We asked: Inavolisib → canine PIK3CA (degrader engagement)

Dock the drug into the target’s binding pocket and score the pose.

Cross-species caveat. Docked against a human ortholog structure standing in for the canine target — cross-species inference; binding-site conservation for this target has not yet been quantified.

Pre-registered tests, each locked to a kill-criterion before it ran. Any single one failing rules the whole idea out.

Survived every test the engine could run. Nothing here is proven — that's the point.

Readout. gnina docked inavolisib into PIK3CA_CANINE: recommended pose -9.6 kcal/mol (CNN pose 0.99, CNN affinity 8.1); best Vina affinity -9.6 kcal/mol. Signal: supports.

Confidence so far: 85% — never proof.

Every result is hashed so anyone can re-derive it. Clearing these checks is necessary, not sufficient — a human still holds the final call, and nothing is auto-promoted.