Day 1 November 3

BioData EU 2017 Day 2

Jo Churchill

Chairman’s remarks and recap of Day 1

KEYNOTE: Implementing Big Data Across Healthcare Systems

Keith McNeil

Keynote Interview – Healthcare & Data: Implementing the NHS patient “data hubs”

Panel discussion

Panel: Data Security & Protection: Where is the patient in all of this?

  • How do you engage people? What innovative approaches can be used to engage the public? Social media? Lessons learnt from social services and education outreach programmes.
  • How do diverse communities feel about sharing their data?
  • What is realistic in terms of patients’ knowledge of how their medical data is being used in research?
  • Discussions around ‘consent’ or ‘opt-out’

10:20 Networking refreshment break

Data Storage & Management

BioData of the Future

Transforming Big Data into Smart Data

Population & Public Health

Data Security & Protection

Innovations in BioData


BioData and Epidemiology


Chair's remarks

Karen Temple, Professor of Medical Genetics within Medicine, NHS England

Governance requirements for electronic health records and reuse for research

  • Ethical, privacy protection and governance requirements for electronic health record architectures and systems
  • What challenges to this privacy protection does research use pose?
  • How can clinical research make use of interoperable electronic health records in a trustworthy way?

Setting the computational standard for scalable genomics and personalised medicine analysis

  • Gain insight into the work being done to create a standard computational method for HPC at a time when genomics data is growing
  • What hurdles were met during development?
  • What opportunities does this standard present to the biodata sector?

Case Study: Translational bioinformatics in oncology

  • What translational bioinformatics is in an academic and multidisciplinary environment within the field of oncology
  • What are some of the strategies, issues and bottlenecks encountered during recent studies?
  • Review a platform developed for NGS automated data management
Emanuele De Rinaldis, Honorary Senior Lecturer & Head of Translational Bioinformatics, NIHR Biomedical Research Centre, Kings College of London

Understanding disease outcomes with biodata

  • Gain an understanding of how biodata is assisting epidemiology studies within drug development and equally drug failures
  • What are some of the challenges around availability of data when looking at real world evidence and disease outcomes?
  • How have population centric phenotypic data helped within this approach?

Data privacy requirements in pharma

  • Review challenges faced by pharma companies in data privacy
  • How do you continue to push scientific development and innovation whilst maintaining adequate data protection measures?
  • How does data privacy sit with the pharma business strategy as a whole?

How artificial intelligence is innovating drug discovery and development

  • Gain an understanding of how medical research is seeing rapid transformation driven by an explosion in data and advances in AI
  • How is BenevolentAI’s approach, of identifying and developing novel products and novel uses of existing products, taking advantage of existing data sets, and the need to access and re-evaluate pharmaceutical databases?
  • What are the main benefits of this AI-based approach to a drug discovery pipeline: time, attrition, financial, and for patients?

Biodata and research into brain tumours

  • Is big data an opportunity or challenge for research into brain tumours?
  • How can those affected by brain tumours lead us on use of their data?
  • How can biobanking help advance developments within this space?

Link between population-level epidemiology and genetic data

  • What can you learn from linking population-level EHRs and genetic data?
  • How can you use other technologies to better understand a disease, such as wearables and other data systems, to track and manage people over time?
  • How do you overcome the challenge of finding the longitudinal phenotypic data required for these studies?

Prediction of novel therapeutic targets using an innovative data approach

  • Gain a better understanding of the challenges around target identification and validation
  • Review a semi-supervised classification approach to explore whether gene – disease association data is sufficient to predict therapeutic targets 
  • Investigate how a neural network is able to predict therapeutic targets with over 70% accuracy demonstrating that disease association is predictive of the ability of a gene or a protein to work as a drug target

Integrating knowledge biocuration with computational biology in cancer

  • Hear an overview of the biocuration-based activities being undertaken by the SIB Swiss Institute of Bioinformatics in the field of cancer
  • Best practices for transforming big data into smart data within this research and development field
  • Gain insights into biota analytics for drug repurposing in immunotherapy

Microbial bioinformatics and epidemiology

  • Gain an understanding of advancements in software development and data analysis within the field of microbial bioinformatics
  • How is biodata specifically working towards combatting anti-microbial resistance?
  • What new methods and technologies are being developed within the microbial bioinformatics space?

Industrialized infrastructure for patient insight – technical advances and organizational barriers

  • The promise of expansive clinical-omics patient data to drive medical research has been hampered by lack of scalable technology platforms
  • Via case studies, and across capabilities from privacy preservation to machine learning, we examine the state of the art in BigData platforms
  • Beyond technology constraints, the session discusses other barriers and stakeholders attitudes, that help or hinder progress   

12:25 Networking lunch break


Data Storage & Management

BioData of the Future

Transforming Big Data into Smart Data

Population & Public Health

Successful Strategies for R&D Data Management

Applications of AI & Machine Learning with BioData

BioData for Health Systems

BioData for Population and Public Health Applications


Chair's remarks

Karen Temple, Professor of Medical Genetics within Medicine, NHS England

Integration of RWE data in the evaluation of clinical probability of success via clinical trial simulation

  • Best practices in modelling to incorporate different data sets
  • Hear a case study of this application within diabetes
  • Examine how to create an Integrated Data

AI methodologies and optimisation within childhood cancer

  • Insights into big data analytics on the causation of a rare childhood cancer
  • How is this enabling drug discovery for this particular patient cohort?
  • Investigate methods used to identify drug responses from each patient within that same cohort

Lessons learnt from changing clinical pathways to embed genomic testing

  • How do we work with hospitals to embed genomic testing in clinical pathways where appropriate?
  • What tools are needed by healthcare to adopt?
  • What is the clinical impact of this change, including impact on cost and value?

The role of bioinformatics in fighting infectious diseases

  • Hear how bioinformatics tools are being used for pathogen identification and typing, as well as pathogenicity and virulence within infectious diseases
  • How is this research helping to identify and combat antimicrobial resistance?
  • Gain an understanding of applications for bioinformatics within infectious diseases: drug resistance testing, pathogen-host interaction, infection and treatment outcomes

“How to eat the elephant”: A review of information architecture

  • How do you make information architecture a priority in corporate environments and deliver immediate impact?
  • Insights into a structured approach to overcome the core challenges of large enterprises to build key data assets
  • Best practices in applying this to a pharmaceutical R&D business

Artificial intelligence & machine learning applications in clinical development: Present & future

  • Gain insights into machine learning as applied to the intelligent mining of clinical trials data and examine predictive analytics to refine the operational execution of drug development
  • What are some of the challenges & opportunities presented by the burgeoning role of technology in clinical research?
  • Consider the future: How AI might be used in years to come?

Case Study: Connected Health Cities and the ‘Learning Health System’

  • Explore how this project unites health data and technology to improve health services in Northern England
  • Review how applications of advanced data analytics have provided more efficient processes and improved public health to patients
  • What are some of the lessons learnt that can be applied elsewhere in the UK and the rest of the world?

"Predictive Prevention"

  • Learn about how the Data for Good Foundation is collecting patient data for research on top of personal data storage
  • What is the dynamic around data ownership and governance?
  • How are the foundation interacting with both health and behaviour data?

Do you have what it takes to build a biodata ecosystem for your enterprise?

  • User cases in pharma and consumer good companies that show case collaborative ecosystems
  • Building a biological data, tools and knowledge informatics ecosystem for innovation and collaboration
  • How to manage metadata and data provenance 

Machine learning for medical image analysis

  • Hear how machine learning techniques are being applied to the automatic interpretation of medical imaging
  • What are the benefits of using these techniques within the radiology setting?
  • Where else could these algorithms be applied?

Using AI to diagnose rare diseases

  • Hear an overview of how AI is helping review patient records and medical literature to generate a series of ranked diagnoses
  • What have been some of the lessons learnt and challenges overcome?
  • Does working with rare diseases alter data protocols and practices at all?

Using biodata to understand the causes of disease as a basis of disease prevention

  • Explore how population-based studies are enabling strategies for prevention
  • Investigate methodologies that can be applied to biobanks and population-based cohorts when studying disease prevention
  • Best practices in overcoming challenges with global coverage and international collaborations
Akram Ghantous, Scientist, International Agency For Research On Cancer

How to manage data in a more structured way

  • Update into Roche’s data management and workflow management strategy
  • What have been some of the challenges rolling it out?
  • How has been accepted by the scientists using the platform?

Novel feature selection strategies for enhanced predictive modelling and deep learning in the biosciences

  • Gain an understanding of how WuXi NextCODE’s robust AI method is helping advance personalised medicine
  • How do their various advanced deepCODE AI tools expand the understanding of the underlying molecular determinants of human cancer?
  • What are these support systems and research tools enabling for the research communities working in this space?

CLOSING KEYNOTE: Horizon Scoping in BioData

Panel discussion

Panel: The Future of Big Data within Life Sciences

  • Where are we going with biodata? What is the sense of direction?
  • What will be the dynamic between biodata and clinical data?
  • What role will we see alternative sources of data (such as behavioural or environmental data) and new technologies (such as nanotechnology and wearable) play in their interaction with biodata?
  • What is the role of AI and machine learning in all of this?
  • Forward looking perspectives on population-based health studies within biodata. What will the interface be between real world data/ real world evidence and genomics? Will this help to better inform precision medicine moving forward?

15:50 End of Day 2 – See you next year!

last published: 19/Oct/17 15:05 GMT