{ "data_id": "34059", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1900", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1900", "version": 9, "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: CHEMBL1900 (TID: 242), and it has 671 rows and 67 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 14:23:21", "update_comment": null, "last_update": "2016-07-15 14:23:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3520375\/data_53239.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1900", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1900 (TID: 242), and it has 671 rows and 67 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": 671, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.10283159463487332, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.0985955975070767, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.4993702030609429, "Quartile2MeansOfNumericAtts": 3.1895417287630403, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.510053837348705, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.664234951049482, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.417113283592418, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8135982578651393, "MaxKurtosisOfNumericAtts": 44.673776252335024, "MinMeansOfNumericAtts": 0.1727645305514158, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 483.36217585693, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.916133429648342, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 14.172932935916542, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5108162683116209, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.614300992928996, "MinStdDevOfNumericAtts": 0.05831794987269277, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.2773575932835204, "MaxStdDevOfNumericAtts": 145.90531824503176, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.13076047086478548, "Quartile3StdDevOfNumericAtts": 1.5787568625667767, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5380029806259312, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.8808094272976743, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 28.179187691768213, "Quartile1SkewnessOfNumericAtts": -0.5469353629828329, "AutoCorrelation": -0.14172388059701602, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.47539919996622215 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "351", "missing": "0", "target": "1", "min": "1", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "671", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.043", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SaaN", "index": "2", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "nThiazoles", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "N.075", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.", "index": "6", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "19", "mean": "6", "stdev": "4" }, { "name": "C.028", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SaaS", "index": "8", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "P_VSA_i_4", "index": "9", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "127", "mean": "36", "stdev": "28" }, { "name": "NaaS", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "11", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "P_VSA_m_4", "index": "12", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "235", "mean": "25", "stdev": "29" }, { "name": "P_VSA_e_3", "index": "13", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "322", "mean": "32", "stdev": "35" }, { "name": "SM02_EA.dm.", "index": "14", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "IC2", "index": "15", "type": "numeric", "distinct": "362", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_07_AN", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "17", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "1" }, { "name": "Eig01_EA.dm.", "index": "18", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "19", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpAD_EA.dm.", "index": "20", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "28", "mean": "10", "stdev": "5" }, { "name": "C.034", "index": "21", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "IC1", "index": "22", "type": "numeric", "distinct": "364", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "23", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nR09", "index": "24", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nS", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "26", "type": "numeric", "distinct": "416", "missing": "0", "min": "11", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "27", "type": "numeric", "distinct": "425", "missing": "0", "min": "9", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM11_EA.bo.", "index": "28", "type": "numeric", "distinct": "424", "missing": "0", "min": "10", "max": "18", "mean": "17", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "29", "type": "numeric", "distinct": "426", "missing": "0", "min": "12", "max": "21", "mean": "19", "stdev": "1" }, { "name": "D.Dtr05", "index": "30", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "159", "mean": "38", "stdev": "35" }, { "name": "SM09_AEA.ed.", "index": "31", "type": "numeric", "distinct": "390", "missing": "0", "min": "14", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM09_EA", "index": "32", "type": "numeric", "distinct": "380", "missing": "0", "min": "7", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "33", "type": "numeric", "distinct": "425", "missing": "0", "min": "13", "max": "23", "mean": "21", "stdev": "1" }, { "name": "ZM1Kup", "index": "34", "type": "numeric", "distinct": "491", "missing": "0", "min": "114", "max": "1048", "mean": "483", "stdev": "146" }, { "name": "PDI", "index": "35", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "S.107", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SM10_AEA.ed.", "index": "37", "type": "numeric", "distinct": "393", "missing": "0", "min": "15", "max": "22", "mean": "20", "stdev": "1" }, { "name": "MAXDN", "index": "38", "type": "numeric", "distinct": "491", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "P_VSA_s_3", "index": "39", "type": "numeric", "distinct": "424", "missing": "0", "min": "0", "max": "92", "mean": "37", "stdev": "20" }, { "name": "SM15_EA.bo.", "index": "40", "type": "numeric", "distinct": "423", "missing": "0", "min": "13", "max": "25", "mean": "22", "stdev": "1" }, { "name": "SIC1", "index": "41", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "DBI", "index": "42", "type": "numeric", "distinct": "51", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "CATS2D_07_AA", "index": "43", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_AA", "index": "44", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_AA", "index": "45", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.s.", "index": "46", "type": "numeric", "distinct": "293", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "NaaaC", "index": "47", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig10_EA.bo.", "index": "48", "type": "numeric", "distinct": "380", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SdsN", "index": "49", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "SpMax1_Bh.i.", "index": "50", "type": "numeric", "distinct": "214", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC3s", "index": "51", "type": "numeric", "distinct": "640", "missing": "0", "min": "17", "max": "267", "mean": "87", "stdev": "45" }, { "name": "SsF", "index": "52", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "80", "mean": "9", "stdev": "15" }, { "name": "CATS2D_04_AA", "index": "53", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_AN", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_AEA.dm.", "index": "55", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nHAcc", "index": "56", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "13", "mean": "6", "stdev": "2" }, { "name": "ZM1V", "index": "57", "type": "numeric", "distinct": "200", "missing": "0", "min": "94", "max": "800", "mean": "431", "stdev": "115" }, { "name": "NdsN", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ZM1MulPer", "index": "59", "type": "numeric", "distinct": "528", "missing": "0", "min": "105", "max": "872", "mean": "468", "stdev": "124" }, { "name": "GGI1", "index": "60", "type": "numeric", "distinct": "25", "missing": "0", "min": "2", "max": "14", "mean": "6", "stdev": "2" }, { "name": "CATS2D_06_AN", "index": "61", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nHet", "index": "62", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "14", "mean": "7", "stdev": "2" }, { "name": "SIC2", "index": "63", "type": "numeric", "distinct": "194", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_AEA.dm.", "index": "64", "type": "numeric", "distinct": "297", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "65", "type": "numeric", "distinct": "233", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "66", "type": "numeric", "distinct": "366", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "Vindex", "index": "67", "type": "numeric", "distinct": "214", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" } ], "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 }