TSAP (Boltz-2)TSAP (AI-QSAR)
Oncology

MEN1 activity model

MEN1 (menin) is a scaffold protein that binds the histone methyltransferase KMT2A (MLL). In acute leukemias with a KMT2A rearrangement or an NPM1 mutation, this binding keeps leukemia genes such as HOXA9 and MEIS1 switched on, so menin inhibitors that block its MLL-binding pocket, such as revumenib, are used to treat these leukemias. The reference structure 4OG4 has the small-molecule inhibitor MIV-3S bound in that pocket.

A model trained on measured activity data for MEN1 (Oncology). Give it compounds and it predicts their IC50 against MEN1, so you can rank candidates by it.

Predict with this model

Model card
UniProt
O00255
Reference structure
PDB 4OG4, ligand 2VK
Training data
TSAP (Boltz-2): 81 compounds, IC50TSAP (AI-QSAR): 81 compounds, IC50
Validation
Predicted and measured values are compared on compounds held out of training.
Cost
From 351 credits
Model version
TSAP (Boltz-2): TSAP pipeline v2.2TSAP (AI-QSAR): Ridge regression on docking features
MEN1 receptor structure (PDB 4OG4) with the ligand 2VK in the binding pocket

Validation results

Predicted and measured values compared on compounds held out of training. RMSE is in log units (pIC50 and similar).

TSAP (Boltz-2)

Pearson r

0.81

R² (CoD)

0.50

RMSE (log units)

0.64

Holdout compounds

20

TSAP (AI-QSAR)

Pearson r

0.78

R² (CoD)

0.59

Holdout compounds

20

How to use it

  1. Under Predict with this model, press TSAP (Boltz-2) or TSAP (AI-QSAR). The wizard of the workflow you pressed opens with the MEN1 model already selected.

  2. Upload the SMILES of the compounds to predict as a .smi, .csv or .txt file.

  3. Check the estimated credits and time, then submit.

  4. The result is a table of compounds ranked by predicted IC50.

Limitations

  • Predictions can be less accurate for compounds whose structures differ a lot from the training data.
  • Validation used only about 20 compounds, so performance on new compounds can differ from these metrics.
  • Predictions do not replace experiments. Use them to decide what to synthesize and measure first.

Run your own predictions with the MEN1 model

Sign up and get 500 credits. No card required. You can also choose to get news about new models and workflows.