We asked: Does sorafenib engage KDR in canine HSA × human angiosarcoma?

Co-fold the target with the ligand to test complex formation + affinity.

Cross-species caveat. Co-folded against human 3VHE (VEGFR2 / KDR). The canine KDR/VEGFR2 ortholog (RefSeq NP_001041489.1 / UniProt A0A8I3NL83, taxid 9615) is 93% identical to human overall, 97% across the kinase domain, and 100% identical at every ATP/TKI-pocket residue — so the human structure is a justified cross-species proxy (the binding pocket is sequence-identical), not an unverified substitution.

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. Boltz-2 co-folded sorafenib with KDR: interface iptm 0.98, P(binder)=0.81, affinity_pred -1.45 (log µM, lower=stronger). Signal: supports.

Confidence so far: 79% — 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.