Agenda

Pre-Conference Day | October 15th

Pre-conference workshops are taking place on October 15th, being delivered by representatives from Pfizer and GSK.

To find out more details on topics, content, benefits of attending and the workshop leaders, click here.

Day 1 | October 16th

8.00     Registration and coffee

9.00     Opening Address from the Chairperson

Thomas Abbott, Head, Real World Evidence, Astellas

9.05     KEYNOTE: Translating Big Data Hype to Deliver Real Patient Hope

  • Human biology can be measured and quantified at unprecedented scale, speed and detail

  • How can this be leveraged to realize a new paradigm – across all sectors – to ensure these breakthroughs result in enhanced human healthcare?  

Nadeem Sarwar, President, Center for Genetics Guided Dementia discovery (G2D2), Eisai

9.30     KEYNOTE: Value of Genomic Data in Discovery

Senior Representative from IBM Watson Health

9.50     KEYNOTE: The Role and Impact of AI in Drug Development

  • Grasp AI & ML’s application in early drug discovery to preclinical work as demonstrated by evidence from use cases

  • See the measurable impact of AI in drug development

Bino John, Associate Director, AstraZeneca

10.10     SPEED NETWORKING

Meet other conference attendees in a fun session designed to break the ice and help you identify who you would most like to speak with later in the meeting. Bring plenty of business cards!

11.10     Morning break and coffee


Attendees Choose One of Two Tracks, Track One - Enabling Science and Track Two - Doing Science


TRACK ONE:
ENABLING SCIENCE

Track Chair: Thomas Abbott, Head, Real World Evidence, Astellas

PLANNING AND EXECUTING YOUR DATA-DRIVEN DRUG DEVELOPMENT STRATEGY  

11.30     CASE STUDY: Shaping Your Business Strategy with Advanced Analytics

  • Learn of the roles that big data and advanced analytics can play in forecasting demand to refocus your product pipeline

  • Delivering results via management of your pipeline along with the risk factors associated with using AI & ML

  • Understand the importance of end-to-end visibility and see how this can drive efficiency and operational excellence

Nuray Yurt, Executive Director, Enterprise Analytics & Data Science, Novartis

12.00     Building and Making the Business Case for Investment and Executive Attention on Better Processes and Infrastructure

  • Learn how to define the commercial costs and returns of data-driven infrastructure and processes

  • Using case-studies to examine when data-driven approaches will best deliver a return on investment

  • Discover a step-by-step process in building and delivering a business case towards data-driven drug development

Thomas Abbott, Head, Real World Evidence, Astellas

12.30     Lunch

1.30     CASE STUDY: Application of Advanced Analytics and Computational Platforms to Optimize Workflow

  • Discover, from case evidence, the effective application of advanced analytics and predictive IT platforms that optimize the drug R&D process

  • Understand the ROI in utilizing data-driven approaches to drug R&D, and grasp the opportunity to create and maximize the value of pre-existing data and materials

  • What are the questions and issues that a predictive IT platform should address? How to ensure IT solutions/ advance analytic approaches will bring value to drug discovery and development by meeting end users’ needs

Brian Kelley, Principal Scientist, Relay Therapeutics

PREPARING FOR PRECISION MEDICINE

2.00     BROAD INSTITUTE CASE STUDY: Keep the Scientific Ecosystem Clean from Digital Pollution

Digital information fuels the Broad and is among our greatest assets. Along with the benefits we gain from data, we have a responsibility to avoid polluting the scientific ecosystem. Integrating data storage management with the analysis pipeline enables us to keep the landscape clean rather than cleaning it up as an afterthought.

Discover a metadata strategy for unstructured data. Hear how custom metadata simplifies managing massive unstructured data repositories at the Broad Institute, enabling biomedical research.  Find data quickly and easily using content-based and policy-driven data classification & tagging.

Linda Moineau, IT Director, The Broad Institute of MIT and Harvard

Frank Lee, Global Healthcare and Life Sciences Industry Leader, IBM Systems

FROM INTEGRATIVE INFORMATICS FOR MULTI-OMICS AND FAIR DATA TO KNOWLEDGE GRAPHS

2.30     FAIR Data, Value to BioPharma and the Killer Use Case

  • Understand the meaning of FAIR beyond its 15 sub-principles, for relevance to our business model

  • Data stewardship, legacy data and data “born FAIR”

  • FAIR datasets as an enabler of rich knowledge graphs and border-less collaboration

Tom Plasterer, Director of Bioinformatics, Data Science & AI, Bio Pharmaceuticals R&D, AstraZeneca

3.00     CASE STUDY: Integrative Informatics, Unlocking the True Potential of Multi-Omics Data to Streamline Your Pipeline

  • Discover a hybrid integrative informatic approach via semantic modelling in combination with traditional bioinformatics analytical pipelines

  • Understand the purpose of integrating genomics, molecular and clinical phenotypic data, and see how you can use this information to answer complex scientific questions

  • Learn how FAIR data principles and hybrid IT approaches can power data integration and provide return on investment

Jonathan Pryke, Senior Business Relationship Manager, AstraZeneca

STREAMLINING CLINICAL TRIALS WORKFLOW USING DATA

3.30     Data Driven Digital Protocol for Clinical Trials

The clinical study protocol is the start of the clinical trial process. Digitizing the protocol and creating metadata will drive efficiencies that will enable the automation of downstream outputs (i.e. eDC/eCRF, CSR, RAP). Using data to drive the design of the protocol will result in a more robust protocol with fewer costly and time-consuming amendments. Find out how.

Elizabeth George, Director, Digital Clincial Trials, GSK

TRACK TWO:
DOING SCIENCE

Track Chair: Tricia Thornton-Wells, Director, Translational Medicine, Alkermes

DATA-POWERED DISCOVERY OF BIOMARKERS, DRUG TARGETS AND MECHANISMS OF ACTION

11.30     CASE STUDY: Target and Biomarkers Discovery via Transcriptome-Wide Studies of Alternative Splicing, Fueled by Advanced RNA-Sequencing Technologies and Computational Tools

  • Discover the possibility of powering alternative splicing using the latest RNA-sequencing technologies and analytical tools, and how this provides leads for drug discovery

  • Learn of the infrastructure and processes needed for efficient drug target and lead discovery via data-driven transcriptome-wide studies; and where the pitfalls are

  • Understand the start of the data life-cycle from RNA sequencing, how are these data stored for reusability and how do they maintain value in the long term?

Shanrong Zhao, Director, Computational Biology and Bioinformatics, Pfizer

12.00     Personalized Medicine from an Analytics Perspective: Using Biomarker Data to Model Disease Complexity

  • A review of the need for reference-based biomarker utility systems and standardized neuroimaging

  • With many current NLP solutions basing their cataloguing on educated guesses instead of real-observed data, what does this mean for the reliability of collected data and the cost-effectiveness of implement NLP?

Tricia Thornton-Wells, Director, Translational Medicine, Alkermes

12.30     Lunch

PREDICTIVE MODELLING FOR TARGET IDENTIFICATION

1.30     CASE STUDY: Machine Learning for Holistic Drug Target Discovery

  • Discover how machine learning can be applied to the entire process of drug target identification

  • Learn about specific machine learning models for link inference on a knowledge graph, and 'omics models for target prediction

  • See how AI tools work hand-in-hand with researchers to make informed decisions about novel targets to test in the lab

Alix Lacoste, VP of Data Science, Benevolent AI

2.00     Computation-Led Drug Re-Purposing and Genetic Data-Driven Approaches to Guide Target Discovery

  • Discover how to initiate, enable, and land computational drug repurposing

  • The target features that translate into clinically successful drugs: an examination with AI and ML-based methods

  • You can do it, but who can help? Choosing the correct internal & external partners

Pankaj Agarwal, Senior Fellow, Computational Biology, GSK (former); Principal Computational Biologist, Biolnfi

USING DATA LAKE COMPRISED OF RWD AND CLINICAL DATA TO DRIVE DRUG DISCOVERY

2.30     CASE STUDY: Integration and Analysis of Clinical Trial and Real-World Data (RWD) for Drug Development: Challenges and Successes

  • What is the purpose of forming a data lake and how does that ultimately translate into progress for patients?

  • How can diverse internal and external data sources be accessed and integrated in a data lake?

  • What are key aspects of a data lake that improve its impact and uses?

  • How can data and metadata be discoverable and interpretable?

Philip C Ross, Director, Head of Translational Bioinformatics Data Science, Bristol-Myers Squibb

G. Celine Han, Research Investigator in Analytics Innovation, Oncology Translational Bioinformatics, Bristol-Myers Squibb

INTERPRETING MULTI-OMICS DATA

3.00     CASE STUDY: Interpreting “Higher-Dimension’’ Integrated Multi-Omics Data to Drive Research Translation

  • Understand what useful multi-omics data look like and how to access it

  • See the analytical tools and platforms involved along with the procedure for effective research translation

  • Where do the success and challenges lie for higher-dimension data?

John Quackenbush, Chair of the Biostatistics Department, Harvard T.H. Chan School of Public Health

3.30     CASE STUDY: Computational Biology Approaches Towards Interrogating the Tumor Microenvironment

  • Quantifying tumour immune and stroma contexture with transcriptome and chromatin landscapes

  • Cell signatures redefined by multi-omics approaches

  • TME Spatial Features

Varenka Rodriguez DiBlasi, Senior Scientist, Boehringer Ingelheim


4.00     Afternoon break and coffee

INNOVATION SHOWCASE

4.30     INNOVATION SHOWCASE: A Solution for the “Big Data” Challenge in Biomarker-Guided Drug Development

  • The integration of biomarkers in drug development has led to an explosion of complex, high throughput and high content multi-omic data - with reports often comprising millions (or tens of millions) of data points

  • Completing thorough analysis of this data to support true multi-omic analysis requires advancements in our approach to (1) the management of these data, and (2) methods with which to analyze these data to extract insights are required

  • Cross-functional expertise is a common challenge but remains a pre-requisite to assemble the right “toolbox” for data integration and analysis. Representative functions include computer science, software engineering, statistics and machine-learning to address the “big data challenge” as well as computational biology and translational sciences to support mechanistically-driven analyses

  • This expertise and these tools can also be tapped to make use of the many publicly available data sets that can be incorporated as early as pre-clinically.

  • We will discuss how leading biotechs assemble these tools to drive insights that aim to solve the myriad of challenges in precision medicine, including predicting patient response to treatment, modelling drug mechanism of action or disease biology, aiding in the systematic and data-driven selection of target pathways for a condition, and identifying patient subtypes

Renee Deehan-Kenney, VP of Computational Biology, QuartzBio

4.40     PANEL SESSION: “How would you build a pharma company from scratch, five years from now? What would be the difference, from talent to drug discovery to commercialization?“ Bertrand Bodson, Chief Digital Officer, Novartis. This panel will seek to provide enlightenment on that important question.

·         What would be the difference, from talent to drug discovery to commercialization?” Bertrand Bodson, Chief Digital Officer, Novartis (former)

·         Do we need a new, overall model for data/information in medicine, if it’s use/housing is not going to be limited to pharma anymore?

Ping Liu, Head of Data Transformation; Industrial Affairs, Sanofi

Ed Addison, CEO, Cloud Pharmaceuticals

Bino John, Associate Director, AstraZeneca

Alix Lacoste, VP of Data Science, Benevolent AI

Nuray Yurt, Executive Director, Enterprise Analytics & Data Science, Novartis

5.25     Chairperson’s Closing Remarks

5.30     Networking Drinks Reception

A chance to relax, unwind and continue chatting to other conference attendees over a glass of wine, beer or soft drink.

6.30     Optional Dinner

A relaxed, informal meal at a local restaurant. Sign-up on the day. The meal is not included in your ticket price.


Day 2 | October 17th

8.00     Registration and coffee

9.00     Opening Address from the Chairperson

Alix Lacoste, VP of Data Science, Benevolent AI

9.05     KEYNOTE: Case Study - Developing and Delivering Semantic Technologies to Allow Both Human and Machine to Understand Data and Produce Value

  • Understand how to create useful and integrated ontologies that support collaboration across heterogeneous systems

  • Discover an emerging knowledge graph infrastructure and the implemented web-based environment for data storage, access, integration, interrogation, analysis and validation

  • Discuss the challenges semantic technologies face in biomedical data and strategies and the possible solutions

  • See some of the values of implementing semantic technologies for drug research and development in a concrete setting

Deborah McGuinness, Tetherless World Constellation Chair, Professor of Computer and Cognitive Science, Chair, Rensselaer Polytechnic Institute; University Researcher, DARPA

9.35     KEYNOTE: Why and How Knowledge Graphs will Transform (and Rescue) Drug Discovery

  • Data-driven processes generally have the goal of finding key information and converting it into knowledge.  With human’s cognitive limitations to manage large data sets, knowledge graphs can provide framework for finding, visualizing, extracting, and predicting relationships

  • This talk will introduce the knowledge graphs and their key underlying technologies

Peter V Henstock, Machine Learning & AI Technical Lead: Combine AI, Software Engineering, Statistics & Visualization, Pfizer

10.05     Morning break and coffee


Attendees Choose One of Two Tracks, Track One - Enabling Science and Track Two - Doing Science


TRACK ONE:
ENABLING SCIENCE

AI & ML’S CURRENT DEVELOPMENTS AND THEIR APPLICATION IN DRUG DEVELOPMENT

10.30     Infrastructure and Investment Implications of Widespread Adoption of AI/ML-Driven Approaches. What’s Required? What’s New?

  • Learn of the key infrastructures in an IT architecture that will better enable AI/ML approaches    

  • Discover the latest innovations and field-leading developments for AI/ML driven R&D

  • See with a commercial context, the operation costs and manual resources requirements of AI/ ML-driven approach, what are the measurable benefits?

Danielle Ciofani, Director of Data Strategy and Alliances, Broad Institute

11.00     CASE STUDY: “Biological Data Representations: Formulating Your Problem to Best Leverage Machine Learning’s Strengths”

  • Get more out of Convolutional Neural Networks to solve genomics problems

  • Graphs as a general-purpose data representation tool for machine learning

Gerald Sun, Senior Data Scientist, AstraZeneca

11.30     CASE STUDY: Real-World Effective Application of Machine Learning Solutions in Clinical Settings to Drive Research Translation

  • Discover the current cutting-edge developments of ML and their impact in healthcare 

  • Understand how to effectively apply and implement this technology to drive research translation

  • What kinds of data are ideal to power these advanced analytical techniques and how to access these data   

Mark Michalski, Executive Director, MGH & BWH Center for Clinical Data Science

12.00     Lunch

DOWNSTREAM PROSPECTS OF DATA-CENTRIC DRUG DEVELOPMENT

1.00     PANEL DISCUSSION: Pharma Ecosystem Alignment in a New Data-Driven World: Speed Versus Regulation, Privacy and Consent

  • With the increasing trend of ‘‘taking drug development out of the lab’’, what does this imply for the quality and safety of drug ADMET data, and how do you validate this data efficiently?

  • How does the growing traction of patient-centricity for data affect consent and access, is this a positive step for both the industry and patients?

Sridevi Ponduru, Associated Medical Director, Takeda

Danielle Ciofani, Director of Data Strategy and Alliances, Broad Institute

Jennifer Hall, Chief, Institute for Precision Cardiovascular Medicine, American Heart Association

NATURAL LANGUAGE PROCESSING IN DRUG R&D

1.30     CASE STUDY: Natural Language Processing, The Latest Advances and Where Do The Challenges Lie

With many current NLP solutions base their cataloguing on educated guesses instead of real-observed data, what does this mean for the reliability of collected data and the cost-effectiveness of implement NLP?

  • Do current NLP solutions meet expectation?

  • Discover the effective applications of NLP from case evidence

  • Where are the challenges and what are the possible solutions

  • How do we proceed with NLP going forward?

Armaghan Naik, AVP R&D Scientific & Digital Innovation, Sanofi

TRACK TWO:
DOING SCIENCE

OPTIMIZING CLINICAL TRIAL PATIENT STRATIFICATION AND DRUG LEADS

10.30     CASE STUDY: Leveraging Integration Multi-Omics Data to Produce Biomarker Strategies to Enhance Drug Discovery and Patient Selection

  • Learn how well-integrated multi-omics data can result in optimized drug candidate and study population cohort selection

  • Understand the process in translating measurable improvement in drug R&D with multi-omics data

  • See where the challenges lie in multi-omics data utilization and devise possible solutions

Mera Tilley, Senior Director, Translational Genetics, Foresite Capital

11.00     CASE STUDY: Discovering and Analysing Internal Data Mines to Optimise The Selection of Drug Target Site and Patient Population

  • Know the hurdles to discovering internal data mines and how to tackle data ownership issues

  • How to analyse these internal data mines, what infrastructures are involved and how to use the findings to optimise drug target site and patient population

  • Grasp the impact from the lack of common terminology for data for drug development, and the solutions

UTILIZING AI IN PREDICTING CLINICAL OUTCOMES

11.30     CASE STUDY: Applying AI/ML and Analytical Approaches to Enhance Clinical Trial Success Rates

  • Presentation of a project where AI/ML have been developed for the prediction of outcomes with live trial patients based on their baseline and trial data

  • Evaluate the meaningful values of applying advanced analytics to clinical trials

  • Where are the successes and pitfalls of AI/ML guided approaches

Yan Ge, Director, Data Analytics, Takeda

12.00     Lunch

1.00     CASE STUDY: Leveraging Pathology Images and Artificial Intelligence to Predict Immuno-Therapy Treatment Outcomes

  • What can we glean from computational analysis of pathology images?

  • Discussion of the challenges associated with quantitative pathology

George Lee, Digital Pathology Informatics Lead, Bristol-Myers Squibb     

PATIENT DATA CENTRICITY AND DRUG DEVELOPMENT

1.30     CASE STUDY: Application of Knowledge Graphs Built From Pharmacy Data to Contrast The Drug Effectiveness of Opioid and Opioid Alternatives in a Healthcare Delivery System

  • Understand the process to building knowledge graphs from pharmacy data with consideration to data discovery and access

  • Discover the ontologies and mapping of data to scientific context for the construction of the knowledge graph’s neural networks

  • See the real-life application of knowledge graphs in evaluating the drug effectiveness between opioid and opioid alternatives in a healthcare delivery system

  • Grasp the possibility of translating this approach to clinical trials

Phil Lanzafame, Director of Knowledge Solutions, Sentara Healthcare

Ashlee Hamel, System Coordinator, Pharmacy Clinical Programs, Sentara Healthcare


2.00     Afternoon break and coffee

2.30     The Role of Consumers in Real World Data and The Future of Health Care

  • See the end-to-end data life cycle of real-world data     

  • With increasing data centricity towards patients, what does this imply for consent, data access and governance?

  • Electronic health records - what are their value and how to best apply them for precision drug development?

Jennifer Hall, Chief, Institute for Precision Cardiovascular Medicine, American Heart Association

3.00     PANEL DISCUSSION: The Now and Future of Drug Discovery and Development

  • Driven by Slido (interactive audience participation), a summary of the day’s discussion and main audience takeaways

  • What the ‘enablers’ and ‘doers’ can learn from each other

  • What needs to happen now? Important focus areas, outstanding questions and priorities

  • Building a report/plan for your team to benefit from this meeting

Justin H. Johnson, Associate Director and Principal Translational Genomic Scientist, AstraZeneca

Deborah McGuinness, Tetherless World Constellation Chair, Professor of Computer and Cognitive Science, Chair, Rensselaer Polytechnic Institute; University Researcher, DARPA

Philip C Ross, Director, Head of Translational Bioinformatics Data Science, Bristol-Myers Squibb

Phil Lanzafame, Director of Knowledge Solutions, Sentara Healthcare

Ashlee Hamel, System Coordinator, Pharmacy Clinical Programs, Sentara Healthcare

4.00     Chairperson’s Closing Remarks and Close of Conference