This repository holds the trained models behind PROTEA's first-place result on the LAFA continuously updated public benchmark for protein function prediction. On the sealed September 2025 to March 2026 target frame (7,401 proteins), scored with the benchmark's own harness, PROTEA leads the public leaderboard.

The score is the benchmark's IA-weighted micro-F, averaged over the three branches of the Gene Ontology, for the three standard settings.

A similarity search finds the most related proteins whose functions are already known and borrows their annotations (strong when nothing else is known). On top of that, a learned combiner weighs three additional signals: a direct predictor that proposes functions across the whole catalogue, the protein's own weaker prior annotations, and, for proteins that are already partly characterised, the functions that habitually accompany what is already known across different branches of the ontology. Every ingredient was chosen on an earlier period of data and the system was measured once on the later, sealed period.

Full recipe, data periods, and commands: the fullgo/ module of the protea-reranker-lab repository (REPRODUCE.md). The whole system uses frozen, pre-computed protein representations and fits on a single 12 GB GPU.

Francisco Miguel Pérez Canales. Part of the PROTEA doctoral thesis project.