OpenML

JavaScript is required to properly view the contents of this page!

Explore
- Data
- Task
- Flow
- Run
- Study
- Task type
- Measure
- People
Help
Blog
Contact
Please cite us

QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2534

deactivated ARFF Publicly available Visibility: public Uploaded 14-07-2016 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: CHEMBL2534 (TID: 10612), and it has 1042 rows and 139 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.

141 features

pXC50 (target)	numeric	220 unique values 0 missing
molecule_id (row identifier)	nominal	1042 unique values 0 missing
P_VSA_e_3	numeric	330 unique values 0 missing
CATS2D_07_AP	numeric	4 unique values 0 missing
piPC09	numeric	759 unique values 0 missing
TPSA.NO.	numeric	588 unique values 0 missing
SpMin1_Bh.p.	numeric	198 unique values 0 missing
piPC10	numeric	762 unique values 0 missing
SpMin1_Bh.i.	numeric	224 unique values 0 missing
nPyridines	numeric	5 unique values 0 missing
piPC08	numeric	737 unique values 0 missing
piPC07	numeric	717 unique values 0 missing
CATS2D_07_DA	numeric	8 unique values 0 missing
nR10	numeric	4 unique values 0 missing
P_VSA_i_4	numeric	417 unique values 0 missing
Hy	numeric	491 unique values 0 missing
SpMin1_Bh.m.	numeric	217 unique values 0 missing
H.050	numeric	14 unique values 0 missing
nHDon	numeric	14 unique values 0 missing
piPC06	numeric	696 unique values 0 missing
P_VSA_p_2	numeric	588 unique values 0 missing
piPC05	numeric	629 unique values 0 missing
SsNH2	numeric	399 unique values 0 missing
N.075	numeric	6 unique values 0 missing
NaaN	numeric	6 unique values 0 missing
TPSA.Tot.	numeric	612 unique values 0 missing
CATS2D_04_PL	numeric	7 unique values 0 missing
SssO	numeric	350 unique values 0 missing
C.028	numeric	5 unique values 0 missing
SAdon	numeric	108 unique values 0 missing
CATS2D_03_PL	numeric	5 unique values 0 missing
GATS1s	numeric	461 unique values 0 missing
SaaaC	numeric	563 unique values 0 missing
GATS1e	numeric	439 unique values 0 missing
N.069	numeric	3 unique values 0 missing
CATS2D_00_DD	numeric	6 unique values 0 missing
CATS2D_00_DP	numeric	6 unique values 0 missing
CATS2D_00_PP	numeric	6 unique values 0 missing
NsNH2	numeric	6 unique values 0 missing
NssO	numeric	7 unique values 0 missing
CATS2D_02_AP	numeric	7 unique values 0 missing
CATS2D_08_AP	numeric	5 unique values 0 missing
D.Dtr10	numeric	194 unique values 0 missing
H.049	numeric	6 unique values 0 missing
NaaaC	numeric	7 unique values 0 missing
CATS2D_02_PL	numeric	5 unique values 0 missing
CATS2D_09_PP	numeric	2 unique values 0 missing
CATS2D_07_AA	numeric	9 unique values 0 missing
CATS2D_08_DA	numeric	10 unique values 0 missing
SaaN	numeric	778 unique values 0 missing
Eig04_EA.ed.	numeric	779 unique values 0 missing
SM13_AEA.dm.	numeric	779 unique values 0 missing
SM15_EA.bo.	numeric	729 unique values 0 missing
CATS2D_02_AL	numeric	17 unique values 0 missing
SM13_EA.bo.	numeric	722 unique values 0 missing
PCD	numeric	757 unique values 0 missing
SpMin6_Bh.m.	numeric	490 unique values 0 missing
SpMin1_Bh.s.	numeric	326 unique values 0 missing
SpMax1_Bh.e.	numeric	249 unique values 0 missing
nArOR	numeric	5 unique values 0 missing
SpMin1_Bh.v.	numeric	200 unique values 0 missing
Eig13_AEA.dm.	numeric	664 unique values 0 missing
SM14_EA.bo.	numeric	723 unique values 0 missing
CATS2D_09_DP	numeric	4 unique values 0 missing
MATS1s	numeric	300 unique values 0 missing
Eig01_EA.bo.	numeric	439 unique values 0 missing
SM11_AEA.ri.	numeric	439 unique values 0 missing
SpDiam_EA.bo.	numeric	442 unique values 0 missing
SpMax_EA.bo.	numeric	439 unique values 0 missing
Chi0_EA.dm.	numeric	845 unique values 0 missing
X1sol	numeric	748 unique values 0 missing
Eig12_EA.ed.	numeric	689 unique values 0 missing
SM07_AEA.ri.	numeric	689 unique values 0 missing
SpMaxA_AEA.ed.	numeric	233 unique values 0 missing
C.032	numeric	3 unique values 0 missing
SpMax8_Bh.i.	numeric	537 unique values 0 missing
CATS2D_06_PL	numeric	9 unique values 0 missing
P_VSA_v_2	numeric	665 unique values 0 missing
SpMin6_Bh.p.	numeric	503 unique values 0 missing
SM08_EA.bo.	numeric	678 unique values 0 missing
SpMax8_Bh.v.	numeric	530 unique values 0 missing
Rperim	numeric	33 unique values 0 missing
Eig11_EA	numeric	587 unique values 0 missing
SM05_AEA.dm.	numeric	587 unique values 0 missing
SpMin1_Bh.e.	numeric	217 unique values 0 missing
SpMaxA_EA.ed.	numeric	328 unique values 0 missing
SM09_EA.bo.	numeric	718 unique values 0 missing
CATS2D_06_DL	numeric	17 unique values 0 missing
SM12_EA.bo.	numeric	715 unique values 0 missing
SpMin6_Bh.v.	numeric	501 unique values 0 missing
SM10_EA.bo.	numeric	710 unique values 0 missing
SpMax8_Bh.e.	numeric	534 unique values 0 missing
CATS2D_04_DL	numeric	16 unique values 0 missing
MPC10	numeric	309 unique values 0 missing
X0sol	numeric	535 unique values 0 missing
SM11_EA.bo.	numeric	706 unique values 0 missing
SpMin8_Bh.e.	numeric	509 unique values 0 missing
ATS5e	numeric	714 unique values 0 missing
Eig12_EA	numeric	594 unique values 0 missing
SM06_AEA.dm.	numeric	594 unique values 0 missing
ATS7i	numeric	778 unique values 0 missing
SpMax1_Bh.v.	numeric	271 unique values 0 missing
SpMin7_Bh.m.	numeric	509 unique values 0 missing
ATS5i	numeric	728 unique values 0 missing
Chi0_AEA.bo.	numeric	663 unique values 0 missing
Chi0_AEA.dm.	numeric	663 unique values 0 missing
Chi0_AEA.ed.	numeric	663 unique values 0 missing
Chi0_AEA.ri.	numeric	663 unique values 0 missing
Chi0_EA	numeric	663 unique values 0 missing
Eta_betaS_A	numeric	129 unique values 0 missing
IC5	numeric	564 unique values 0 missing
Eig09_EA	numeric	562 unique values 0 missing
SM03_AEA.dm.	numeric	562 unique values 0 missing
SNar	numeric	187 unique values 0 missing
ATS7e	numeric	767 unique values 0 missing
X1	numeric	681 unique values 0 missing
nR06	numeric	7 unique values 0 missing
SpMin7_Bh.v.	numeric	516 unique values 0 missing
Eta_betaS	numeric	98 unique values 0 missing
SpMax8_Bh.p.	numeric	526 unique values 0 missing
Sp	numeric	833 unique values 0 missing
IDET	numeric	894 unique values 0 missing
S0K	numeric	248 unique values 0 missing
X1Mad	numeric	948 unique values 0 missing
Sv	numeric	886 unique values 0 missing
Eig15_EA.bo.	numeric	680 unique values 0 missing
LPRS	numeric	897 unique values 0 missing
X2sol	numeric	836 unique values 0 missing
P_VSA_MR_7	numeric	161 unique values 0 missing
Xu	numeric	878 unique values 0 missing
SpMaxA_EA	numeric	134 unique values 0 missing
ATS1e	numeric	608 unique values 0 missing
GMTI	numeric	878 unique values 0 missing
X5	numeric	853 unique values 0 missing
Eig15_EA.ri.	numeric	727 unique values 0 missing
ATS1i	numeric	617 unique values 0 missing
CID	numeric	481 unique values 0 missing
Chi1_EA.ri.	numeric	961 unique values 0 missing
ON1	numeric	258 unique values 0 missing
Psi_i_0	numeric	925 unique values 0 missing
IVDM	numeric	315 unique values 0 missing

Show first 100 features

107 properties

NumberOfInstances

1042

Number of instances (rows) of the dataset.

NumberOfFeatures

141

Number of attributes (columns) of the dataset.

NumberOfClasses

Number of distinct values of the target attribute (if it is nominal).

NumberOfMissingValues

Number of missing values in the dataset.

NumberOfInstancesWithMissingValues

Number of instances with at least one value missing.

NumberOfNumericFeatures

140

Number of numeric attributes.

NumberOfSymbolicFeatures

Number of nominal attributes.

PercentageOfMissingValues

Percentage of missing values.

Quartile3KurtosisOfNumericAtts

51.92

Third quartile of kurtosis among attributes of the numeric type.

AutoCorrelation

0.47

Average class difference between consecutive instances.

RandomTreeDepth1Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

J48.00001.AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .00001

MaxSkewnessOfNumericAtts

30.34

Maximum skewness among attributes of the numeric type.

MinStdDevOfNumericAtts

0.03

Minimum standard deviation of attributes of the numeric type.

PercentageOfNumericFeatures

99.29

Percentage of numeric attributes.

Quartile3MeansOfNumericAtts

13.74

Third quartile of means among attributes of the numeric type.

CfsSubsetEval_DecisionStumpAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth2AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

J48.00001.ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .00001

MaxStdDevOfNumericAtts

82867.5

Maximum standard deviation of attributes of the numeric type.

MinorityClassPercentage

Percentage of instances belonging to the least frequent class.

PercentageOfSymbolicFeatures

0.71

Percentage of nominal attributes.

Quartile3MutualInformation

Third quartile of mutual information between the nominal attributes and the target attribute.

CfsSubsetEval_DecisionStumpErrRate

Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth2ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

J48.00001.Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .00001

MeanAttributeEntropy

Average entropy of the attributes.

MinorityClassSize

Number of instances belonging to the least frequent class.

Quartile1AttributeEntropy

First quartile of entropy among attributes.

Quartile3SkewnessOfNumericAtts

4.31

Third quartile of skewness among attributes of the numeric type.

CfsSubsetEval_DecisionStumpKappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth2Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2

J48.0001.AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .0001

MeanKurtosisOfNumericAtts

59.21

Mean kurtosis among attributes of the numeric type.

NaiveBayesAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes

Quartile1KurtosisOfNumericAtts

0.87

First quartile of kurtosis among attributes of the numeric type.

Quartile3StdDevOfNumericAtts

3.79

Third quartile of standard deviation of attributes of the numeric type.

CfsSubsetEval_NaiveBayesAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth3AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

J48.0001.ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .0001

MeanMeansOfNumericAtts

122.52

Mean of means among attributes of the numeric type.

NaiveBayesErrRate

Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes

Quartile1MeansOfNumericAtts

0.89

First quartile of means among attributes of the numeric type.

REPTreeDepth1AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 1

CfsSubsetEval_NaiveBayesErrRate

Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth3ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

J48.0001.Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .0001

MeanMutualInformation

Average mutual information between the nominal attributes and the target attribute.

NaiveBayesKappa

Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes

Quartile1MutualInformation

First quartile of mutual information between the nominal attributes and the target attribute.

REPTreeDepth1ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 1

CfsSubsetEval_NaiveBayesKappa

Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

RandomTreeDepth3Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3

J48.001.AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .001

MeanNoiseToSignalRatio

An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.

NumberOfBinaryFeatures

Number of binary attributes.

Quartile1SkewnessOfNumericAtts

-0.51

First quartile of skewness among attributes of the numeric type.

REPTreeDepth1Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 1

CfsSubsetEval_kNN1NAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

StdvNominalAttDistinctValues

Standard deviation of the number of distinct values among attributes of the nominal type.

J48.001.ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .001

MeanNominalAttDistinctValues

Average number of distinct values among the attributes of the nominal type.

Quartile1StdDevOfNumericAtts

0.37

First quartile of standard deviation of attributes of the numeric type.

REPTreeDepth2AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 2

CfsSubsetEval_kNN1NErrRate

Error rate achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

kNN1NAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk

J48.001.Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .001

MeanSkewnessOfNumericAtts

3.02

Mean skewness among attributes of the numeric type.

Quartile2AttributeEntropy

Second quartile (Median) of entropy among attributes.

REPTreeDepth2ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 2

CfsSubsetEval_kNN1NKappa

Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W

kNN1NErrRate

Error rate achieved by the landmarker weka.classifiers.lazy.IBk

MajorityClassPercentage

Percentage of instances belonging to the most frequent class.

MeanStdDevOfNumericAtts

630.17

Mean standard deviation of attributes of the numeric type.

Quartile2KurtosisOfNumericAtts

3.07

Second quartile (Median) of kurtosis among attributes of the numeric type.

REPTreeDepth2Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 2

ClassEntropy

Entropy of the target attribute values.

kNN1NKappa

Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk

MajorityClassSize

Number of instances belonging to the most frequent class.

MinAttributeEntropy

Minimal entropy among attributes.

Quartile2MeansOfNumericAtts

3.78

Second quartile (Median) of means among attributes of the numeric type.

REPTreeDepth3AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 3

DecisionStumpAUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump

MaxAttributeEntropy

Maximum entropy among attributes.

MinKurtosisOfNumericAtts

-0.83

Minimum kurtosis among attributes of the numeric type.

Quartile2MutualInformation

Second quartile (Median) of mutual information between the nominal attributes and the target attribute.

REPTreeDepth3ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 3

DecisionStumpErrRate

Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump

MaxKurtosisOfNumericAtts

951.19

Maximum kurtosis among attributes of the numeric type.

MinMeansOfNumericAtts

-0.4

Minimum of means among attributes of the numeric type.

Quartile2SkewnessOfNumericAtts

0.91

Second quartile (Median) of skewness among attributes of the numeric type.

REPTreeDepth3Kappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 3

DecisionStumpKappa

Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump

MaxMeansOfNumericAtts

13799.85

Maximum of means among attributes of the numeric type.

MinMutualInformation

Minimal mutual information between the nominal attributes and the target attribute.

PercentageOfBinaryFeatures

Percentage of binary attributes.

Quartile2StdDevOfNumericAtts

0.83

Second quartile (Median) of standard deviation of attributes of the numeric type.

RandomTreeDepth1AUC

Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

Dimensionality

0.14

Number of attributes divided by the number of instances.

MaxMutualInformation

Maximum mutual information between the nominal attributes and the target attribute.

MinNominalAttDistinctValues

The minimal number of distinct values among attributes of the nominal type.

PercentageOfInstancesWithMissingValues

Percentage of instances having missing values.

Quartile3AttributeEntropy

Third quartile of entropy among attributes.

RandomTreeDepth1ErrRate

Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1

EquivalentNumberOfAtts

Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.

MaxNominalAttDistinctValues

The maximum number of distinct values among attributes of the nominal type.

MinSkewnessOfNumericAtts

-2.03

Minimum skewness among attributes of the numeric type.

Show all 107 properties