marinkaz commited on
Commit
15d584d
1 Parent(s): cca4f63

Update readme

Browse files
Files changed (1) hide show
  1. README.md +11 -9
README.md CHANGED
@@ -9,15 +9,17 @@ metrics:
9
  tags:
10
  - biology
11
  - chemistry
 
 
 
 
12
  library_name: tdc
13
  license: bsd-2-clause
14
  ---
15
 
16
  ## Dataset description
17
 
18
- 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.
19
-
20
-
21
 
22
  ## Task description
23
 
@@ -29,8 +31,9 @@ Binary classification. Given a drug SMILES string, predict the activity of BBB.
29
  Total: 1,975 drugs
30
 
31
 
32
- ## Dataset split:
33
  Random split on 70% training, 10% validation, and 20% testing
 
34
  To load the dataset in TDC, type
35
 
36
  ```python
@@ -39,8 +42,7 @@ data = ADME(name = 'BBB_Martins')
39
  ```
40
 
41
  ## Model description
42
- Morgan chemical fingerprint with an MLP decoder. Model is tuned with 100 runs using Ax platform.
43
-
44
 
45
  ```python
46
  from tdc import tdc_hf_interface
@@ -50,6 +52,6 @@ dp_model = tdc_hf_herg.load_deeppurpose('./data')
50
  tdc_hf.predict_deeppurpose(dp_model, ['YOUR SMILES STRING'])
51
  ```
52
 
53
- ## References:
54
-
55
- [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.
 
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
  ---
19
 
20
  ## Dataset description
21
 
22
+ 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 central nervous system.
 
 
23
 
24
  ## Task description
25
 
 
31
  Total: 1,975 drugs
32
 
33
 
34
+ ## Dataset split
35
  Random split on 70% training, 10% validation, and 20% testing
36
+
37
  To load the dataset in TDC, type
38
 
39
  ```python
 
42
  ```
43
 
44
  ## Model description
45
+ Morgan chemical fingerprint with an MLP decoder. The model is tuned with 100 runs using the Ax platform.
 
46
 
47
  ```python
48
  from tdc import tdc_hf_interface
 
52
  tdc_hf.predict_deeppurpose(dp_model, ['YOUR SMILES STRING'])
53
  ```
54
 
55
+ ## References
56
+ * Dataset entry in Therapeutics Data Commons, https://tdcommons.ai/single_pred_tasks/adme/#bbb-blood-brain-barrier-martins-et-al
57
+ * 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.