{ "data_id": "39305", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1860", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1860", "version": 11, "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: CHEMBL1860 (TID: 59), and it has 449 rows and 66 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.", "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 07:26:49", "update_comment": null, "last_update": "2016-07-16 07:26:49", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3670048\/data_53099.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1860", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1860 (TID: 59), and it has 449 rows and 66 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. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 449, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.1514476614699332, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.4493548438867916, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6478452689472799, "Quartile2MeansOfNumericAtts": 0.8982138084632516, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.45890346675717, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.7402244458452686, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5526112450512815, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8969703221562901, "MaxKurtosisOfNumericAtts": 7.480873554157595, "MinMeansOfNumericAtts": -0.07765033407572383, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 93.51000668151447, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.3830966949782977, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 2.328730512249442, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1764600211232834, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.3787650252448196, "MinStdDevOfNumericAtts": 0.004084876667397196, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.0481851803005973, "MaxStdDevOfNumericAtts": 41.34933303970066, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7437286372222025, "Quartile3StdDevOfNumericAtts": 1.753097884804001, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4187082405345214, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.07883556409319382, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 3.5656556859355777, "Quartile1SkewnessOfNumericAtts": 0.25347191533521146, "AutoCorrelation": 0.14793973214285636, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4394402116898408 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "273", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "449", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nArOH", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsOH", "index": "2", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "O.057", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "piPC10", "index": "4", "type": "numeric", "distinct": "317", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "CATS2D_08_DL", "index": "5", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "H.050", "index": "6", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "nHDon", "index": "7", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "NdO", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "2" }, { "name": "nDB", "index": "9", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "2" }, { "name": "GATS1i", "index": "10", "type": "numeric", "distinct": "288", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ALOGP", "index": "11", "type": "numeric", "distinct": "382", "missing": "0", "min": "0", "max": "10", "mean": "5", "stdev": "2" }, { "name": "ALOGP2", "index": "12", "type": "numeric", "distinct": "396", "missing": "0", "min": "0", "max": "100", "mean": "23", "stdev": "16" }, { "name": "O.058", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SssO", "index": "14", "type": "numeric", "distinct": "233", "missing": "0", "min": "0", "max": "22", "mean": "4", "stdev": "4" }, { "name": "CATS2D_01_AN", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "16", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NssO", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nArOR", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "JGI7", "index": "19", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "O.060", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nRCONR2", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "22", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS4s", "index": "23", "type": "numeric", "distinct": "359", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NssCH2", "index": "24", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "20", "mean": "5", "stdev": "4" }, { "name": "CATS2D_05_AA", "index": "25", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "X.", "index": "26", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "3" }, { "name": "nX", "index": "27", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nArX", "index": "28", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NaasC", "index": "29", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "N.072", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_AL", "index": "31", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "5" }, { "name": "nS..O.2", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCb.", "index": "33", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "CATS2D_02_AA", "index": "34", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_s_1", "index": "35", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "3" }, { "name": "CATS2D_01_AA", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "N.076", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nArNO2", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NddsN", "index": "39", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "O.061", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS2m", "index": "41", "type": "numeric", "distinct": "268", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NddssS", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "S.110", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_NL", "index": "44", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_AA", "index": "45", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "MATS1s", "index": "46", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_LL", "index": "47", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "42", "mean": "8", "stdev": "7" }, { "name": "GATS2p", "index": "48", "type": "numeric", "distinct": "290", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Hy", "index": "49", "type": "numeric", "distinct": "219", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_05_NL", "index": "50", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "51", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "207", "mean": "20", "stdev": "31" }, { "name": "MATS6m", "index": "52", "type": "numeric", "distinct": "286", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "53", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS1s", "index": "54", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS6e", "index": "55", "type": "numeric", "distinct": "286", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1v", "index": "56", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "57", "type": "numeric", "distinct": "214", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_09_DL", "index": "58", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "GATS4m", "index": "59", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nRCOOH", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS2v", "index": "61", "type": "numeric", "distinct": "259", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1i", "index": "62", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1p", "index": "63", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.005", "index": "64", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "65", "type": "numeric", "distinct": "143", "missing": "0", "min": "4", "max": "11", "mean": "5", "stdev": "2" }, { "name": "P_VSA_LogP_4", "index": "66", "type": "numeric", "distinct": "63", "missing": "0", "min": "30", "max": "210", "mean": "94", "stdev": "41" } ], "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 }