{ "data_id": "34749", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5409", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5409", "version": 10, "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: CHEMBL5409 (TID: 100857), and it has 319 rows and 65 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": "2016-07-15 16:11:19", "update_comment": null, "last_update": "2016-07-15 16:11:19", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3537739\/data_52736.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5409", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5409 (TID: 100857), and it has 319 rows and 65 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": 319, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -1.24709096561588, "Dimensionality": 0.21003134796238246, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 2.0968275862068966, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.41494552655912237, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.538208060077047, "Quartile2SkewnessOfNumericAtts": 0.2652224060192718, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.2604341518567866, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8616155861446848, "MinMeansOfNumericAtts": -0.02408777429467086, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 7.493659113203881, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.7138781047896656, "MaxMeansOfNumericAtts": 304.5427398119122, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 5.561478840125392, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -0.32053033609147275, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.012701503357309104, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6347492171280947, "MaxSkewnessOfNumericAtts": 3.073550948053034, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.5943964099480568, "Quartile3StdDevOfNumericAtts": 3.258103041745553, "MaxStdDevOfNumericAtts": 141.60393516999105, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6762147335423198, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": -0.8589338648179786, "Quartile1SkewnessOfNumericAtts": 0.030927175457476412, "MeanMeansOfNumericAtts": 10.68706155599886, "Quartile1StdDevOfNumericAtts": 0.07510397995241233, "AutoCorrelation": 0.17845283018867922, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "204", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "319", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpDiam_AEA.bo.", "index": "1", "type": "numeric", "distinct": "114", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "2", "type": "numeric", "distinct": "116", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_F_A", "index": "3", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X5Av", "index": "4", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AL", "index": "5", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "6", "stdev": "4" }, { "name": "SpDiam_AEA.ed.", "index": "6", "type": "numeric", "distinct": "148", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "BLI", "index": "7", "type": "numeric", "distinct": "174", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1Av", "index": "8", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1i", "index": "9", "type": "numeric", "distinct": "162", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "10", "type": "numeric", "distinct": "131", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS1v", "index": "11", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3Av", "index": "12", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4Av", "index": "13", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1s", "index": "14", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ri.", "index": "15", "type": "numeric", "distinct": "165", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eta_betaS_A", "index": "16", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "17", "type": "numeric", "distinct": "102", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "18", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "19", "type": "numeric", "distinct": "86", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "N.", "index": "20", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "SpMin1_Bh.e.", "index": "21", "type": "numeric", "distinct": "99", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X2Av", "index": "22", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "23", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_epsi_A", "index": "24", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RCI", "index": "25", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "26", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1p", "index": "27", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "28", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "PCR", "index": "29", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "30", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "3" }, { "name": "Eta_L_A", "index": "31", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "32", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "58", "mean": "24", "stdev": "17" }, { "name": "X.", "index": "33", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "SpMin6_Bh.i.", "index": "34", "type": "numeric", "distinct": "160", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "35", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.s.", "index": "36", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Me", "index": "37", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "38", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "ATSC6m", "index": "39", "type": "numeric", "distinct": "289", "missing": "0", "min": "10", "max": "110", "mean": "49", "stdev": "28" }, { "name": "CATS2D_02_DL", "index": "40", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "CATS2D_04_DL", "index": "41", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "4" }, { "name": "H.", "index": "42", "type": "numeric", "distinct": "105", "missing": "0", "min": "31", "max": "62", "mean": "48", "stdev": "9" }, { "name": "ATSC3m", "index": "43", "type": "numeric", "distinct": "271", "missing": "0", "min": "14", "max": "76", "mean": "39", "stdev": "19" }, { "name": "ATS6i", "index": "44", "type": "numeric", "distinct": "262", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "nCrs", "index": "45", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "5" }, { "name": "SpMAD_EA.ri.", "index": "46", "type": "numeric", "distinct": "162", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NaasC", "index": "47", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "3" }, { "name": "GATS1v", "index": "48", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "49", "type": "numeric", "distinct": "51", "missing": "0", "min": "129", "max": "636", "mean": "305", "stdev": "142" }, { "name": "SsOH", "index": "50", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "43", "mean": "10", "stdev": "13" }, { "name": "nCb.", "index": "51", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "CATS2D_01_LL", "index": "52", "type": "numeric", "distinct": "30", "missing": "0", "min": "2", "max": "37", "mean": "15", "stdev": "10" }, { "name": "CATS2D_05_DL", "index": "53", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "4" }, { "name": "ATSC2p", "index": "54", "type": "numeric", "distinct": "231", "missing": "0", "min": "4", "max": "21", "mean": "11", "stdev": "5" }, { "name": "P_VSA_MR_7", "index": "55", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "137", "mean": "41", "stdev": "43" }, { "name": "Eig01_AEA.bo.", "index": "56", "type": "numeric", "distinct": "96", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "57", "type": "numeric", "distinct": "96", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "CATS2D_03_LL", "index": "58", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "72", "mean": "27", "stdev": "23" }, { "name": "piPC07", "index": "59", "type": "numeric", "distinct": "196", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC3p", "index": "60", "type": "numeric", "distinct": "268", "missing": "0", "min": "6", "max": "31", "mean": "16", "stdev": "8" }, { "name": "PCD", "index": "61", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "2" }, { "name": "SpMAD_EA", "index": "62", "type": "numeric", "distinct": "112", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "N.071", "index": "63", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArNR2", "index": "64", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.004", "index": "65", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" } ], "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 }