Update readme
Browse files
README.md
CHANGED
@@ -9,6 +9,10 @@ metrics:
|
|
9 |
tags:
|
10 |
- biology
|
11 |
- chemistry
|
|
|
|
|
|
|
|
|
12 |
library_name: tdc
|
13 |
license: bsd-2-clause
|
14 |
---
|
@@ -17,18 +21,13 @@ license: bsd-2-clause
|
|
17 |
|
18 |
The CYP P450 genes are involved in the formation and breakdown (metabolism) of various molecules and chemicals within cells. Specifically, CYP3A4 is an important enzyme in the body, mainly found in the liver and in the intestine. It oxidizes small foreign organic molecules (xenobiotics), such as toxins or drugs, so that they can be removed from the body.
|
19 |
|
20 |
-
|
21 |
-
|
22 |
## Task description
|
23 |
Binary classification. Given a drug SMILES string, predict CYP3A4 inhibition.
|
24 |
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
## Dataset statistics
|
29 |
Total: 12,328 drugs
|
30 |
|
31 |
-
## Dataset split
|
32 |
Random split on 70% training, 10% validation, and 20% testing
|
33 |
To load the dataset in TDC, type
|
34 |
```python
|
@@ -38,7 +37,7 @@ data = ADME(name = 'CYP3A4_Veith')
|
|
38 |
|
39 |
## Model description
|
40 |
|
41 |
-
AttentiveFP is a Graph Attention Network-based molecular representation learning method.
|
42 |
|
43 |
```python
|
44 |
from tdc import tdc_hf_interface
|
@@ -48,5 +47,6 @@ dp_model = tdc_hf_herg.load_deeppurpose('./data')
|
|
48 |
tdc_hf.predict_deeppurpose(dp_model, ['YOUR SMILES STRING'])
|
49 |
```
|
50 |
|
51 |
-
## References
|
52 |
-
|
|
|
|
9 |
tags:
|
10 |
- biology
|
11 |
- chemistry
|
12 |
+
- therapeutic science
|
13 |
+
- drug design
|
14 |
+
- drug development
|
15 |
+
- therapeutics
|
16 |
library_name: tdc
|
17 |
license: bsd-2-clause
|
18 |
---
|
|
|
21 |
|
22 |
The CYP P450 genes are involved in the formation and breakdown (metabolism) of various molecules and chemicals within cells. Specifically, CYP3A4 is an important enzyme in the body, mainly found in the liver and in the intestine. It oxidizes small foreign organic molecules (xenobiotics), such as toxins or drugs, so that they can be removed from the body.
|
23 |
|
|
|
|
|
24 |
## Task description
|
25 |
Binary classification. Given a drug SMILES string, predict CYP3A4 inhibition.
|
26 |
|
|
|
|
|
|
|
27 |
## Dataset statistics
|
28 |
Total: 12,328 drugs
|
29 |
|
30 |
+
## Dataset split
|
31 |
Random split on 70% training, 10% validation, and 20% testing
|
32 |
To load the dataset in TDC, type
|
33 |
```python
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
40 |
+
AttentiveFP is a Graph Attention Network-based molecular representation learning method. The model is tuned with 100 runs using the Ax platform.
|
41 |
|
42 |
```python
|
43 |
from tdc import tdc_hf_interface
|
|
|
47 |
tdc_hf.predict_deeppurpose(dp_model, ['YOUR SMILES STRING'])
|
48 |
```
|
49 |
|
50 |
+
## References
|
51 |
+
* Dataset entry in Therapeutics Data Commons, https://tdcommons.ai/single_pred_tasks/adme/#cyp-p450-3a4-inhibition-veith-et-al
|
52 |
+
* Veith, Henrike et al. “Comprehensive characterization of cytochrome P450 isozyme selectivity across chemical libraries.” Nature Biotechnology vol. 27,11 (2009): 1050-5.
|