Protein Function Test Data with GO Annotations and Interactions

BioReason-Pro Test Data is an evaluation dataset for protein function prediction containing proteins with Gene Ontology term annotations, GO-GPT predictions, InterPro domains, STRING protein-protein interactions, and protein metadata. It was created by wanglab and follows the CAFA framework's temporal holdout protocol. The dataset was last updated in March 2026.

Use Cases

• Benchmark protein function prediction models using GO term annotations as ground truth labels.
• Evaluate the performance of GO-GPT predictions against established protein metadata and InterPro domain features.
• Analyze protein-protein interaction networks from STRING data in the context of functional annotation.
• Train multimodal models that combine sequence-derived features (InterPro domains) with network features (STRING interactions) for function prediction.

Strengths

• Designed for evaluation following the established CAFA framework's temporal holdout protocol.
• Contains multiple linked biological data types: GO annotations, predictions, domains, and interactions.

Limitations

• Dataset size, row count, and specific class distributions are unknown.
• The temporal recency of the underlying protein data and annotations is unspecified.

Provenance

Source

wanglab

Collection Method

Constructed as an evaluation dataset, likely aggregating from sources like GO, InterPro, and STRING.

Freshness

Last updated on 2026-03-20.