As a membrane separating circulating blood and brain extracellular fluid, the blood-brain barrier (BBB) is the protective layer that blocks most foreign drugs. Thus the ability of a drug to penetrate the barrier to deliver to the site of action forms a crucial challenge in developing drugs for the central nervous system.
Task description
Binary classification. Given a drug SMILES string, predict the activity of BBB.
CNN is applying Convolutional Neural Network on SMILES string fingerprint. Model is tuned with 100 runs using Ax platform.
To load the pre-trained model, type
python
1from tdc import tdc_hf_interface
2tdc_hf = tdc_hf_interface("BBB_Martins-CNN")3# load deeppurpose model from this repo4dp_model = tdc_hf.load_deeppurpose('./data')5tdc_hf.predict_deeppurpose(dp_model,['YOUR SMILES STRING'])
Martins, Ines Filipa, et al. “A Bayesian approach to in silico blood-brain barrier penetration modeling.” Journal of chemical information and modeling 52.6 (2012): 1686-1697.
