{ "data_id": "38838", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741179", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741179", "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: CHEMBL1741179 (TID: 103975), and it has 826 rows and 70 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 05:41:39", "update_comment": null, "last_update": "2016-07-16 05:41:39", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3654409\/data_53633.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741179", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1741179 (TID: 103975), and it has 826 rows and 70 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": 826, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.840283877428401, "MinMeansOfNumericAtts": 0.038875302663438256, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.8621194057605814, "MaxMeansOfNumericAtts": 213.1521234866828, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 4.7221452784503635, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.781990082948121, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3SkewnessOfNumericAtts": 1.2122545978219905, "MaxSkewnessOfNumericAtts": 3.508578521429707, "MinStdDevOfNumericAtts": 0.049015252118101385, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 3.6816094572301923, "MaxStdDevOfNumericAtts": 83.30142654807321, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.16250494748705746, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6140653753026635, "MeanKurtosisOfNumericAtts": 1.2893608341473872, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 16.667170054223647, "Quartile1SkewnessOfNumericAtts": 0.3145390130942293, "AutoCorrelation": 0.325350303030303, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3378576926782504, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08716707021791767, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.6877376981980783, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6593036240353546, "Quartile2MeansOfNumericAtts": 1.5753559322033899, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.557374512569281, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.616476943452435, "Quartile2StdDevOfNumericAtts": 0.8731615172992828, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6825066129363493, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "336", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "826", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NsSH", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "S.106", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SsSH", "index": "3", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "nN.", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS1m", "index": "5", "type": "numeric", "distinct": "266", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_PL", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "nTriazoles", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nHM", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.044", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SaaN", "index": "11", "type": "numeric", "distinct": "378", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "5" }, { "name": "NaaN", "index": "12", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "N.075", "index": "13", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "N.079", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "15", "type": "numeric", "distinct": "448", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AMW", "index": "16", "type": "numeric", "distinct": "687", "missing": "0", "min": "5", "max": "15", "mean": "8", "stdev": "1" }, { "name": "SpMin5_Bh.m.", "index": "17", "type": "numeric", "distinct": "460", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1m", "index": "18", "type": "numeric", "distinct": "754", "missing": "0", "min": "1", "max": "21", "mean": "8", "stdev": "4" }, { "name": "GATS1i", "index": "19", "type": "numeric", "distinct": "506", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_01_AA", "index": "20", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "21", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "146", "mean": "30", "stdev": "26" }, { "name": "nNq", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NssssN.", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SssssN.", "index": "24", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS5i", "index": "25", "type": "numeric", "distinct": "657", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "O.058", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATSC6v", "index": "27", "type": "numeric", "distinct": "803", "missing": "0", "min": "1", "max": "36", "mean": "9", "stdev": "5" }, { "name": "CATS2D_03_PL", "index": "28", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "29", "type": "numeric", "distinct": "515", "missing": "0", "min": "0", "max": "321", "mean": "85", "stdev": "38" }, { "name": "SpMin8_Bh.m.", "index": "30", "type": "numeric", "distinct": "484", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS5e", "index": "31", "type": "numeric", "distinct": "647", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "32", "type": "numeric", "distinct": "162", "missing": "0", "min": "24", "max": "541", "mean": "213", "stdev": "79" }, { "name": "SpMin7_Bh.m.", "index": "33", "type": "numeric", "distinct": "463", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "34", "type": "numeric", "distinct": "228", "missing": "0", "min": "19", "max": "65", "mean": "43", "stdev": "8" }, { "name": "SpMin6_Bh.s.", "index": "35", "type": "numeric", "distinct": "407", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NdssC", "index": "36", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SpMAD_AEA.dm.", "index": "37", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "38", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "39", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "40", "type": "numeric", "distinct": "204", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "SM09_EA.dm.", "index": "41", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "16", "mean": "4", "stdev": "4" }, { "name": "SM11_EA.dm.", "index": "42", "type": "numeric", "distinct": "190", "missing": "0", "min": "0", "max": "19", "mean": "5", "stdev": "5" }, { "name": "SM13_EA.dm.", "index": "43", "type": "numeric", "distinct": "186", "missing": "0", "min": "0", "max": "23", "mean": "5", "stdev": "6" }, { "name": "SM15_EA.dm.", "index": "44", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "27", "mean": "6", "stdev": "7" }, { "name": "SpMax7_Bh.i.", "index": "45", "type": "numeric", "distinct": "486", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "46", "type": "numeric", "distinct": "452", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "47", "type": "numeric", "distinct": "424", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "48", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATSC7v", "index": "49", "type": "numeric", "distinct": "807", "missing": "0", "min": "0", "max": "32", "mean": "9", "stdev": "5" }, { "name": "ATSC1p", "index": "50", "type": "numeric", "distinct": "708", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "BIC0", "index": "51", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "52", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_LogP_2", "index": "53", "type": "numeric", "distinct": "327", "missing": "0", "min": "0", "max": "93", "mean": "16", "stdev": "16" }, { "name": "ATS7i", "index": "54", "type": "numeric", "distinct": "686", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS6e", "index": "55", "type": "numeric", "distinct": "674", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATSC4p", "index": "56", "type": "numeric", "distinct": "792", "missing": "0", "min": "1", "max": "22", "mean": "9", "stdev": "3" }, { "name": "P_VSA_i_1", "index": "57", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "129", "mean": "24", "stdev": "26" }, { "name": "ATSC4m", "index": "58", "type": "numeric", "distinct": "816", "missing": "0", "min": "2", "max": "65", "mean": "25", "stdev": "11" }, { "name": "NssNH", "index": "59", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SssNH", "index": "60", "type": "numeric", "distinct": "289", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "C.006", "index": "61", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "C.040", "index": "62", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Eta_epsi_A", "index": "63", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "64", "type": "numeric", "distinct": "239", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS7e", "index": "65", "type": "numeric", "distinct": "677", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "P_VSA_e_1", "index": "66", "type": "numeric", "distinct": "59", "missing": "0", "min": "34", "max": "541", "mean": "202", "stdev": "83" }, { "name": "P_VSA_m_1", "index": "67", "type": "numeric", "distinct": "57", "missing": "0", "min": "34", "max": "541", "mean": "202", "stdev": "83" }, { "name": "P_VSA_v_1", "index": "68", "type": "numeric", "distinct": "57", "missing": "0", "min": "34", "max": "541", "mean": "202", "stdev": "83" }, { "name": "ATS8i", "index": "69", "type": "numeric", "distinct": "684", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig02_EA.dm.", "index": "70", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" } ], "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 }