---
language:
- en
metrics:
- accuracy
- AUC ROC
- precision
- recall
pipeline_tag: molecule-property-prediction
tags:
- biology
- chemistry
library_name: tdc
license: bsd-2-clause
---

## Dataset description

As a membrane separating circulating blood and brain extracellular fluid, the blood-brain barrier (BBB) is the protection 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 development of drugs for central nervous system.

## Task description
Binary classification. Given a drug SMILES string, predict the activity of BBB.

## Dataset statistics
Total: 1,975; Train_val: 1,580; Test: 395

## Dataset split: 
Random split on 70% training, 10% validation, and 20% testing
To load the dataset in TDC, type
```python
from tdc.single_pred import ADME
data = ADME(name = 'BBB_Martins')
```

## Model description
AttentiveFP is a Graph Attention Network-based molecular representation learning method. Model is tuned with 100 runs using Ax platform.
To load the pre-trained model, type

```python
from tdc import tdc_hf_interface
tdc_hf = tdc_hf_interface("BBB_Martins-AttentiveFP")
# load deeppurpose model from this repo
dp_model = tdc_hf_herg.load_deeppurpose('./data')
tdc_hf.predict_deeppurpose(dp_model, [YOUR SMILES STRING'])
```

## References:
[1] 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.