Predict HDAC11 inhibitor potency from structure alone.
Paste a SMILES string. Get physicochemical descriptors, drug-likeness flags, and an estimated HDAC11 binding potency — from a model trained on real bioactivity data.
Enter a SMILES string
——
Why HDAC11
A zinc-dependent enzyme, and an understudied drug target.
Histone deacetylases remove acetyl groups from lysine residues on histone tails, tightening chromatin and switching genes off. Their catalytic core coordinates a single zinc ion — the same site most inhibitors, including hydroxamic acids, are designed to chelate.
Of the eleven human HDAC isoforms, HDAC11 remains comparatively underexplored relative to HDAC1 or HDAC6, despite emerging interest in immuno-oncology. Public, ready-to-use prediction tools for it are effectively nonexistent — most HDAC QSAR work exists only inside published papers, not as something a chemist can actually open and use.
How it works
Structure in, estimated potency out.
The model is trained on public HDAC11 bioactivity data from ChEMBL — real IC50 and Ki measurements from published assays, not synthetic or simulated data.
Structure fingerprint
RDKit converts the SMILES into descriptors and a Morgan fingerprint — a structural signature the model can read.
Trained prediction
A random forest model, trained on ~500 known HDAC11 compounds, estimates binding potency from that fingerprint.
Confidence check
Each prediction is scored by similarity to the training data — so you know when it's extrapolating.
On accuracy — this model explains roughly 45% of the variance in known HDAC11 potency (test R² ≈ 0.45). Treat predictions as a rough ranking, not a lab measurement. Descriptors and drug-likeness flags are exact RDKit calculations, independent of the model.