Evaluation for prokn
Evaluator: Automated evaluation (GPT-5.1-Codex-Max)
Evaluated on: 2026-01-23
⚠️ Automated Evaluation: This evaluation was generated automatically using an AI-based system. It is distinct from manual evaluations curated by human experts. Please review findings carefully and report any inaccuracies.
Evaluation Criteria: This evaluation uses the KG-Registry evaluation rubric as described in Cortes et al. (2025) . The rubric assesses knowledge graphs across multiple dimensions including access, provenance, documentation, maintenance, and fitness for purpose.
Access Level and Types
| Question | Answer | Comment |
|---|---|---|
| Access to data outside of the knowledge graph | Y | Per-source node and edge CSVs downloadable from the ProKN downloads page. |
| API or online access to the knowledge graph | Y | REST API documented at https://research.bioinformatics.udel.edu/ProKN/restapi. |
| Multiple access options available | Y | Interactive explorer UI, REST API, and CSV downloads. |
| Source code availability | Y | Website code on GitHub (ProKN-Website repository linked from the footer - inaccessible at eval time). |
| Downloadable knowledge graph | Y | CSV node/edge files for each source are available for download. |
Section Score: 5/5
Provenance of Nodes and Edges
| Question | Answer | Comment |
|---|---|---|
| Source list provided | Y | Sources enumerated in the downloads tables (e.g., GlyGen, LINCS, PIR, GTEx). |
| Source versions information | N | No upstream source versions or dump dates stated beyond a single "Last Updated" column. |
| Import dependencies | Y | Dependencies implied by the listed source datasets feeding ProKN. |
| Node and edge sources | Y | Each node/edge file name encodes its originating source. |
| Edges deduplication | N | No mention of edge deduplication steps. |
| Triples source details | N | No triple-level provenance beyond source-level grouping. |
| Edge type schema | N | No formal edge-type schema documented. |
Section Score: 3/7
Documented standards, schema, construction
| Question | Answer | Comment |
|---|---|---|
| Biological usable data | Y | Integrates protein-centric biomedical data and associations. |
| Resolvable IDs | Y | Uses standard identifiers (e.g., UniProt, GO, ClinVar, GTEx). |
| Construction documentation | N | No build or ETL documentation provided. |
| Transformation documentation | N | Transform steps from sources to ProKN not described. |
| Schema used | N | No explicit schema statement. |
Section Score: 2/5
Update frequency and versioning
| Question | Answer | Comment |
|---|---|---|
| Stable versions | N | No release tags or versioned downloads. |
| Public tracker information | Y | GitHub issues link on the ProKN website footer (repo inaccessible at eval time). |
| Knowledge graph contact information | Y | Contact email (chenc@udel.edu) provided. |
| Updated annually | N | No stated update cadence. |
| Prior versions access | N | No archive of prior versions or dumps. |
Section Score: 2/5
Evaluation - Metrics and Fitness for Purpose
| Question | Answer | Comment |
|---|---|---|
| Use case provided | Y | Describes protein-centric integration for functional genomics and CFDE reuse. |
| Evaluation against other models | N | No comparative evaluation reported. |
| Defined scope | Y | Scope limited to protein-related knowledge spanning listed sources. |
| Multiple evaluation methods | N | No evaluation methodology described. |
| Accuracy metrics | N | No accuracy or quality metrics provided. |
Section Score: 2/5
License Information
| Question | Answer | Comment |
|---|---|---|
| License | N | No license specified on the site. |