Date
Notes Nick Lynch (Unlicensed)
...
Andrew Conkie, Mark Roberts, Jabe Wilson ,Chris Morris, Peter Henstock, David Ficenec, Terry Stouch, Ted Slater, Nick Lynch
Goals
...
Compl
Presentation Material
Timing:
To select best practice goals (possible exemplar business use case(s)) and create a business case(s) for funding by mid Feb 2018 to present at London Conference
Discussion items
...
Failed Clinical Trials
Persuasive models, QSPR
Use Case (Chris): druglikeness. With larger datasets, it will be possible to provide a better molecule quality indicator than RO5 or QED. Public data is available from the point of USAN assignment, but not at the hit to lead stage when triage is most important. With suitable methods for ensuring confidentiality of individual molecules, it will be possible to collaborate on a shared model.
...
Should we develop a wider training course?
Fundamental part of Life Science capability
Who to partner with here? Online Courses (Moots) or add to others (EdX etc)
...
Toolkit providers
Platform providers
Community sites
Service providers
...
Do we also mean Augmented AI
NLP, Machine learning and Neural Networks
...
Action items
& Discussions
Review the business case material
- Add some compelling examples in key areas:
- Pitfalls
- Bread of literature
- Consider impact & value of best practice on community
- Magnify the investment as a funder
- Access to experienced people for a small investment in project
- Speed of delivery
- Time saved and risks of AI errors reduced
- Raise the base level of understanding
- Educational value more broadly
- Neutral party as Pistoia Alliance can recommend things
- Could support requirements definition for tools and platforms with Life Science focus
- Could review platforms and provide feedback
- Magnify the investment as a funder
- Pitfalls - See Mark's great mindmap in this folder
- What shall we take from this to add to business case?
- What could have been the cost/impact of these issues
- Any use cases to add to Business case
- Literature - Jabe and colleagues started a search strategy
- Size of challenge exemplified by numbers of papers. Cannot do this alone
- What could be our search strategy to provide these insights to wider community
Links to Material
Best practices Business Case
https://docs.google.com/document/d/1dc9q_UrUprBGZOGKi5ep2Ob2JNyTcUW8ubnHrFb6KbA/edit#
Action items - Complete by 19 Jan. Next meeting week of 22 Jan
- Document Areas for AI Community
- Best Practices Group Folder
- Working Document
-
Examples of pitfalls approaches: Mark R, Andrew CAll to read Business case and document and make changes/additions
Short compilation of pitfalls (and especially if there has been an impact or potential impact to data output or decision making)
- Can we define any metrics
Aim to show the business value a project that would address these issues
- Need good examples of value
- Phasing - what could be done in 6-9 months by end of 2018
- Who else to involve?
- Mark to see how best to use Pitfall examples in the case
- Jabe consider what sunmmary from Literature review can make case
- Breadth of challenge highlighted
- How the project can use teams experience (& tools) to find good examples to build on
- What would best pratices look like: - Peter H
- How would this best practices look from the customer side?
- How best to draw on existing sites and communities?What is different about Pistoia Alliance approach