Day 1 November 2

BioData EU 2017 Day 1

KEYNOTE: Implementing Big Data Across Life Sciences R&D and Drug Discovery

One-on-one interviews with some of biodata’s principal thought-leaders, discussing what they are doing to enable the implementation of big data across in their R&D pipelines and within healthcare practices
Ruth March
09:00

Update on AstraZeneca’s Integrated Genomics Initiative

Mauricio Carneiro
09:20

Experimental and computational platforms at Verily Life Sciences

09:40

Question and answer session

10:00

Speed Networking

10:20 Networking refreshment break

Pedro Ballester
11:00

Building more predictive and interpretable in silico models of in vivo drug response via model complexity control

  • Hear an overview of how the high dimensionality of pharmacogenomics data hampers the discovery of complex molecular markers
  • Gain an understanding of ways to improve the performance of machine learning algorithms on high-dimensional data in the context of precision oncology
  • Examine how to assess which molecular profiles are most predictive of PDX response depending on treatment and cancer type
Andy Grant

13:00 Networking lunch break

Data Storage & Management

Data Computing & Processing

Transforming Big Data into Smart Data

Data Sources

Data Integration & Interoperability

Up in the Cloud

Rare Diseases

Innovations in Data Sources and Acquisition Technologies

14:20

Integrating proteomics in precision medicine

  • Gain an understanding of the role proteomics is playing in precision medicine, and their benefits beyond genomics
  • Best practices in integrating multi-omics data
  • Explore the latest developments within mass spectrometry methods
14:20

Case Study: Federated In-Memory Database System (FIMDB)

  • Overview of this platform that boasts the benefits of a public cloud but with private processing capabilities
  • Explore the technical foundations of this platform that combines integrated data processing and real-time data analysis
  • In what way was there unmet need for such a managed service within academia internationally?
14:20

Collecting and storing standardised clinical data within rare diseases

  • How has working within rare diseases forced a more progressive approach to biodata?
  • What role has automation played throughout the rare disease analysis pipeline?
  • What are some of the challenges integrating genomic and clinical data from a standardisation perspective?
14:20

Standardising data capture

  • How does the biodata community need to come together to standardise the language used in data capture?
  • How does this differ between genomic and clinical data?
  • What role does incentivising data generators play in the standardisation of the data captured?
14:40

Infrastructure development for Europe’s human genomics data

  • Gain an understanding of human data discovery through ELIXIR Beacon project
  • Challenges in managing human genomics data in rare diseases and common complex diseases - working across different countries and multiple institutions
  • How can this infrastructure enable new insights leading to improved healthcare outcomes?
14:40

Lessons learnt from implementing a cloud initiative in pharma

  • What have been some of the major bottlenecks encountered when moving into the cloud?
  • Best practices in engaging the research side with the IT side of a pharma business to ensure a successful transition into the cloud
  • How do you best consider the business strategy in line with the IT agenda in order to enable and elevate the pharma business to its greatest potential?
14:40

The role of data in drug repurposing for rare diseases

  • Delve into the role data has played in the ability to repurpose existing drugs for treating rare diseases
  • How does machine learning along with biodata analysis enable these drugs to be matched with diseases?
  • What’s next for this approach?
14:40

Data capture methods for long-term robustness and authentication

  • A model to enable anonymous aggregated analysis of federated data
  • A strategy for long-term data management
  • Authentication using Blockchain for data capture & other pipeline processes 
15:00

Genomic data sharing and integration for clinical applications

  • Insights into drivers and barriers to genomic data sharing and integration in the NHS
  • What is the clinical necessity?
  • What are some of the ethical and legal dimensions?
15:00

Using the cloud in drug discovery and design

  • Examine how the cloud is being used to computationally design new drugs
  • How does this method differ from more traditional drug discovery methods and what are the benefits?
  • What does the future look like for the combination of AI and cloud computing in the drug discovery space?
15:00

Biobanks as a data resource

  • Hear an overview of the current status of biobanking and how they consume data
  • What are some of the challenges around getting clinical sample data, a different kind of big data?
  • What role do biobanks play with regards to data linkage and anonymization?
15:20

The Automated Data Scientist

  • Gain an understanding of ways to curate and weave complex data types to make them useful for analysis?
  • What have been some of the major challenges to overcome when working with biological, clinical and RWE data sets?
  • What role does automation play in data curation?
15:20

Faster Results to Discovery: Adding High-Speed Data Transfer to your Cloud Applications

  • Moving big data to the cloud for collaborative research and pharma applications is nearly impossible over the internet and shipping hard drives is a risky alternative
  • Learn how IBM Aspera high-speed transfer software makes it possible securely move data of any size to the cloud at speeds 100s of times faster than other solutions
  • Explore best practices from organizations like BGI and Bluebee High Performance Genomics that use Aspera to accelerate critical cloud-based research and bioinformatics
Per Hansen, Regional Manager Sales Engineering, Aspera, an IBM company
15:20

The role of biodata from rare disease discovery to clinical application

  • How is the growth in precision medicine and biodata helping to accelerate progress in the development of treatment for rare diseases?
  • Where are there still pitfalls in rare disease data that can be addressed?
  • What is the biggest opportunity moving forward for biodata and rare diseases?
15:20

Cognitive Search & Analytics: Building a next-generation search platform for biodata to

  • Overcome the challenges of working with large, diverse datasets, of both structured and unstructured, from internal and external sources within pharmaceutical R&D
  • Enable Pharma companies accelerate research and shorten Drug Time-to-Market
  • Drive innovation within research whilst maintaining information governance and security 
Dominique Raimbaux, UK Regional Sales Manager, Sinequa

15:40 Networking refreshment break

Data Storage & Management

Data Computing & Processing

Transforming Big Data into Smart Data

Open-Source Data Models

NGS & NGS Informatics

Other Therapeutic Areas

16:25

Case Study: Open Targets

  • Hear about the new data being generated as part of the Open Targets public-private initiative
  • Update on the bioinformatics platform
  • What is the progress being made in experimental data and how are they integrating that data into the platform?
16:25

Highly scalable NGS data processing between research and clinic

  • Gain an understanding of how the QuickNGS and CancerSysDB platforms achieve highest throughput in NGS applications, ranging from basic research to clinical investigation
  • Hear how this highly scalable approach can crunch large-scale study population data and facilitates timely analyses of patients' personal genomes
  • Review challenges including the appropriate deal with national rules for personal data protection, uninterrupted availability of HPC resources, and maintenance of highly complex analysis codes
16:25

Renal virtual clinics and online monitoring of kidney disease

  • Updates on collecting data from patients doing dialysis at home and from a virtual clinic
  • Lessons learnt from this format of data collection that can be applied across other therapeutic areas
  • Explore clinical benefits being seen as a result of this data
16:45

Data-sharing across borders: A Nordic case study

  • What are some of the ethical, legal and technical issues encountered in sharing data across Nordic borders, and what are possible solutions?
  • Lessons learnt from both the Nordic Network and the BigMed Project that can be applied in other geographies
  • Exploring the value of the third party role in data sharing
16:45

Adoption of NGS in the Mayo Clinic

  • Insights from a leading clinic as to where NGS is going within healthcare
  • Review of MP-Seq as a powerful clinical tool
  • With all the tools Mayo Clinic has, why are they not doing genomes?
16:45

On Biomarker Discovery

  • Analysis roadmap
  • Systematic validation of early findings
  • Biomarker validation approaches 
17:05

How to analyse large virtual cohort of distributed Biomedical data

  • Access and search petabytes of public and private data sets
  • Build a desired cohort using multiple data sources with different custodians, access rules, and locations
  • Project data in the form expected by your analysis application
  • Run analytics anywhere with apps and data that are interoperable and technology independent
Les Mara, Founder, Databiology
17:05

Benefits of whole genome cohort migration to GRCh38

  • What are the key considerations around performance, storage and quality?
  • Review best practices in working at scale with large cohorts of whole genome data
  • What yield can you expect when using GRCh38?
17:05

Case Study: Moorfields Eye Hospital – DeepMind Health Collaboration

  • Hear an overview of the collaboration where they are training an algorithm to diagnose retinal diseases
  • What have been some of the challenges to overcome within this particular project?
  • What are the biggest opportunities on offer by using AI technology within ophthalmology?
17:25

Realising the potential of big data through multi-national open-source data sharing

  • Update on the work EMBL-EBI are undertaking
  • Why is it important to have multi-national open-source data sharing platforms within biodata?
  • What are some of the implementation challenges around national rules and regulations, governance and project funding?
17:25

Project MinE: an international whole-genome sequencing study (22’500 samples) in amyotrophic lateral sclerosis

  • What is ALS/MND? A brief introduction to this devastating disease and its genetics 
  • What is Project MinE? Consortium design, data infrastructure and analysis 
  • Preliminary results, future prospectives and role in both the international genetic research and population health
Alfredo Iacoangeli, postdoctoral researcher, King's College London

17:45 End of Day 1 – Networking Drinks Reception

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