With the increased generation of data from a wide number of sources, including R&D, clinical, translational, genomic and health data, pharma and biotech must effectively manage, integrate, and analyze data from all stages of the pharmaceutical value chain to enable more informed decisions. Further, high-quality data is fundamental for all decision making processes in pharma and ensuring data consistency and correctness is of the highest priority for the industry right now. Track 10 explores current progress made in the analysis and integration of complex datasets, including genomic, discovery, clinical, external/internal collaboration and real world to transform all stages of R&D.

Tuesday, May 23

7:00 am Workshop Registration and Morning Coffee

8:00 – 11:30 Recommended Morning Pre-Conference Workshop*

(W5) Mobile Health, Virtual Research, Wearables, and Sensors; How to Accelerate Their Use and Adoption in Your Company

12:30 – 4:00 pm Afternoon Pre-Conference Workshops*

* Separate registration required.

2:00 – 6:00 Main Conference Registration Open

4:00 PLENARY KEYNOTE SESSION

5: 00 – 7:00 Welcome Reception in the Exhibit Hall with Poster Viewing

Wednesday, May 24

7:00 am Registration Open and Morning Coffee

8:00 PLENARY KEYNOTE SESSION

9:50 Coffee Break in the Exhibit Hall with Poster Viewing

DATA INTEGRATION, ANALYTICS & COLLABORATION

10:50 Chairperson’s Remarks

Yuriy Gankin, Vice President, CSO, Life Sciences, EPAM

11:00 Pharma R&D: Challenges & Opportunities

Ingrid Akerblom, Ph.D., Executive Director, Analytics and Knowledge Management, Amgen

The challenges and opportunities for pharmaceutical R&D have never been greater. The drive to bring value to stakeholders whether patients, payors or healthcare providers from our therapies is transforming our approach to data and analytics for insight generation. This presentation will explore the nature of that change and how it is leading to greater global collaboration internally and with partners.

11:30 From Big Data to Smart Data: Advancing a Data First Strategy

M. Hall Gregg, Ph.D., Vice President, Research & Development, Business Technology, Pfizer, Inc.

The pressure on pharmaceutical R&D organizations to accelerate innovation, to deliver quality medicines at the lowest possible cost, and to demonstrate the value of their medicine has never been greater. Enabling a culture where data is an enterprise asset is critical to being responsive to these challenges. A data first strategy focused on delivering data liquidity, agility, reuse and self-service allows data to be an enterprise asset and big data becomes smart data.

12:00 pm A Paradigm Shift in Informatics to Platform-Based Solutions

John Stalker, Director, Core Informatics (part of Thermo Fisher Scientific)

The pace of scientific change is accelerating far beyond the capabilities of traditional data management systems. A laboratory informatics platform should make life easier by removing barriers to progress and supporting a company’s unique workflows. This talk will discuss the benefits of a platform-based approach to informatics and how it adds value to organizations developing the next generation of biotherapeutics.

12:15 Smart Data Lakes - Transforming Pharma R&D, Customer Success Stories

Jim LaPointe, Managing Director, Pharma & Life Sciences, Cambridge Semantics

We will present use cases in production at some top tier Pharma companies and how they are leveraging Smart Data Lakes in cutting drug development times by years and realizing mammoth savings.

12:30 Session Break

12:40 Luncheon Presentation I: The Five Key Technologies Required to Deliver Global Mega-Scale Biomedical Data Analysis

Georges Heiter, Founder, Databiology

Dealing with the variety of biomedical data and real-world evidence by managing scale and complexity. Ensuring agility and simplicity to conduct any analysis on any data at any time. Delivering end-to-end provenance and reproducibility. Managing integrity & security of data and access. Enabling the flexibility to collaborate at any level and at any location.

 1:10 Luncheon Presentation II: HCL’s Next Generation Research Platform
Anil Verma, Vice President, Life Sciences, HCL  

HCL’s Next Generation Research Platform (NGRP) is a collaborative, pre-competitive ecosystem built with open standards and designed to support the new paradigm of Drug discovery with tightly integrated scientific capabilities from ‘best of breed’ technology partners. Learn how NGRP can help you accelerate new drug discovery by facilitating collaboration, mining scientific data, improving scientists’ productivity and adopting new technology capabilities

1:40 Session Break

DATA ANALYTICS & DATA INTEGRATION

1:50 Chairperson’s Remarks

Peter Covitz, Ph.D., Senior Director, Research & Translational IT, Biogen

1:55 If Data Is the Lifeblood of Scientific Research, Can We Breathe New Life into Pharmaceutical R&D by Improving the Circulation and Use of Data?

Bryan Takasaki, Ph.D., Director, R&D Information US Lead, AstraZeneca

There is considerable room for improvement in the way we share data and information amongst the global scientific community. Mining of the published literature is hampered by the lack of semantic standards and the sharing of structured quantitative data remains largely isolated and point-to-point. Progress in the drive to correlate biological mechanism and disease, preclinical and clinical results as well as clinical and real world evidence requires effective data sharing and collaboration between academia and multiple industries. This talk will explore the opportunities and challenges in addressing the shortcomings of the current scientific data sharing and collaboration paradigm.

2:25 Integration and Use of Thousands of Preclinical and Clinical Studies at Novartis

Philippe Marc, Ph.D., Director, Global Head Integrated Data Sciences, Novartis Institute for Biomedical Research

The Novartis translational medicine study data-warehouse became, in the past years, an essential tool for hundreds of researchers. It is fed every day with data from Novartis-sponsored preclinical and clinical studies, generated in house or at CROs. Basic architecture and use will be described.

2:55 From HELM to Applications: ChemAxon's Way into the World of Large Molecule Informatics

Aurora Costache, Ph.D., Application Scientist, ChemAxon

HELM is a success story in pre-competitive collaboration. Uptake is increasing in the industry to improve description of biological entities in informatics systems. ChemAxon contributes since the beginning, defining extensions, providing support for HELM user community. This talk will give an overview about ChemAxon's involvements in the HELM project, and introduce the tools built on these grounds through use cases.

3:10 Drive Innovation, Accelerate Research and Shorten Drug Time-to-Market with Cognitive Search & Analytics

Laurent Fanichet, Vice President, Marketing, Sinequa
Martin Leach, Ph.D., Vice President, R&D IT, Enterprise Data Management & Analytics, Alexion Pharmaceuticals

In the highly competitive world of biopharma, your organization is likely to cope with hundreds of millions of documents, including lab and clinical trial reports, publications, patent filings, and emails, as well as billions of database records from internal and external trade sources. Learn how Cognitive Search & Analytics can help drive innovation, speed up submission of new drugs.

3:25 Refreshment Break in the Exhibit Hall with Poster Viewing

DATA ANALYTICS & DATA INTEGRATION

4:00 Informatics Enabling Chemoproteomics and Knowledge Driven MOA Analytics

Xudong Qiao, Senior Specialist, Chemistry Pharmacology & HTS Informatics IT, Merck Research Labs IT

The insufficient number of novel, well validated disease modifying targets poses a critical risk to drug discovery today. The application of chemical biology techniques, tools, and analyses to the investigation of disease biology can aid in the search for novel therapeutic targets and a much increased understanding of target and pathway biology. Merck has developed information technology solutions to automate chemoproteomics experiment workflows, and enable data processing and analysis, in order to establish a knowledgebase needed for data mining and decision-making.

4:30 Using Salesforce for Outsourcing Scientific Data Curation

Angelika Fuchs, Ph.D., Head, Large Molecule Workflows, Roche pRED Informatics

High quality data is fundamental for all decision-making processes in the pharmaceutical industry. Ensuring data consistency and correctness, however, is often both difficult and time-consuming as it requires in many research areas expert domain knowledge not easily available for data curation efforts. We have developed a novel data curation application based on the popular Salesforce platform to enable the outsourcing of data curation tasks to CROs with the required expert knowledge. The application provides easy access to both internal and external users and is fully integrated with in-house terminology services and down-stream systems to facilitate data availability for review and further processing by in-house scientists. With this application we were able to scale-up data curation efforts on demand while ensuring high data quality for research and lab decision making.

5:00 Transforming Disparate Data into Collective Insights

Frederik van den Broek, Ph.D., Consultant, Research & Development Solutions, Elsevier

Gregory Landrum, Ph.D., Vice President, Life Sciences, KNIME.com AG

Big data in R&D is simply today’s data. Efficiently and reproducibly learning from this data requires us to combine different types of information from various sources and to apply advanced analytics and visualisation to the resulting data set(s) using integrated workflow and analytics platforms. This talk will present use cases showing how one can obtain these insights which are vital for R&D decision-making in today’s competitive drug discovery environment.

5:30 – 6:30 15th Anniversary Celebration in the Exhibit Hall with Poster Viewing and Best of Show Awards

Thursday, May 25

7:00 am Registration Open and Morning Coffee

8:00 PLENARY KEYNOTE SESSION & AWARDS PROGRAM

8:05 Benjamin Franklin Awards and Laureate Presentation

8:35 Best Practices Awards Program

8:50 Plenary Keynote

9:45 Coffee Break in the Exhibit Hall and Poster Competition Winners Announced

FROM TRANSLATIONAL TO REAL WORLD - THE IMPACT ON R&D

10:30 Chairperson’s Remarks
Tom Plasterer, Ph.D., Director, US Cross-Science Lead & Open PHACTS Lead, AstraZeneca 

10:40 Transforming Early Pharmaceutical R&D Strategies with Real World Evidence

Cliona Molony, Ph.D., Senior Director & Head of Computational Biomedicine, Computational Biology & Biomedicine, Pfizer

Pfizer is capitalizing on maturing healthcare informatics, expanding sources of real world evidence, and deeply characterized populations to adopt value-driven and precision medicine R&D strategies. Together these resources (a) fuel a deeper understanding of disease subtypes to dissect novel mechanisms, (b) help to assess the burden of patient co-morbidities and adjacencies for drug development opportunities, and (c) enable precision medicine approaches to test therapeutic hypotheses matched to the pathology of patients. This presentation will discuss our approach and the informatics capabilities that are driving real world data into Pfizer's early drug discovery pipeline research efforts.

11:10 Co-Presentation: rHEALTH (Real World Evidence Health Analytics Hub): Transition Janssen from Opportunistic to Systematic Strategic Use of Real World Evidence

Xiaoying Wu, M.D., MS, Director, RWE IT CoE & Medical Informatics, Data Sciences, Janssen IT, Johnson & Johnson

Asha Mahesh, Senior Manager, Emerging Technologies, Janssen R&D IT, Johnson & Johnson

rHEALTH is a Janssen developed enterprise Real World Data (RWD) and analytics platform to address challenges that the Janssen RWE community is facing. The ecosystem consists of four components: a global RWE knowledge portal, a Smart Catalog, a data platform that ingests data from disparate data sources and transforms the data to a Common Data Model, and a tailored analytical environment. With the new enterprise RWE-generating platform rHEALTH, we reduced the time for data access and analysis from months to days, enabling business partners to deliver valuable research insights faster than previously possible.

11:40 Accelerating Research through Full Text Semantic Enrichment and Data Integration

Mike Iarrobino, Product Management, Copyright Clearance Center
Anna Lyubetskaya, Data Scientist, Copyright Clearance Center

R&D-focused organizations are processing scientific content at scale to extract relationships between biological features. You will gain insights from diverse cases for applying full-text semantic enrichment integrated with other data sets at your organization. In this session, you’ll learn how to: use a network environment where text, raw data, and structured data are easily connected to help you make informed decisions, save time and increase efficiency by uncovering and integrating expert knowledge computationally to address potential challenges that result from an increased volume of information and novel facts present in unstructured text and experimental output.

12:10 pm Session Break

12:20 Luncheon Presentation I: Addressing the Pain Points of Bioinformatics R&D in Post-Genomic Era: Lessons Learnt from the Pharmaceutical Industry

Misha Kapushesky, Ph.D., CEO, Genestack

A key challenge in pharmaceutical R&D is to leverage high-throughput multi-omics data, combined with clinical data to inform the drug discovery process. This requires data federation, data governance, and scalable storage and compute, enabled by a modular environment which would fast-track genomics data analysis. Here, we present case studies illustrating how Genestack has helped its customers achieve these goals.

12:50 Luncheon Presentation II (Sponsorship Opportunity Available)

1:20 Dessert Refreshment Break in the Exhibit Hall with Poster Viewing

FROM TRANSLATIONAL TO REAL WORLD - THE IMPACT ON R&D

1:55 Chairperson’s Remarks

Ralph Haffner, Head Discovery Workflows Basel - pRED Informatics, Roche Pharma Research and Early Development, F. Hoffmann-La Roche Ltd.

2:00 Digital Biomarker Development at Roche pRED - Using mSensors to Gain New Insights into Neurological Disorders

Christian Gossens, Ph.D., Global Head Early Development Workflows, Roche pRED Informatics, F. Hoffmann-La Roche Ltd.

Roche is pioneering a smartphone-based remote monitoring system for patients with e.g. Parkinson's disease. It complements the conventional physician-led assessments in the clinical trial, which are resource-intensive and represent only a snapshot in time. The data collected provide information on patients’ symptom fluctuations and disease impact on daily living. This presentation will discuss what it took to collect such data and convert raw data into clinical insights.

IDENTIFICATION AND PRIORITIZATION OF TARGETS IN DRUG DISCOVERY & DEVELOPMENT

2:20 Pfizer's Causal Reasoning Engine: Generating Specific and Testable Hypotheses from Large-Scale 'Omics Data

Enoch S. Huang, Ph.D., Executive Director, Head of Computational Sciences, Pfizer Worldwide Research and Development

Ease of large-scale generation of different 'omics data types for model systems and patients has driven the need for computational methods that offer ease-of-interpretation as well as robust results. In this talk, I will present Pfizer-developed approaches based on causal networks assembled from prior knowledge for the prediction of upstream regulators, boosting genetic signals, and robust patient stratification.

2:40 Navigating through an Ocean of Targets—How Informatics Can Help to Advance an R&D Pipeline

Jonathan Dewey, M.D., Associate Director of R&D Information Technology, Biogen

Drug discovery organizations advancing a portfolio of targets through an R&D pipeline require evidence beyond genetic associations and genomic correlations to disease states. Biogen scientists accelerate the process via target prioritization using network analysis, 'omics data integration, and computational pathway engines to discover novel hypotheses and mechanisms of action critical to advancing each target.

ENSURING HIGH QUALITY DATA FOR GOOD DECISION-MAKING

3:00 BioPharma Adoption of FAIR Data, a Collaborative Advantage

Tom Plasterer, Ph.D., Director, US Cross-Science Lead & Open PHACTS Lead, AstraZeneca

The concept of FAIR (Findable, Accessible, Interoperable and Reusable) data is becoming a reality as stakeholders from industry, academia, funding agencies and publishers are embracing this approach. For BioPharma being able to effectively share and reuse data is a tremendous competitive advantage, within a company, with peer organizations, key opinion leaders and regulatory agencies. A few key drivers, success stories and prognostications for FAIR data will be presented.

3:30 Enabling Collaborative Analysis and Decision-Making between Business and R&D Groups in the Pharmaceutical Industry

Robert Cain, Ph.D., Informatics Investigator, Allergan plc

In this talk I will discuss tools to bring together pharmacology, genomic and chemistry research data along with competitive intelligence, patent, financial and other data and make it computable. I’ll also describe our open science model and our distributed decision making and tools we use to share insights between groups. Steps to define drug landscapes and collaboratively mine target, indication and drug information will be discussed along with our repurposing tools.

4:00 Conference Adjourns