Description

Mitigation

Responsible Party

Failure to identify business questions, or picking too many or too few

Draft appropriate business questions

Lee Harland, John Wise, Bruce Press

Validate that Open Targets either has a ready to use Knowledge Graph implementation, or can be converted into a KG with reasonable cost

Meeting on Jan 17, 2024: recording (password: w*Qi2#D9) and transcript

BioCypher could be the right KG. It contains Open Targets. Required steps are:

• QC (anything missing?)

• Update process

• Learn about Abbvie prototypes

The Hyve
Jordan Ramsdell
Robert Gill
Brian Evarts

Failure to identify a suitable LLM

Technology research, feature and cost analysis, and selection

Jon Stevens, Etzard Stolte, Helena Deus; Brian Evarts; Wouter Franke, Matthijs van der Zee

Does Open Targets use an ontology?

Perhaps The Hyve team has a ready answer

Failure to download a large volume of data (all of the PubMed as a maximum) for the prompt-tuning of the LLM

TBD

Failure to perform KG generation from text by an LLM

1. Technology research

2. If no ready-to-use technology exists, estimate bespoke development (tuning an existing LLM for this purpose)

Failure to perform local KG comparison with calculation of a score

1. Technology research

2. If no ready-to-use technology exists, estimate bespoke development

3. If estimates indicate infeasibility, this may become a gap

Failure to generate a proper query for a KG database system by an LLM

Technology research. Code generation by LLMs is a common task, so this risk may be seen as low.

See refs 7, 8 below

Failure to build a prototypical target discovery pipeline on the limited budget in case of mounting technical difficulties

Schedule the project in phases. Aim to answer known unknowns and to establish risk mitigation strategies early in this phase (“project elaboration”)