ProtNLM2 External predictions
View prediction review YAML · CycA-protnlm-predictions-review.yaml · Review status: COMPLETE
Both the CDK-regulator and mitotic-transition predictions are supported by characterized cyclin A biology and complete retention of the cyclin domain.
Source documents: genes/DROME/CycA/CycA-protnlm-source.json · genes/DROME/CycA/CycA-bioinformatics/RESULTS.md
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 · file:DROME/CycA/CycA-protnlm-source.json
Review rationale: The PC isoform preserves the complete cyclin domain of characterized Drosophila CycA. Primary work on the CycA–Cdk1 system demonstrates control of CDK substrate recognition through the cyclin hydrophobic patch. The one-residue N-terminal isoform difference lies outside that domain, supporting the broad regulator transfer. Sparse accession-level GOA does not make this established fly function biologically novel, so CNN applies; actual inclusion in the model training set is not established.
Supporting Evidence:
- PMID:17431409: "We propose that binding of Frs to cyclins blocks the hydrophobic patch to interfere with Cdk1 substrate recognition."
- file:DROME/CycA/CycA-bioinformatics/RESULTS.md: "The annotated cyclin domain 206–332 is fully retained and maps to target 205–331."
CNN — Correct but not novel Review score: 2/2
Prediction method: ProtNLM2 · Version: UniProt API snapshot 2026-09-08 · file:DROME/CycA/CycA-protnlm-source.json
Review rationale: Fly cyclin A is required for continued mitotic divisions and undergoes cell-cycle-dependent accumulation and prophase relocalization. PC retains the complete cyclin domain, supporting the conserved mitotic-transition role. The original target GOA contains broader terms, but the relevant same-gene biology is already described in the literature. The prediction is therefore CNN; actual inclusion in the model training set is not established.
Supporting Evidence:
- PMID:2564316: "a functional cyclin A gene was required for continued division after exhaustion of maternally contributed cyclin A."
- PMID:2564316: "cyclin A accumulates in the interphase cytoplasm of cellularized embryos, but relocates to the nuclear region early in prophase"
- file:DROME/CycA/CycA-bioinformatics/RESULTS.md: "The annotated cyclin domain 206–332 is fully retained and maps to target 205–331."