{ "data_id": "25772", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4608", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4608", "version": 7, "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: CHEMBL4608 (TID: 11006), and it has 692 rows and 68 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": "2016-07-14 17:42:49", "update_comment": null, "last_update": "2016-07-14 17:42:49", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3284422\/data_53397.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4608", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4608 (TID: 11006), and it has 692 rows and 68 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": 692, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4656026011560694, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.5872960140305747, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5170.570710312477, "Quartile1SkewnessOfNumericAtts": 0.5524659499106316, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5466909893811703, "AutoCorrelation": 0.09118813314037655, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.408242504237272, "Dimensionality": 0.10115606936416185, "MeanSkewnessOfNumericAtts": 1.3226976231759957, "Quartile2MeansOfNumericAtts": 8.689306358381506, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 9630.816988073639, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.471509627427237, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.5034292730944108, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 5.86375542196541, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 27.255721764412467, "MinMeansOfNumericAtts": 0.05572109826589597, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 258883.53179190782, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.580593421235337, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 117.13510476878614, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7057710726060078, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 4.228059475882085, "MinStdDevOfNumericAtts": 0.015073490810920543, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.767866871391171, "MaxStdDevOfNumericAtts": 494342.6053354364, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.16743841169296902, "Quartile3StdDevOfNumericAtts": 88.27766286700297 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "382", "missing": "0", "target": "1", "min": "3", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "692", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS1i", "index": "1", "type": "numeric", "distinct": "334", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "2", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_09_DL", "index": "3", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "46", "mean": "11", "stdev": "11" }, { "name": "C.", "index": "4", "type": "numeric", "distinct": "123", "missing": "0", "min": "29", "max": "52", "mean": "39", "stdev": "3" }, { "name": "CATS2D_06_DL", "index": "5", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "36", "mean": "8", "stdev": "9" }, { "name": "SM05_EA.bo.", "index": "6", "type": "numeric", "distinct": "388", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "7", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "29", "mean": "5", "stdev": "6" }, { "name": "SpAD_EA.dm.", "index": "8", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "134", "mean": "23", "stdev": "21" }, { "name": "CATS2D_09_DD", "index": "9", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "4" }, { "name": "ATSC1s", "index": "10", "type": "numeric", "distinct": "580", "missing": "0", "min": "2", "max": "196", "mean": "27", "stdev": "26" }, { "name": "CATS2D_08_DL", "index": "11", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "41", "mean": "10", "stdev": "10" }, { "name": "Eig14_EA.dm.", "index": "12", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig07_EA", "index": "13", "type": "numeric", "distinct": "353", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "14", "type": "numeric", "distinct": "353", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "HNar", "index": "15", "type": "numeric", "distinct": "219", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MW", "index": "16", "type": "numeric", "distinct": "521", "missing": "0", "min": "200", "max": "2661", "mean": "741", "stdev": "393" }, { "name": "Uindex", "index": "17", "type": "numeric", "distinct": "529", "missing": "0", "min": "24", "max": "579", "mean": "107", "stdev": "84" }, { "name": "CATS2D_03_DL", "index": "18", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "41", "mean": "9", "stdev": "7" }, { "name": "P_VSA_MR_5", "index": "19", "type": "numeric", "distinct": "427", "missing": "0", "min": "4", "max": "787", "mean": "184", "stdev": "151" }, { "name": "ZM1V", "index": "20", "type": "numeric", "distinct": "316", "missing": "0", "min": "122", "max": "2828", "mean": "710", "stdev": "428" }, { "name": "ATSC4s", "index": "21", "type": "numeric", "distinct": "616", "missing": "0", "min": "8", "max": "1103", "mean": "178", "stdev": "157" }, { "name": "IAC", "index": "22", "type": "numeric", "distinct": "513", "missing": "0", "min": "39", "max": "617", "mean": "163", "stdev": "93" }, { "name": "TIC0", "index": "23", "type": "numeric", "distinct": "513", "missing": "0", "min": "39", "max": "617", "mean": "163", "stdev": "93" }, { "name": "SpMax8_Bh.m.", "index": "24", "type": "numeric", "distinct": "432", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0sol", "index": "25", "type": "numeric", "distinct": "414", "missing": "0", "min": "11", "max": "139", "mean": "38", "stdev": "21" }, { "name": "CATS2D_09_AP", "index": "26", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "GMTIV", "index": "27", "type": "numeric", "distinct": "605", "missing": "0", "min": "3625", "max": "5674250", "mean": "258884", "stdev": "494343" }, { "name": "Eig15_EA.dm.", "index": "28", "type": "numeric", "distinct": "47", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig13_EA.dm.", "index": "29", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax7_Bh.m.", "index": "30", "type": "numeric", "distinct": "387", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CMC.80", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X0v", "index": "32", "type": "numeric", "distinct": "552", "missing": "0", "min": "9", "max": "105", "mean": "31", "stdev": "15" }, { "name": "MATS5s", "index": "33", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig12_EA.dm.", "index": "34", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC8m", "index": "35", "type": "numeric", "distinct": "613", "missing": "0", "min": "7", "max": "378", "mean": "93", "stdev": "64" }, { "name": "Eig09_EA.dm.", "index": "36", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.dm.", "index": "37", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig11_EA.dm.", "index": "38", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nN", "index": "39", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "34", "mean": "8", "stdev": "6" }, { "name": "Infective.80", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "UNIP", "index": "41", "type": "numeric", "distinct": "322", "missing": "0", "min": "40", "max": "3237", "mean": "367", "stdev": "387" }, { "name": "X2sol", "index": "42", "type": "numeric", "distinct": "521", "missing": "0", "min": "6", "max": "81", "mean": "23", "stdev": "12" }, { "name": "ON0", "index": "43", "type": "numeric", "distinct": "252", "missing": "0", "min": "8", "max": "107", "mean": "28", "stdev": "16" }, { "name": "NdO", "index": "44", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "5", "stdev": "5" }, { "name": "O.058", "index": "45", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "4", "stdev": "5" }, { "name": "X0A", "index": "46", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_L", "index": "47", "type": "numeric", "distinct": "589", "missing": "0", "min": "3", "max": "52", "mean": "14", "stdev": "8" }, { "name": "ATSC4e", "index": "48", "type": "numeric", "distinct": "514", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "ATS1m", "index": "49", "type": "numeric", "distinct": "455", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_betaS_A", "index": "50", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CSI", "index": "51", "type": "numeric", "distinct": "482", "missing": "0", "min": "240", "max": "19611", "mean": "2199", "stdev": "2493" }, { "name": "SAtot", "index": "52", "type": "numeric", "distinct": "568", "missing": "0", "min": "285", "max": "3658", "mean": "999", "stdev": "535" }, { "name": "DLS_01", "index": "53", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ZM2MulPer", "index": "54", "type": "numeric", "distinct": "598", "missing": "0", "min": "133", "max": "2596", "mean": "709", "stdev": "397" }, { "name": "VvdwZAZ", "index": "55", "type": "numeric", "distinct": "528", "missing": "0", "min": "196", "max": "2489", "mean": "697", "stdev": "366" }, { "name": "Psi_i_s", "index": "56", "type": "numeric", "distinct": "493", "missing": "0", "min": "30", "max": "525", "mean": "127", "stdev": "79" }, { "name": "SMTI", "index": "57", "type": "numeric", "distinct": "532", "missing": "0", "min": "1741", "max": "1755680", "mean": "89179", "stdev": "163614" }, { "name": "P_VSA_LogP_4", "index": "58", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "1119", "mean": "159", "stdev": "168" }, { "name": "MDDD", "index": "59", "type": "numeric", "distinct": "530", "missing": "0", "min": "10", "max": "821", "mean": "89", "stdev": "103" }, { "name": "NaaaC", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eta_C", "index": "61", "type": "numeric", "distinct": "616", "missing": "0", "min": "9", "max": "385", "mean": "74", "stdev": "56" }, { "name": "AMR", "index": "62", "type": "numeric", "distinct": "596", "missing": "0", "min": "64", "max": "665", "mean": "203", "stdev": "98" }, { "name": "ATS8p", "index": "63", "type": "numeric", "distinct": "527", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MSD", "index": "64", "type": "numeric", "distinct": "513", "missing": "0", "min": "4", "max": "29", "mean": "10", "stdev": "4" }, { "name": "ON0V", "index": "65", "type": "numeric", "distinct": "474", "missing": "0", "min": "5", "max": "60", "mean": "18", "stdev": "9" }, { "name": "CATS2D_05_AL", "index": "66", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "34", "mean": "11", "stdev": "5" }, { "name": "ATS2s", "index": "67", "type": "numeric", "distinct": "496", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "TIC1", "index": "68", "type": "numeric", "distinct": "573", "missing": "0", "min": "75", "max": "1373", "mean": "371", "stdev": "211" } ], "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 }