{
"data_id": "40304",
"name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6149",
"exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6149",
"version": 12,
"version_label": null,
"description": "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL6149 (TID: 102770), and it has 73 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).",
"format": "ARFF",
"uploader": "Noureddin Sadawi",
"uploader_id": 62,
"visibility": "public",
"creator": "\"Dr Jeremy Besnard, Dr Ivan Olier, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn\"",
"contributor": null,
"date": "2016-07-16 10:59:48",
"update_comment": null,
"last_update": "2016-07-16 10:59:48",
"licence": "Public",
"status": "deactivated",
"error_message": null,
"url": "https:\/\/www.openml.org\/data\/download\/3693123\/data_36235.arff",
"kaggle_url": null,
"default_target_attribute": "pXC50",
"row_id_attribute": "molecule_id",
"ignore_attribute": null,
"runs": 1,
"suggest": {
"input": [
"QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6149",
"This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL6149 (TID: 102770), and it has 73 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). "
],
"weight": 5
},
"qualities": {
"NumberOfInstances": 73,
"NumberOfFeatures": 45,
"NumberOfClasses": 0,
"NumberOfMissingValues": 0,
"NumberOfInstancesWithMissingValues": 0,
"NumberOfNumericFeatures": 44,
"NumberOfSymbolicFeatures": 1,
"MeanKurtosisOfNumericAtts": 3.6664975734447824,
"NumberOfBinaryFeatures": 0,
"Quartile1MutualInformation": null,
"MeanMeansOfNumericAtts": 25.741049501867995,
"Quartile1SkewnessOfNumericAtts": 0.268641035220976,
"MeanMutualInformation": null,
"Quartile1StdDevOfNumericAtts": 0.43445416138306003,
"AutoCorrelation": 0.4659583333333333,
"MeanNoiseToSignalRatio": null,
"Quartile2AttributeEntropy": null,
"ClassEntropy": null,
"MeanNominalAttDistinctValues": null,
"Quartile2KurtosisOfNumericAtts": -0.040678875912665946,
"Dimensionality": 0.6164383561643836,
"MeanSkewnessOfNumericAtts": 1.073324225956717,
"Quartile2MeansOfNumericAtts": 5.563684931506849,
"EquivalentNumberOfAtts": null,
"MeanStdDevOfNumericAtts": 5.325148706085482,
"Quartile2MutualInformation": null,
"MajorityClassPercentage": null,
"MinAttributeEntropy": null,
"Quartile2SkewnessOfNumericAtts": 0.34356024789909484,
"MajorityClassSize": null,
"MaxAttributeEntropy": null,
"MinKurtosisOfNumericAtts": -0.8898035088795511,
"PercentageOfBinaryFeatures": 0,
"Quartile2StdDevOfNumericAtts": 2.1294813926241436,
"MaxKurtosisOfNumericAtts": 72.99999999999999,
"MinMeansOfNumericAtts": 0,
"PercentageOfInstancesWithMissingValues": 0,
"Quartile3AttributeEntropy": null,
"MaxMeansOfNumericAtts": 453.5291780821918,
"MinMutualInformation": null,
"PercentageOfMissingValues": 0,
"Quartile3KurtosisOfNumericAtts": 1.7338887836811494,
"MaxMutualInformation": null,
"MinNominalAttDistinctValues": null,
"PercentageOfNumericFeatures": 97.77777777777777,
"Quartile3MeansOfNumericAtts": 34.86301369863014,
"MaxNominalAttDistinctValues": null,
"MinSkewnessOfNumericAtts": -0.9513154857180347,
"PercentageOfSymbolicFeatures": 2.2222222222222223,
"Quartile3MutualInformation": null,
"MaxSkewnessOfNumericAtts": 8.544003745317513,
"MinStdDevOfNumericAtts": 0,
"Quartile1AttributeEntropy": null,
"Quartile3SkewnessOfNumericAtts": 1.3786910289061414,
"MaxStdDevOfNumericAtts": 83.59487748051154,
"MinorityClassPercentage": null,
"Quartile1KurtosisOfNumericAtts": -0.45954396152486554,
"Quartile3StdDevOfNumericAtts": 5.746978541683865,
"MeanAttributeEntropy": null,
"MinorityClassSize": null,
"Quartile1MeansOfNumericAtts": 0.660958904109589,
"StdvNominalAttDistinctValues": null
},
"tags": [
{
"tag": "MetaQSAR",
"uploader": "62"
},
{
"tag": "study_13",
"uploader": "62"
}
],
"features": [
{
"name": "pXC50",
"index": "44",
"type": "numeric",
"distinct": "14",
"missing": "0",
"target": "1",
"min": "5",
"max": "9",
"mean": "5",
"stdev": "1"
},
{
"name": "molecule_id",
"index": "0",
"type": "nominal",
"distinct": "73",
"missing": "0",
"identifier": "1",
"distr": []
},
{
"name": "AMW",
"index": "1",
"type": "numeric",
"distinct": "69",
"missing": "0",
"min": "7",
"max": "12",
"mean": "8",
"stdev": "1"
},
{
"name": "C.",
"index": "2",
"type": "numeric",
"distinct": "62",
"missing": "0",
"min": "35",
"max": "51",
"mean": "42",
"stdev": "4"
},
{
"name": "H.",
"index": "3",
"type": "numeric",
"distinct": "56",
"missing": "0",
"min": "24",
"max": "51",
"mean": "42",
"stdev": "5"
},
{
"name": "Me",
"index": "4",
"type": "numeric",
"distinct": "36",
"missing": "0",
"min": "1",
"max": "1",
"mean": "1",
"stdev": "0"
},
{
"name": "Mi",
"index": "5",
"type": "numeric",
"distinct": "36",
"missing": "0",
"min": "1",
"max": "1",
"mean": "1",
"stdev": "0"
},
{
"name": "Mp",
"index": "6",
"type": "numeric",
"distinct": "56",
"missing": "0",
"min": "1",
"max": "1",
"mean": "1",
"stdev": "0"
},
{
"name": "Mv",
"index": "7",
"type": "numeric",
"distinct": "56",
"missing": "0",
"min": "1",
"max": "1",
"mean": "1",
"stdev": "0"
},
{
"name": "MW",
"index": "8",
"type": "numeric",
"distinct": "72",
"missing": "0",
"min": "255",
"max": "642",
"mean": "454",
"stdev": "84"
},
{
"name": "N.",
"index": "9",
"type": "numeric",
"distinct": "52",
"missing": "0",
"min": "2",
"max": "18",
"mean": "9",
"stdev": "3"
},
{
"name": "nAB",
"index": "10",
"type": "numeric",
"distinct": "18",
"missing": "0",
"min": "10",
"max": "30",
"mean": "19",
"stdev": "5"
},
{
"name": "nAT",
"index": "11",
"type": "numeric",
"distinct": "37",
"missing": "0",
"min": "36",
"max": "83",
"mean": "56",
"stdev": "12"
},
{
"name": "nB",
"index": "12",
"type": "numeric",
"distinct": "1",
"missing": "0",
"min": "0",
"max": "0",
"mean": "0",
"stdev": "0"
},
{
"name": "nBM",
"index": "13",
"type": "numeric",
"distinct": "20",
"missing": "0",
"min": "11",
"max": "32",
"mean": "21",
"stdev": "5"
},
{
"name": "nBO",
"index": "14",
"type": "numeric",
"distinct": "26",
"missing": "0",
"min": "21",
"max": "52",
"mean": "36",
"stdev": "7"
},
{
"name": "nBR",
"index": "15",
"type": "numeric",
"distinct": "2",
"missing": "0",
"min": "0",
"max": "1",
"mean": "0",
"stdev": "0"
},
{
"name": "nBT",
"index": "16",
"type": "numeric",
"distinct": "37",
"missing": "0",
"min": "38",
"max": "87",
"mean": "60",
"stdev": "13"
},
{
"name": "nC",
"index": "17",
"type": "numeric",
"distinct": "20",
"missing": "0",
"min": "14",
"max": "35",
"mean": "23",
"stdev": "5"
},
{
"name": "nCL",
"index": "18",
"type": "numeric",
"distinct": "3",
"missing": "0",
"min": "0",
"max": "2",
"mean": "0",
"stdev": "1"
},
{
"name": "nCsp",
"index": "19",
"type": "numeric",
"distinct": "3",
"missing": "0",
"min": "0",
"max": "2",
"mean": "0",
"stdev": "0"
},
{
"name": "nCsp2",
"index": "20",
"type": "numeric",
"distinct": "20",
"missing": "0",
"min": "7",
"max": "26",
"mean": "17",
"stdev": "4"
},
{
"name": "nCsp3",
"index": "21",
"type": "numeric",
"distinct": "16",
"missing": "0",
"min": "0",
"max": "16",
"mean": "6",
"stdev": "4"
},
{
"name": "nDB",
"index": "22",
"type": "numeric",
"distinct": "6",
"missing": "0",
"min": "0",
"max": "5",
"mean": "1",
"stdev": "1"
},
{
"name": "nF",
"index": "23",
"type": "numeric",
"distinct": "5",
"missing": "0",
"min": "0",
"max": "6",
"mean": "1",
"stdev": "1"
},
{
"name": "nH",
"index": "24",
"type": "numeric",
"distinct": "27",
"missing": "0",
"min": "9",
"max": "42",
"mean": "24",
"stdev": "7"
},
{
"name": "nHet",
"index": "25",
"type": "numeric",
"distinct": "9",
"missing": "0",
"min": "5",
"max": "13",
"mean": "9",
"stdev": "2"
},
{
"name": "nHM",
"index": "26",
"type": "numeric",
"distinct": "4",
"missing": "0",
"min": "0",
"max": "3",
"mean": "1",
"stdev": "1"
},
{
"name": "nI",
"index": "27",
"type": "numeric",
"distinct": "2",
"missing": "0",
"min": "0",
"max": "1",
"mean": "0",
"stdev": "0"
},
{
"name": "nN",
"index": "28",
"type": "numeric",
"distinct": "8",
"missing": "0",
"min": "1",
"max": "8",
"mean": "5",
"stdev": "1"
},
{
"name": "nO",
"index": "29",
"type": "numeric",
"distinct": "7",
"missing": "0",
"min": "0",
"max": "6",
"mean": "2",
"stdev": "1"
},
{
"name": "nP",
"index": "30",
"type": "numeric",
"distinct": "1",
"missing": "0",
"min": "0",
"max": "0",
"mean": "0",
"stdev": "0"
},
{
"name": "nS",
"index": "31",
"type": "numeric",
"distinct": "3",
"missing": "0",
"min": "0",
"max": "2",
"mean": "0",
"stdev": "1"
},
{
"name": "nSK",
"index": "32",
"type": "numeric",
"distinct": "23",
"missing": "0",
"min": "19",
"max": "46",
"mean": "32",
"stdev": "6"
},
{
"name": "nTB",
"index": "33",
"type": "numeric",
"distinct": "2",
"missing": "0",
"min": "0",
"max": "1",
"mean": "0",
"stdev": "0"
},
{
"name": "nX",
"index": "34",
"type": "numeric",
"distinct": "6",
"missing": "0",
"min": "0",
"max": "6",
"mean": "1",
"stdev": "1"
},
{
"name": "O.",
"index": "35",
"type": "numeric",
"distinct": "40",
"missing": "0",
"min": "0",
"max": "10",
"mean": "4",
"stdev": "2"
},
{
"name": "RBF",
"index": "36",
"type": "numeric",
"distinct": "49",
"missing": "0",
"min": "0",
"max": "0",
"mean": "0",
"stdev": "0"
},
{
"name": "RBN",
"index": "37",
"type": "numeric",
"distinct": "13",
"missing": "0",
"min": "1",
"max": "13",
"mean": "6",
"stdev": "3"
},
{
"name": "SCBO",
"index": "38",
"type": "numeric",
"distinct": "44",
"missing": "0",
"min": "29",
"max": "69",
"mean": "47",
"stdev": "9"
},
{
"name": "Se",
"index": "39",
"type": "numeric",
"distinct": "72",
"missing": "0",
"min": "36",
"max": "83",
"mean": "57",
"stdev": "12"
},
{
"name": "Si",
"index": "40",
"type": "numeric",
"distinct": "72",
"missing": "0",
"min": "41",
"max": "94",
"mean": "63",
"stdev": "14"
},
{
"name": "Sp",
"index": "41",
"type": "numeric",
"distinct": "72",
"missing": "0",
"min": "24",
"max": "54",
"mean": "38",
"stdev": "8"
},
{
"name": "Sv",
"index": "42",
"type": "numeric",
"distinct": "72",
"missing": "0",
"min": "22",
"max": "52",
"mean": "37",
"stdev": "7"
},
{
"name": "X.",
"index": "43",
"type": "numeric",
"distinct": "31",
"missing": "0",
"min": "0",
"max": "11",
"mean": "2",
"stdev": "3"
}
],
"nr_of_issues": 0,
"nr_of_downvotes": 0,
"nr_of_likes": 0,
"nr_of_downloads": 0,
"total_downloads": 0,
"reach": 0,
"reuse": 0,
"impact_of_reuse": 0,
"reach_of_reuse": 0,
"impact": 0
}