Day 1 | Enabling Science

8.00     Registration and coffee

9.00     Opening Address from the Chairperson

Xosé Fernández, Chief Data Officer, Institut Curie


9.10     KEYNOTE: Pharma R&D Data Integration – Data Landscaping, FAIR Play, FAIRification, Killer Apps and the ROI Question

Philippe Marc, Director, Global Head of Integrated Data Science, Novartis

 9.50     KEYNOTE: The Big Picture: Why Getting Data Right is so Important for Pharma

  • What are we fixing? What is the current problem? What are the drivers for change?

  • What’s required to fully embrace data-driven decision making and drug development at executive level?

  • Top-level strategies for implementing and improving the efficiency and effectiveness of data-driven approaches.

  • Bottom-up: Considering the needs of end users and developing a clear vision & strategy to manage transition.

  • What the main challenges in the context of data are cultural and ethical, not technical.

Martin Romacker, Principal Scientist, Roche

10.20   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


11.30   CASE STUDY: Transforming Data into Knowledge for R&D and Beyond (for Market Access and Convincing Payors) in the Most Efficient Ways. 

  • Developing a big data platform to ensure that data from more than 350 clinical trials are easily explorable.

  • Executing a strategy to ensure that everyone working on data (integrating, standardizing, analyzing, modeling, simulating) works under the same roof.

  • Considerations for ensuring a common infrastructure, database, platform of software/quality control systems and a synergetic pool of data experts.

  • Data science as an increasingly cross-functional discipline.

  • Breaking silos by centralizing data.

Anne Danniau, Head of Data Sciences, Grunenthal Group

12.00   CASE STUDY: Using Deep Learning to Accelerate Drug Discovery and Reduce Time to Market

  • An outline of Single Cell Cloning in the drug discovery process.

  • Achieving full automation with Single Cell Cloning.

  • The impact of deep learning on improving automation.

  • Examining the impact on drug discovery.

Adam Fathalrahman, Data Scientist, Tessella

12.30   CASE STUDIES: Harnessing the Complexity of Cancer to Drive New Insights and Treatments

  • Why cancer is such a valuable source of example for big data approaches

  • Data cleansing, structuring and analysis at the largest cancer research centre in France.

  • An outline of the Curie Data Resource as the foundation of a knowledge-driven organisation.

  • Case studies in the deployment of real-world data databases in the French centralised social security system.

Xosé Fernández, Chief Data Officer, Institut Curie

13.00   PANEL DISCUSSION: Building and Making the Business Case for Investment and Executive Attention/Focus on Better Data-Processes and Infrastructure.

  • Developing an awareness of compelling factors.

  • Understanding the benefits of investing to make data FAIR.

  • Considerations for making the business case and investment

  • Scale and the importance of adaptive infrastructure.

  • Delivering and demonstrating ROI

Anne Danniau, Head of Data Sciences, Grunenthal Group
Philippe Marc,
Director, Global Head of Integrated Data Science, Novartis
Martin Romacker,
Principal Scientist, Roche
Andrea Splendiani,
Director, Data Strategy, Novartis

13.30   Lunch


14.30   KEYNOTE: Data-Driven Scientific Problem-Solving in Drug R&D: Developing Data Science Capabilities in a Forward-thinking Global Pharmaceutical Company

Philipp Diesinger, Global Chief Data Scientist, Boehringer Ingelheim

15.00   CASE STUDY: Lessons Learned from Implementing Automated Knowledge Management Methods

Knowledge extraction methods are notoriously difficult, but hold great promise if the quality is sufficient. Using various Machine Learning methods over the last 5 years, Knowledge Management at Roche has been able to pass the necessary threshold of around 75% accuracy.

  • Increasing compliance and reducing operational costs with technologies like Natural Language Processing (NLP), Named Entity Recognition (NER) and un-/supervised learning tools, we can increase compliance and reduce operational costs.

  • Why underlying technologies like semantic search, data dictionaries, knowledge trees, taxonomies on a high-performance computer cluster are prerequisites.

  • In this talk I will present our learnings, as well as the limitations and opportunities we see for the future in “Semantic Computing”.

Etzard Stolte, Global Head, Knowledge Management, Pharma Technical Development, Roche

15.30   Afternoon break and coffee


16.00   FAIRplus

  • One of the goals of the FAIRplus project is to develop guidelines and tools for making life science data FAIR and to facilitate the application of “FAIR” principles to data from certain IMI projects and datasets from pharmaceutical companies.

  • Why is making data Findable, Accessible, Interoperable and Reusable important?

  • Moving forward: How can FAIRplus goals be applied in a commercial context?

Dorothy Silver Reilly, Technical Associate Director, NIBR Informatics, Novartis


16.30   INNOVATION SHOWCASE: 4 x 10 minute presentations.

This is an interactive session presenting the most innovative breakthrough technologies affecting data-driven drug development today (not tomorrow). At the end of the session, the audience vote for the technology/presentation that they think will have the greatest impact.

16.35   TALK 1: Interpretable Deep Learning for Discovering Novel Biomarkers, Next Generation Clinical Trials Using Deep Learning and the Power of Federated AI and Decentralised Data

Parker Moss, Chief Business Officer, Owkin

16.45   TALK 2: A Solution for the “Big Data” Challenge in Biomarker-Guided Drug Development

Matthew Hall, Senior Director, Data Integration & AI strategy, QuartzBio

16.55   TALK 3: The DNAnexus Apollo Platform for Translational Research

Aniket Deshpande, Senior Solutions Scientist, DNAnexus

17.05   TALK 4: AI-powered Drug Discovery: How AI Reasoning is Transforming Drug-disease Data into Novel Treatments for Rare Diseases

Ian Roberts, Chief Technology Officer, Healx


17.15   PANEL DISCUSSION: “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.

Paul Agapow, Director, Health Informatics, AstraZeneca
Philipp Diesinger,
Global Chief Data Scientist, Boehringer Ingelheim
Martin Akerman,
Co-Founder & Chief Technology Officer, Envisagenics

17.45   Chairperson’s Closing Remarks

Xosé Fernández, Chief Data Officer, Institut Curie

19.15   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 | Doing Science

8.00     Registration and coffee

9.00     Opening Address from the Chairperson

Emma Laing, Lead Bioinformatician in Neuroscience and Principal Research Scientist, Eli Lilly


9.05     KEYNOTE: The (R)evolution of the Health Data Ecosystem and the Role of the Patient

  • How can we leverage data from the many siloes in the current health data ecosystem

  • How can we accelerate data interoperability and the broader use of data?

  • How do we get prepared for a world where patients are in control of their data?

Peter Speyer, Global Head of Digital, Medical and Real-World Data Solutions, Novartis

9.35     CASE STUDIES: Filling the Gaps in Translational Research

  • Development of new therapies and interventions is today a matter of translational research, converting the results of basic research into actionable healthcare

  • But too often translational research focuses on the wrong problems: those that are interesting or easy rather than important (e.g. drug discovery, a multitude of integration methods)

  • Here I detail what problems and approaches translational research should be focusing upon (drug repurposing, method benchmarking, human models, interpretation of RWD, etc.), illustrated with good and bad examples.

Paul Agapow, Director, Health Informatics, AstraZeneca


10.05   CASE STUDIES: Genetics and -omics Data Driven Target Discovery/Validation

  • Landscape of available genetics and -omics data

  • What does reusable mean in target discovery/validation?

  • Current and future approaches in data driven target discovery/validation

Emma Laing, Lead Bioinformatician in Neuroscience and Principal Research Scientist, Eli Lilly

10.35   Morning break and coffee

11.05   CASE STUDY: Artificial Intelligence-enabled Target Identification

  • The journey of data to medicines at BenevolentAI

  • An outline of AI/ML-driven target ID case studies

  • Lessons learned from applying AI/ML approaches to target ID/validation

  • Next steps – what does the immediate future look like for AI/ML-led target discovery?

James Dunbar, Senior Bioinformatics Data Scientist, BenevolentAI

11.35   CASE STUDY: C4X Discovery’s Novel Target Identification Platform Taxonomy3® and its Utility in Neurodegenerative and Autoimmune Disorders

  • Unlocking ‘missing heritability’ in analysis of publicly available GWAS datasets using novel mathematics

  • Appreciation of what analysis of genetic data from GWAS does and doesn’t tell you

  • Phenotypic approaches to accelerate path from novel gene-disease association to initiation of novel small molecule drug discovery programme

Craig Fox, Chief Scientific Officer, C4X Discovery

12.05   CASE STUDY: Drug Target Discovery with Splicing AI

  • Splicing errors are the cause of at least 370 human diseases and can be modulated with small molecules or antisense drugs

  • Envisagenics’ platform, SpliceCore, uses AI to discover druggable splicing errors

  • How SpliceCore has successfully identified and validated novel targets for triple-negative breast cancer

Martin Akerman, Co-Founder & Chief Technology Officer, Envisagenics

12.35   Lunch


13.25   Opening Comments from the Chairperson

Pedro Ballester, Group Leader, Machine Learning for Precision Oncology and Drug Design, INSERM

13.30   CASE STUDY: From (Big) Data to Value in Drug Discovery: Surfing on the Data Lake

  • Discovery data has been historically siloed and data preparation and analysis has been piecemeal.

  • Data flows, data FAIRness and integration along with the right tools and training and enables powerful data mining, ML and AI along with efficiency improvements

  • GSK’s journey in Big Data integration and the learnings so far

George Papadatos, Director of Discovery Data Strategy, R&D, GSK

14.00   CASE STUDY: Accelerating the Drug Discovery Process Using Advance Analytics. How AI and Advance Analytics Contribute to the Discovery of New Lead Compound by Enabling:

  • The progression of compounds into hits / leads in complex and biologically relevant screening assay  

  • The selection of most relevant chemical matter to a given assay

  • The acceleration of the drug discovery process

Pierre Farmer, Head of Data Science Technology, Chemical Biology & Therapeutics (CBT) Department, Novartis


14.30   Rethinking Drug Design - The Impact of Artificial Intelligence

  • Latest applications of AI methods to de novo molecule design

  • From natural products to small synthetic compounds with AI

  • Opportunities and challenges for collaborative intelligence in drug design

Gisbert Schneider, Professor of Computer-Assisted Drug Design, ETH Zurich

15.00   Afternoon break and coffee


15.30   CASE STUDY: Exploiting Artificial Neural Networks (ANNs) to Gain Clinically Actionable Insights into Mechanisms of Drug Combination Action

  • An overview on the use of ANNs

  • Application of ANN’s across late and early stage clinical programs

  • Some insights gained from these approaches, and general points

Jonathan Wagg, Head of Oncology Disease Modelling, Roche

16.00   CASE STUDY: Predicting Patient Response - Machine Learning for Precision Oncology

Cancer patients often respond differently to the same drug treatment. Precision oncology aims at predicting which treatments will be effective on a given patient. Integrated treatment response and tumour molecular data from patients can be exploited by Machine Learning (ML) techniques to build multi-variate models able to predict treatment response.

  • That ML models generally have high recall and therefore identify a high proportion of responsive tumours that otherwise would be missed by mutation-based single-gene markers.

  • How treatments are better predicted if a range of tumour profiles and ML algorithms is considered.

Pedro Ballester, Group Leader, Machine Learning for Precision Oncology and Drug Design, INSERM


16.30   PANEL DISCUSSION: How Did We Get Here, Where Do We Go Now?

  • Why is there such a different in approach to application of data-driven approaches within pharma R&D?

  • What’s going to be the next big success that forces the rest to follow?

  • How do you scale up efficiently and begin to seriously look at integrating multi-omic and real-world data?

Emma Laing, Lead Bioinformatician in Neuroscience and Principal Research Scientist, Eli Lilly
George Papadatos,
Director of Discovery Data Strategy, R&D, GSK
Olivier Leconte,
Global Head of Statistical Programming & Analysis, Janssen
Peter Speyer,
Global Head of Digital, Medical and Real-World Data Solutions, Novartis

17.15   Chairperson’s Closing Remarks and Close of Conference