talk will include
recent global initiatives to accelerate screening, diagnosis, and treatments of rare and undiagnosed diseases. He will also share work on the development of an AI-driven digital health platform to improve clinical trial operational efficiencies while
significantly reducing costs and travel burden on patients.
8:55 PANEL DISCUSSION: Applications of AI Technologies in Pharmaceuticals: Facilitating Development of Therapeutics in Treating Rare Diseases
The complex research framework involving industry, academia, and government to discover and develop new therapeutic products makes drug discovery a laborious process. With rapid strides that life sciences companies are making in the fields of gene and
cell therapies, -omics technologies, and smart molecule approaches, an urgent need exists for cost-effective, time-effective, and advanced technologies to analyze large databases of information to help develop novel therapies. Organizations are recognizing
the value of AI-based platforms and tools to leverage data to find hidden drug-disease correlations. Also, structured and unstructured data can be derived from multiple sources as never before. This panel brings senior level experts in pharma, AI-based
technology, and government to discuss the role of AI platforms and tools to establish a robust pipeline as part of drug discovery portfolio and address new therapeutic areas, including rare diseases.
NEW: Moderator: Annastasiah Mudiwa Mhaka, PhD, Founder and Principal, Mawambo Lifesciences; Co-Founder, Convenor and Former President, Alliance for AI in Healthcare (AAIH)
Panelists: Tom Defay, Senior Director, R&D Strategy and Alliances, SPMD, Strategy, Program Management and Data Sciences, Alexion
Harsha Rajasimha, MS, PhD, Founder, Jeeva Informatics Solutions, Inc.; Founder and Chairman, IndoUSrare; Co-Director, Rare Diseases Systems Biology Initiative, George Mason University
Vasu Rangadass, President, CEO, L7 Informatics, Inc.
9:40 Refreshment Break in the Exhibit Hall with Poster Viewing, Speed Networking, Book Signing, and Meetup Group
10:40 Chairperson’s Remarks
Pankaj Agarwal, Chief Computational Biologist, BioInfi
10:45 Advancing the Use of Real World Data to Support R&D and Personalized Healthcare
Ryan Copping,
PhD, Global Head of Analytics, PHC Data Science, Personalized Healthcare (PHC), Product Development, Roche & Genentech
Generating insights from Real World Data (RWD) is a critical success factor for personalized healthcare. This presentation will look at some of the advancements being made in terms of data (access/growth/quality/linkages, etc.), analytics and technology
and will share some specific examples from Roche/Genentech’s R&D efforts as well some of the challenges and opportunities for the future.
11:15 NEW: CO-PRESENTATION: Target Identification and Drug Repurposing: From Machine Learning Theory to Practical Experience
Pankaj Agarwal, Chief Computational Biologist, BioInfi
Deepak Kumar Rajpal, PhD, Head, Bioinformatics, Translational Sciences, Sanofi
AI and Machine Learning are being widely used in drug discovery, yet there are significant challenges because of the lack of training examples in the biological data space. We will show three case studies examining the same problem from different angles
and using different methods. You will see the limitations of each approach and how different validation schemes impact results.
Presentation delivered via a live, interactive video conferencing platform.
11:45 Massively Multitask Profile-QSAR: Applications of
Experiment-Quality Models for >8500 Novartis Biochemical And Cellular Assays
Eric Martin, PhD,
Director, Computer Aided Drug Design, Novartis Institutes for BioMedical
Research, Inc.
Profile-QSAR predicts biological activity with unprecedented accuracy and applicability domain by combining 20 million IC50 measurements from 2 million compounds covering 12,000 assays. The 8600 “successful” models have average accuracy comparable
to 4-concentration IC50 experiments. Models are updated monthly, storing 60 billion predictions for 5.5 million compounds in a databricks database. It has been applied to 150 projects for virtual screening, selectivity design, tox and MoA prediction,
and more.
12:15 pm Session Break
12:20 BIO-IT WORLD WEST CO-LUNCHEON PRESENTATION I: Describing Chemistry to Algorithms: Why Scientific Expertise Improves Accuracy
Alpha Lee, PhD, Doctor, Physics, University of Cambridge
Matthew McBride, MS, Director, Science IP, CAS
If a picture is worth a thousand words, then a chemical structure is worth thousands of features. Join Dr. Alpha Lee from the University of Cambridge to see how impactful descriptors are on predictions. If your AI initiatives aren’t
meeting expectations, see how better representations of chemistry structures improve algorithm performance. CAS descriptors are derived from centuries of scientific knowledge and are proven to improve AI accuracy.
12:50 BIO-IT WORLD WEST LUNCHEON PRESENTATION II: Towards the Digital Lab
Paul Denny Gouldson, Chief Digital Officer, Digital Solutions, Zifo RnD Solutions
1:20 Refreshment Break in the Exhibit Hall with Poster Viewing, Speed Networking, Book Signing, and Meetup Group
2:00 Breakout Discussions in the Exhibit Hall (please click 3:00 Transition to Keynote Session
(please see Keynote pages for details)
3:15 Organizer’s Remarks
Christina Lingham, Executive Director, Conferences and Fellow, Cambridge Healthtech Institute
3:20 Keynote Introduction
Allison Mallory, PhD, Director, R&D Molecular Biology, Stilla Technologies
3:35 What Does the New Era of Genomic Medicine Look Like? Effects on Patient Care, Therapeutics, and Diagnostics
20 years after the completion of the first draft of the Human Genome Project, there is compelling evidence of genomics delivering the rich promise of precision medicine. There have been major advances in the throughput and affordability of genome sequencing,
enhanced tools for genome analysis and interpretation, new paradigms for therapeutics and strong signs of clinical benefit using genome editing. But major challenges remain. In this special plenary roundtable, three established pioneers of genomic
medicine – David Haussler, Stephen Kingsmore, and Liz Worthey – offer their insights on the extraordinary advances in genomic medicine over the past 1-2 decades and share their hopes and concerns for the future of our field.
Moderator: Kevin Davies,
PhD, Executive Editor, The CRISPR Journal, Mary Ann Liebert, Inc.
Panelists: Stephen Kingsmore, MD, DSc, President/CEO, Rady Children’s Institute for Genomic Medicine
David Haussler, PhD, Investigator, Howard Hughes Medical Institute; Distinguished Professor, Biomolecular Engineering, University of California, Santa Cruz; Scientific Director, UC Santa Cruz Genomics Institute; Scientific Co-Director, California
Institute for Quantitative Biosciences (QB3)
Elizabeth
Worthey, PhD, Director, Genomic Medicine, University of Alabama, Birmingham School of Medicine
4:50 Spring Fling Celebration in the Exhibit Hall with Poster Viewing, Speed Networking, Book Signing, and Meetup Group
6:00 End of Day
Wednesday, March 4
6:45 am Registration Open
7:00 BREAKFAST PANEL DISCUSSION: The Time is NOW: Creating Meaningful Change for Women in the Workplace (Sponsorship Opportunity Available)
(please see Women in Science page for details)
Moderator:
Robin Toft, Author of WE CAN, The Executive Woman’s Guide to Career Advancement; Founder and Chairman, Toft Group Executive Search
Panelists: Camille Samuels, MBA, Partner, Venrock
Paul
Hastings, President and CEO, Nkarta Therapeutics, Inc
Teresa
L. Wright, MD, Staff Physician, Medicine, San Francisco Veterans Administration
(please see Keynote pages for details)
8:00 Organizer’s Remarks
Mana Chandhok, Conference Producer, Cambridge Healthtech Institute
8:05 Chairperson’s Remarks
Joseph Ferrara, CEO, Boston Healthcare
8:10 Keynote Introduction
Fred Lee, MD, MPH, Head of Health Care, Life Sciences Business Development, AWS Data Exchange, AWS
8:25 KEYNOTE PRESENTATION: The Value and Application of Informatics in Cancer Care Delivery
Debra A. Patt,
MD, Vice President, Public Policy & Academic Affairs, Medical
Oncologist, Texas Oncology Cancer Center & Editor in Chief, Journal of Clinical Oncology-Clinical Cancer Informatics
8:55 KEYNOTE PANEL DISCUSSION: Pragmatic Use of Informatics in Cancer Care Delivery and Cancer Research: Big Data and AI Take on Cancer
Moderator: Joseph Ferrara, CEO, Boston Healthcare
Panelists: Mark Hulse, Chief Digital Officer, City of Hope
Debra A. Patt, MD, Vice President, Public Policy & Academic Affairs, Medical Oncologist, Texas Oncology Cancer Center & Editor in Chief, Journal of Clinical Oncology-Clinical Cancer Informatics
Kristin Beaumont, PhD, Assistant Professor, Assistant Director of Single Cell Genomics Technology Development Icahn Institute, Dept. of Genetics & Genomic Sciences, Icahn School
Ajay Shah, PhD, Executive Director & Head of IT for Translational Medicine, Bristol-Myers Squibb
Paul A. Rejto, PhD, Vice President, Head of Translational Research, Pfizer Oncology R&D
9:40 Refreshment Break in the Exhibit Hall with Poster Viewing, Speed Networking, Book Signing, and Meetup Group
10:40 Chairperson’s Remarks
Faisal Khan, PhD, Executive Director, Advanced Analytics and AI, AstraZeneca
10:45 NEW: On the Road to Genetically Validated Targets in Kidney Diseases: Computational Challenges
Thomas Tibbitts, PhD, Senior Vice President, Computational Discovery, Goldfinch Bio
Focal segmental glomerulosclerosis (FSGS) is scarring of the kidney that can lead to kidney failure. To discover genetic variants associated with FSGS, we built the Kidney Genome Atlas (KGA 1.0), which contains whole genomes (>30X) on 23000 individuals,
including 2000 cases of FSGS and other proteinuric disorders. To efficiently process and analyze this large amount of genomic data we have implemented infrastructure and pipelines on AWS and launched a web portal to facilitate target discovery.
11:15 PANEL DISCUSSION: Partnering for AI Startups and Pharma
Topics to be Discussed:
- Meeting expectations, what is good for both sides
- How we can facilitate the transformation of pharma R&D
- Best practices
Moderator: Annastasiah Mudiwa Mhaka, PhD, Founder and Principal, Mawambo Lifesciences; Co-Founder, Convenor and Former President, Alliance for AI in Healthcare (AAIH)
Panelists:
Joseph Szustakowski, PhD, Vice President of Translational Bioinformatics, Informatics & Predictive Sciences, Bristol-Myers Squibb
Jonathan Allen, PhD, Computational
Scientist, ATOM Consortium
Christopher Willis, PhD, Lead IT Business Partner, Precision Medicine, BMS
Gini Deshpande, PhD, Founder & CEO, NuMedii, Inc.
12:00 pm PANEL DISCUSSION: Recruiting Data Scientists
Given the massive expansion of Data Science and the consequent need for experts in this area across all industries, there is a massive competition to find and source the talent required. How can we identify, recruit and retain the best data scientists?
What are the pitfalls and challenges to avoid and success stories we can learn from?
Moderator: Faisal Khan, PhD, Executive Director, Advanced Analytics and AI, AstraZeneca
Panelists: Mustaqhusain Kazi, Head of Personalized Healthcare, Pharma Informatics, Genetech
Zahra ‘Nasim’ Eftekhari, Senior Manager, Head of Applied AI and Data Science, City of Hope
José Duca, PhD, Global Head, Computer-Aided Drug Discovery, Novartis
12:45 Session Break
12:50 Enjoy Lunch on Your Own
1:20 Refreshment Break in the Exhibit Hall with Last Chance Poster Viewing, Speed Networking, Book Signing, and Meetup Group
2:00 Chairperson’s Remarks
Geraldine A. Van der Auwera, PhD, Director of Outreach and Communications, Data Sciences Platform, Broad Institute
2:05 Fake It ‘til You Make It (Reproducible): Synthetic Data Resources for Genomics
Geraldine A. Van der Auwera, PhD, Director of Outreach and Communications, Data Sciences Platform, Broad Institute
The computational reproducibility of published biomedical research is limited by data access restrictions, affecting not just researchers who wish to reuse published analysis code, but also tool developers and educators who lack suitable example data
for testing and training. We present: 1) a prototype pipeline that wraps established open-source data simulation tools to generate publicly shareable synthetic sequence data at any scale; and 2) a plan to develop community resources.
2:35 Drug Targets with Genomic Support: A Genomics-based Strategic Framework for Improving Target Discovery and Accelerating Drug Development
Justin Wade Davis, PhD, ACOS Research Fellow, Director, Computational Genomics, Genomics Research Center (GRC), AbbVie
Despite strong vetting for disease activity, only 10% of candidate new molecular entities in Ph1 clinical trials are approved. Analyzing historical data, Nelson et al. 2015 concluded pipeline drug targets with human genetic evidence of disease association
are twice as likely to lead to approved drugs. We extend this using updated data, test prospectively whether genetic evidence predicts future successes, and introduce statistical models adjusting for target and indication-level properties.
3:05 Close of Conference