ACACB activity model
ACACB (ACC2) is the acetyl-CoA carboxylase on the mitochondrial membrane. The malonyl-CoA it makes holds back fatty-acid oxidation, so its inhibitors are studied for fatty liver disease (MASH), obesity and type 2 diabetes. The reference structure 5KKN has ND-646 bound, an allosteric inhibitor that sits on the biotin carboxylase domain and blocks its dimerization.
A model trained on measured activity data for ACACB (Metabolic). Give it compounds and it predicts their IC50 against ACACB, so you can rank candidates by it.
Predict with this model
- UniProt
- O00763
- Reference structure
- PDB 5KKN, ligand 6U3
- Training data
- TSAP (AI-QSAR): 49 compounds, IC50
- Validation
- Predicted and measured values are compared on compounds held out of training.
- Cost
- From 519 credits
- Model version
- TSAP (AI-QSAR): Ridge regression on docking features
Validation results
Predicted and measured values compared on compounds held out of training.
TSAP (AI-QSAR)
Pearson r
0.80
Holdout compounds
12
How to use it
Under Predict with this model, press TSAP (AI-QSAR). Its wizard opens with the ACACB model already selected.
Upload the SMILES of the compounds to predict as a .smi, .csv or .txt file.
Check the estimated credits and time, then submit.
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 12 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 ACACB model
Sign up and get 500 credits. No card required. You can also choose to get news about new models and workflows.