Data
QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5914

QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5914

in_preparation ARFF Publicly available Visibility: public Uploaded 16-07-2016 by Noureddin Sadawi
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5914 (TID: 102711), and it has 74 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median).

45 features

pXC50 (target)numeric31 unique values
0 missing
molecule_id (row identifier)nominal74 unique values
0 missing
AMWnumeric70 unique values
0 missing
C.numeric63 unique values
0 missing
H.numeric57 unique values
0 missing
Menumeric36 unique values
0 missing
Minumeric36 unique values
0 missing
Mpnumeric56 unique values
0 missing
Mvnumeric56 unique values
0 missing
MWnumeric73 unique values
0 missing
N.numeric53 unique values
0 missing
nABnumeric18 unique values
0 missing
nATnumeric37 unique values
0 missing
nBnumeric1 unique values
0 missing
nBMnumeric20 unique values
0 missing
nBOnumeric26 unique values
0 missing
nBRnumeric2 unique values
0 missing
nBTnumeric37 unique values
0 missing
nCnumeric21 unique values
0 missing
nCLnumeric3 unique values
0 missing
nCspnumeric3 unique values
0 missing
nCsp2numeric20 unique values
0 missing
nCsp3numeric16 unique values
0 missing
nDBnumeric6 unique values
0 missing
nFnumeric5 unique values
0 missing
nHnumeric27 unique values
0 missing
nHetnumeric9 unique values
0 missing
nHMnumeric4 unique values
0 missing
nInumeric2 unique values
0 missing
nNnumeric8 unique values
0 missing
nOnumeric7 unique values
0 missing
nPnumeric1 unique values
0 missing
nSnumeric3 unique values
0 missing
nSKnumeric24 unique values
0 missing
nTBnumeric2 unique values
0 missing
nXnumeric6 unique values
0 missing
O.numeric40 unique values
0 missing
RBFnumeric49 unique values
0 missing
RBNnumeric13 unique values
0 missing
SCBOnumeric44 unique values
0 missing
Senumeric73 unique values
0 missing
Sinumeric73 unique values
0 missing
Spnumeric73 unique values
0 missing
Svnumeric73 unique values
0 missing
X.numeric31 unique values
0 missing

18 properties

74
Number of instances (rows) of the dataset.
45
Number of attributes (columns) of the dataset.
-1
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
44
Number of numeric attributes.
1
Number of nominal attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
0
Percentage of missing values.
-1
The predictive accuracy obtained by always predicting the majority class.
97.78
Percentage of numeric attributes.
0.61
Number of attributes divided by the number of instances.
2.22
Percentage of nominal attributes.
-1
Percentage of instances belonging to the most frequent class.
-1
Number of instances belonging to the most frequent class.
-1
Number of instances belonging to the least frequent class.
0
Number of binary attributes.

3 tasks

1 runs - estimation_procedure: Custom 10-fold Crossvalidation - target_feature: pXC50
Define a new task