AI Data Group 25 Jan 2018 Action Minutes

Date

Notes Nick Lynch (Unlicensed)

Attendees

  • Frederik, Ian, Eric Marshall, Jabe, Bryn, Helena, Nick, Ted, Carmen, Terry, Will, Les

  • Apologies Afrozy, Evelina

Goals & Discussions

  • Comments since last meeting

  • Review the emerging business case (let me know if you cannot edit, should be open but please use a Google account if you can)
  • Goal is to gather 2 or 3 business use cases
  • Ideas on a common template for capturing these, this could go along with the top down approach discussed last meeting 
    • Would like to use a common template for defining these use cases


      • What is the business issue/challenge that could be addressed with AI
      • What would be the benefits?
      • What could be the deliverables? And early pilots
      • Who should we get involved?
      • What aspects of the data needs addressing, eg
        • Is about Quantity of data
        • Labelling?
      • Risks & issues (Could be a checklist to rank likelihood of success)
        • Minimal set of data points
        • Widely observed issue or small community
        • Impact on drug discovery process. How does it impact a drug project
        • Critical Metadata (minimum information standards for area)
        • Confidence in each of the data sets being used/combined
        • Domain knowledge for the area
        • Alignment to FAIR principle
  • Project Timing & phasing options:
    • Early delivery in 4-5 months, second delivery year end?
  • Next steps focusing on Business case and data use cases
    • create a business case(s) for funding by mid Feb 2018 to pitch to groups and present at London Conference

Timing:

To select business use case(s) areas is our key priority

Emerging Data Areas

ItemSummary
Use CasesWhere are the current pain points: We hope to identify these top down from known areas or in other ways
Data 

Need to select areas that have enough data and that this data is accessible or can be made accessible easily.

Longer terms goals to encourage best data access in parallel with other initiatives

Toxicology

Is this Pre-clinical, clinical or post marketing?

Can we link to ETox data sources and other groups who are collecting data

Instrument & Lab data

How to best include Devices and sensors not just from lab but wider data collection tools 

Possible focus on maintenance information and prediction of issues

Rare Disease areasAre there suitable groups to partner here?* Building on Hackathon example from 2017 (frederick ataraxia disease)

*Ian Harrow is a member of the Rare Diseases GO-FAIR group (Marco Roos and Barend Mons) at Leiden, NL. Inaugral meeting is next week.

There is potential value in publishing the use cases and discussion there

Action items

  • Document Areas for AI Community
  • Data Group Folder
  • Working Document
  • All to read and comment on business case document

    • Need to add use cases and examples
  • Planning a AI group meeting 13 March in London, more details
  • Jabe, Dennis, Frederik, Afrozy - Best Practice for data
    • Drawing other industry examples including non Life Sciences
    • See Affrozy section above
  • Industry Examples of AI usage: Terry, Ian

  • Quick review of current AI uses (Imaging, QSAR activity, others)

  • Lessons from Hackathon - Nick wrote to all the participants, awaiting feedback