Description

Mitigation

Responsible Party

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

Draft appropriate business questions - DONE; but not all business questions can be answered with specific technologies, so must take this factor into account

Lee Harland, John Wise, Bruce Press, Peter Revill

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

• BioCypher

• Can we also use Open Targets native API https://platform.opentargets.org/api OR https://platform-docs.opentargets.org/data-access/google-bigquery

• Need to record selection criteria and rank the technologies on these criteria

• Need to produce an architecture diagram

The Hyve
Jordan Ramsdell
Robert Gill
Brian Evarts

Open Targets/EBI:

Sebastian Lobentanzer

Ellen McDonagh

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.

• See refs 7, 8 below

• BioCypher by EBI may have this capability already - needs evaluation

The Hyve
Jordan Ramsdell
Robert Gill
Brian Evarts

Open Targets/EBI:

Sebastian Lobentanzer

Ellen McDonagh

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”)

Is there need for an architecture that would be broadly applicable beyond the narrow POC?

• Technology research

• Need agents that can collect data from any source

• How is BioChatter/BioCypher architecture deficient?

Some proprietary LLMs may be censored, thus introducing uncontrollable bias in the answers that they produce

• DONE: Strong preference for an open-source, uncensored LLMs

Identified and resolved in the LLM sub-team