Track 10: Pharmaceutical R&D Informatics

There is no end in sight for the amount of data we can generate in pharmaceutical R&D – the amount of clinical, translational, genomic, and electronic health data we generate and collect necessitates effective strategies and infrastructure for managing, integrating, and analyzing these data for better decision making. As new tools and technologies emerge – from digital biomarkers to artificial intelligence – we must ensure that our data is not only of high quality, but also correct and consistent. The Pharmaceutical R&D Informatics track explores real-world projects and strategies for integrating and analyzing complex data sets that are driving R&D and precision medicine.

Final Agenda

Tuesday, April 16

7:00 am Workshop Registration Open and Morning Coffee


8:0011:30 Recommended Morning Pre-Conference Workshops*

W4. AI for Pharma

12:304:00 pm Recommended Afternoon Pre-Conference Workshops*

W10. Digital Biomarkers in Pharma R&D: Technical Challenges and Strategies for Advancing Personalized Medicine

* Separate registration required.

2:006:30 Main Conference Registration Open

4:00 PLENARY KEYNOTE SESSION
Amphitheater

5:007:00 Welcome Reception in the Exhibit Hall with Poster Viewing


Wednesday, April 17

7:30 am Registration Open and Morning Coffee

8:00 PLENARY KEYNOTE SESSION
Amphitheater

9:45 Coffee Break in the Exhibit Hall with Poster Viewing


DIGITAL TRANSFORMATION OF PHARMA R&D
Cityview 1

10:50 Chairperson’s Remarks

Christopher Waller, PhD, Life Sciences, EPAM Systems, Inc.

11:00 The Foundation for the Digital Transformation of the Laboratory

Dana E. Vanderwall, PhD, Director, Biology & Preclinical IT, Discovery IT, Bristol-Myers Squibb Company

An intelligent laboratory – where data, methods, and disparate hardware and software components are completely inter-operable – can ensure data and its context and relationships are seamlessly captured, shared, integrated and ready for analytics to deliver knowledge and insights. This digital transformation requires basic foundational changes in mindset, informatics and data architectures. Doing so also enables more hardware and workflow automation, and drastically improves the integrity and quality of data feeding decisions.

11:30 Intelligent Lab Data Streaming

Ralph Haffner, Global Area Head, Research Informatics, Roche

Is there a way to ‘real time’ stream the relevant data from lab instruments into drug project decision platforms? It usually starts with a vision and first steps. That’s where we in Roche Discovery Informatics are. Good concepts and promising approaches, a couple of PoCs. Some evolutionary some more revolutionary. I would like to expose our model, show first implementations and invite you to join in an open discussion to further explore this exciting and promising space.

12:00 pm A Cloud Based Approach for Automated SAR/SPR Analysis of Focused Compound Libraries

Csaba Peltz, Product Owner of ChemAxon, Cloud Solutions, ChemAxon

This presentation demonstrates a process and the corresponding cloud based tools that make the work of data aggregation and analysis easy and seamless for all parties that collaborate in the hit-to-lead optimization efforts. Data coming from different sources can be made available for joint queries, while executing automated statistical methods on the results.

12:15 Natural Language Processing: Enabling Data-Driven Rather than Document-Driven Decision Making

Jane Reed, Head, Life Science Strategy,Linguamatics, an IQVIA company

Organizations are embracing the digital revolution, including developing strategies to access information buried in text. Top pharma are using Linguamatics NLP to transform unstructured text into actionable structured data for decision support from bench to bedside. In this talk we will present use cases including access to safety data from silo'ed study reports and integrated workflows for real world insights.

12:30 Session Break

12:40 Luncheon Presentation I: Becoming Information-Driven

Sean Liu, Global Head, Translational Science Systems, Takeda Pharmaceuticals

In the past, Takeda scientists faced challenges when attempting to access the right information quickly and across different discovery, medical and clinical groups. The vast amounts of accumulated scientific content – such as electronic lab notebooks, statistical analysis plans, protocols, clinical reports, and others - is siloed in countless repositories, making it difficult to access relevant information in a timely manner and collaborate effectively. Learn how Takeda tackled these challenges with Sinequa’s AI-Powered Search & Analytics platform to break information silos, shorten the path to knowledge-mining, accelerate innovation, and become information-driven.

BSI-Business-Systems 1:10 Luncheon Co-Presentation II: BSI Studio – The Platform for Digital Love Stories In R&D

Maria Andreasen, Pharma Business and IT Consultant, HERAX

Jan Nielsen, Senior Project Manager & Community Manager, CTMS, BSI Business Systems Integration AG

BSI Studio is a multi-functional "director‘s tool" for digitized person interactions, a life science journey management platform, a content management tool, and an analytics tool – all in one. With BSI Studio, you as a corporate leader can make sure that your life science processes are consistently aligned between your  patients, study centers, suppliers and the clinical operation teams, while you are simultaneously driving the digital transformation of all life science relationships and business processes. 

1:40 Session Break

 

DIGITAL TRANSFORMATION OF PHARMA R&D (CONT.)
Cityview 1

1:50 Chairperson’s Remarks

Ralph Haffner, Global Area Head, Research Informatics, Roche

1:55 Accelerating Digital Transformation In R&D

Anastasia Christianson, Vice President, R&D Operations and Oncology IT, Janssen

Digital transformation is well underway in every facet of our lives, from home to work, from communication to transportation, from banking to healthcare and beyond, proceeding at a different pace in each area. Pharma R&D is no exception with digital technology changing drug discovery, development, manufacturing and commercialization. This talk will provide examples of how digital technology is transforming Pharmaceutical R&D.” 

INTEGRATING AND ANALYZING DIFFERENT DATA TYPES IN A COMPLEX DATA LANDSCAPE
Cityview 1

2:25 Building Structured Data at the Onset of Collection in Real World Evidence Generation – Lessons Learned from Biogen’s Learning Health System for MS

Eunice Jung, Associate Director, Real World Evidence Strategy and Analytics, Medical Evidence, Research & Innovation, Biogen

Biogen’s evidence-based LHS built for MS PATHS uses clinical terminology dictionaries to curate data which are used for real world evidence analytics. This case study will look at lessons learned from integrating disparate data types, importance of enhancing usability by cleaning and standardizing data, leveraging technology-enable approaches to curate diverse dataset and maximize completeness, and ensuring consistency in data values and data quality.

2:55 Building a Strong Data Foundation: from Instrument Integration to Machine Learning

Reed Molbak, Product Manager, Benchling

High-quality data is a prerequisite for machine learning and advanced analytics. A first step is to ensure data is centralized and standardized. Learn how leading biopharma companies are using modern informatics to organize and structure R&D data - all the way from results-producing instruments to advanced analysis.

Schrodinger 3:10  Collaborative Drug Discovery with LiveDesign: Integrated Computational Chemistry and Cheminformatics

Paul Sanschagrin, Strategic Deployment Manager, Enterprise Informatics, Schrödinger

Collaboration across computational and medicinal chemistry project teams for idea generation and evaluation, data querying, and project management has become vital to the success of modern drug discovery projects. Here we will present LiveDesign, a collaborative, web-based, modeling platform that brings together computational tools, experimental data, workflow management, and informatics to accelerate the design of new compounds.

3:25 Refreshment Break in the Exhibit Hall with Poster Viewing, Meet the Experts: Bio-IT World Editorial Team, and Book Signing with Joseph Kvedar, MD, Author, The Internet of Healthy Things℠ (Book will be available for purchase onsite)

INTEGRATING AND ANALYZING DIFFERENT DATA TYPES IN A COMPLEX DATA LANDSCAPE (CONT.)
Cityview 1

4:00 Biomarker Data Management Framework – Accomplishments and Challenges

Christina Lu, Director and Head of Data Management and Engineering, Development Sciences Informatics, Genentech (A member of the Roche Group)

Everyone wants to generate insights from their data. Where do you even start when data is not centrally available and is constantly evolving? Data needs to have the proper linkage information and metadata and be stored in a flexible way so it can be used for downstream analysis. This talk focuses on the work done to date with establishing a framework for exploratory biomarker data so it can be consumed for analysis.

4:30 Building/Testing Drug-Sensitivity Predictive Models to Support Translational Research

Bin Li, PhD, Director, Translational Bioinformatics, Computational Biology, Takeda

We developed and tested various machine learning methods to build drug-sensitivity predictive models utilizing genetic and genomic data, to support patient stratification, disease indication selection, mechanism of action study, as well as reverse translation efforts.

5:00 Leveraging an Informatics Platform to Derive Scientific Insights

Marc Siladi, Product Manager, Data Analytics, Thermo Fisher Scientific

The discovery of a life transforming therapy requires the generation of large sums of data. Making sense of this data and determining what is vital to support a novel discovery is time consuming and requires collaboration. Thermo Scientific™ Platform for Science™ software utilizes powerful data visualization tools and provides collaboration and integration capabilities to drive scientific research.

PerkinElmer 5:15 Co-Presentation: Collaborating to Create a Better Screening Data Process

Daniel Weaver, PhD, Senior Product Manager and Solutions Architect, PerkinElmer, Inc.

Dana Kawahara, PhD, Research Scientist, AMRI (Albany Molecular Research Inc.

Despite years of effort in the pharmaceutical R&D informatics space, many organizations still process their screening data through Excel spreadsheets or home-grown data systems. These organizations likely own TIBCO® Spotfire® which has robust data analysis functionality, but, for various reasons, they do not use it for screening data.

5:30 Best of Show Awards Reception in the Exhibit Hall with Poster Viewing

Thursday, April 18

7:30 am Registration Open and Morning Coffee

8:00 PLENARY KEYNOTE SESSION & AWARDS PROGRAM
Amphitheater

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

DEVELOPING AND INTEGRATING DIGITAL BIOMARKERS
Cityview 1

10:30 Chairperson’s Remarks

Tomasz Adamusiak, MD, PhD, Director of Medical Informatics, Digital Medicine & Translational Imaging, Pfizer

10:40 Integrating Digital Biomarkers and Electronic Clinical Outcome Assessments (eCOA) in Clinical Trials

Tomasz Adamusiak, MD, PhD, Director of Medical Informatics, Digital Medicine & Translational Imaging, Pfizer

The mission of the Digital Medicine group and the Pfizer Innovation Research (PfIRe) Lab is to solve key business problems using dynamical measures and advanced-STEM platforms. Our goal is to utilize digital remote monitoring of patients’ symptoms to develop and validate novel clinical endpoints for disease diagnosis and health state assessment. This talk will highlight the unique challenges digital endpoints have in terms of data consistency, quality, and fit for purpose, as well as explore ways to overcome those challenges.

11:10 Digital Disease Markers from Speech and Accelerometer Data

Vladimir Morozov, PhD, Bioinformatics Solutions Architect, Shire

Proliferation of wearable devices combined with advancements in machine learning enable development of digital disease markers. We present cases of developing biomarkers for ALS and Parkinson’s from speech and accelerometer data. We show that deep neural networks (“deep learning”) make it possible to construct markers from raw data without labor intensive signal analysis. The obtained biomarkers are competitive with hand-crafted ones.

Accenture_black 11:40 Co-Presentation: Drug Discovery Innovation in a PreCompetitive Cloud Platform

Joe Donahue, Managing Director, Accenture

Carol Rohl, Executive Director, Research IT, Research Labs, Merck

Today, the informatics systems used by scientists come from many vendors, were developed over time with various UI standards, and it is often challenging to easily access and integrate the heterogenous siloed data generated in the research process in a meaningful way that facilitates innovation and collaborations.   Accenture and Merck will discuss the capabilities and benefits – to both drug discovery organizations and software providers - of a new research platform that allows the research science world to leverage highly elastic, commodity infrastructure while accelerating and enabling competitive differentiation for all parties.

12:10 pm Session Break

12:20 Luncheon Presentation I: A Discovery and Integration Layer for Digital Health

Brendon Kellner, Senior Consultant, Field Operations, Cambridge Semantics, Inc.
Barabara Petrocelli, Vice President of Strategy, Cambridge Semantics, Inc.

Life Sciences companies recognize data as the competitive battleground. Anzo is a Discovery and Integration layer to integrate and blend digital health assets from across the business, offering an edge over traditional competitors and disruptors. This layer sits above the company’s enterprise data assets and provides data consumers with a data fabric, a connected business view of enterprise data.

12:50 Luncheon Presentation II: Supporting Scientific Experimentation from Design to Decide Using a Modern Informatics Approach

Andrew Anderson, Vice President, Innovation & Informatics Strategy, ACD/Labss

Many organizations are transitioning from human-initiated experiments, summarized in documents, to automation-initiated experiments, summarized in comprehensive digital formats. Such comprehensive digital characterization requires a variety of application, architecture, and data standards. This presentation will cover comprehensive digital representations of scientific experiments: from initial experimental design, planning, execution, and observation to final analysis – with an emphasis on high-throughput, parallel experimentation.

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

PROPELLING THE PIPELINE: AI IN DRUG DISCOVERY AND DEVELOPMENT
Harborview 2

1:55 Chairperson’s Remarks

Bino John, PhD, Associate Director, AstraZeneca

2:00 FEATURED PRESENTATION: Application of Machine Learning and Artificial Intelligence as a Driver of Productivity in Drug Discovery & Development

Morten Sogaard, Vice President, Target Sciences & Technologies, External Sciences & Innovation, Worldwide R&D, Pfizer

This talk will provide an overview of the impact of AI on productivity on pharma with the focus on three areas – process engineering & automation, drug design and manufacturing, and target and biomarker discovery and validation, illustrated by specific examples.

2:30 Intersection of AI Techniques and Rare Disease Diagnosis

Margaret Bray, PhD, Senior Data Scientist, Alexion

A look into the latest AI techniques applied to the field of rare disease diagnostics as well as a look at the limitation of current methodologies and areas for future growth.

3:00 Automated Compliance and Quality Checks

Etzard Stolte, PhD, Global Head Knowledge Management PTD, F. Hoffmann-La Roche

Machine learning technologies, like Natural Language Processing (NLP), have reached the maturity for automated quality controls of operational information, e.g. as compliance and quality supervision tools. Over the last years Pharma Technical Development at Roche has created a single front end for many business and validated systems, that uses a mixture of curation and supervised learning tools to increase compliance and reduce operational costs. This talk will present our learnings, as well as the limitations and opportunities we see for the future.

3:30 AI for Improving Drug Safety to Accelerate Drug Development

Bino John, PhD, Associate Director, AstraZeneca

Drug candidates that result from millions of dollars in investment frequently fail during clinical or preclinical testing phases due to safety concerns. Such safety related failures continue to pose a challenge to the industry. This talk will highlight some of the efforts at AstraZeneca that seek to use AI/ML approaches to minimize such clinical/preclinical failures.

4:00 Conference Adjourns

Platinum Sponsors:

accenture

Dell EMC

Elsevier small logo

IBM_Blue

IDBS

Lucidworks

Microsoft

netapp