ProtNLM2 External predictions
View prediction review YAML · CG3515-protnlm-predictions-review.yaml · Review status: COMPLETE
The nucleus prediction is supported as a conserved WDR82-family localization and is already represented in the annotation record.
Source documents: projects/PROTNLM_EVALUATION/fly-benchmark/predictions.jsonl.gz · genes/DROME/CG3515/CG3515-predictions-source.json
Review score: 2 = concordant with evidence; 1 = uncertain; 0 = discordant with evidence. This is an assessment score, not a model probability.
CNN — Correct but not novel Review score: 2/2
Prediction method: ProtNLM2 · Version: UniProt API snapshot 2026-09-08
Review rationale: Nuclear localization is a reasonable conserved inference from the diagnostic Swd2/WDR82 family assignment and curated chromatin/COMPASS placement. Primary WDR82 experiments establish chromatin association and Set1-complex membership, providing the biological basis for that transfer. CG3515 is a separate fly paralog from Wdr82/CG17293, so these are not claimed as direct target experiments. The nucleus term is already present, making this supported prediction non-novel.
Supporting Evidence:
- file:DROME/CG3515/CG3515-uniprot.txt: "DR InterPro; IPR037867; Swd2/WDR82."
- PMID:18838538: "We have shown that Wdr82, which associates with chromatin in a histone H2B ubiquitination-dependent manner, is a specific component of Set1 complexes but not that of MLL1-4 complexes."