Description

Mitigation

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

Establish a consensus on the minimal number of business questions

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

1. Technology research - review Open Targets

2. Review preliminary work done at Abbvie

3. If no KG is available, estimate the conversion process

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

Failure to identify a suitable open LLM

This is not yet known and represents a gap

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

This is not yet known and represents a gap

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

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”)