{ "data_id": "35395", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3081", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3081", "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: CHEMBL3081 (TID: 17058), and it has 305 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": "2016-07-15 17:55:35", "update_comment": null, "last_update": "2016-07-15 17:55:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3556548\/data_53030.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3081", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3081 (TID: 17058), and it has 305 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": 305, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 95.05502521573352, "MinMeansOfNumericAtts": -0.8510131147540982, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.735589847001513, "MaxMeansOfNumericAtts": 125.92167868852458, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 11.963245901639343, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.338873316001745, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3SkewnessOfNumericAtts": 0.7283894732191579, "MaxSkewnessOfNumericAtts": 7.459300999611182, "MinStdDevOfNumericAtts": 0.0023837646504094854, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.2716320986624143, "MaxStdDevOfNumericAtts": 76.28653415108445, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.0003913905311097, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9378852459016394, "MeanKurtosisOfNumericAtts": 2.5974720680063794, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.588289454367507, "Quartile1SkewnessOfNumericAtts": -0.16759264668034637, "AutoCorrelation": 0.020430921052631806, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.25435693636800233, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.22295081967213115, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.24149820854117543, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5090135588954795, "Quartile2MeansOfNumericAtts": 4.405540983606557, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.725112406376154, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.23899093144699335, "Quartile2StdDevOfNumericAtts": 0.610313961339887, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5835366310414014, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "150", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "305", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig05_EA.ed.", "index": "1", "type": "numeric", "distinct": "218", "missing": "0", "min": "1", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "2", "type": "numeric", "distinct": "218", "missing": "0", "min": "1", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SpMax5_Bh.s.", "index": "3", "type": "numeric", "distinct": "210", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "PCR", "index": "4", "type": "numeric", "distinct": "152", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "5", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "249", "mean": "92", "stdev": "39" }, { "name": "nCsp2", "index": "6", "type": "numeric", "distinct": "19", "missing": "0", "min": "2", "max": "24", "mean": "12", "stdev": "4" }, { "name": "SpMax7_Bh.s.", "index": "7", "type": "numeric", "distinct": "236", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "1" }, { "name": "C.039", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "JGI9", "index": "9", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCrt", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "11", "type": "numeric", "distinct": "232", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "12", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "357", "mean": "101", "stdev": "47" }, { "name": "SpMAD_EA.dm.", "index": "13", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "LLS_01", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "15", "type": "numeric", "distinct": "123", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "GATS2p", "index": "16", "type": "numeric", "distinct": "192", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Psi_i_t", "index": "17", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCt", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Mp", "index": "19", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "20", "type": "numeric", "distinct": "192", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "GGI7", "index": "21", "type": "numeric", "distinct": "145", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "D.Dtr06", "index": "22", "type": "numeric", "distinct": "214", "missing": "0", "min": "0", "max": "413", "mean": "126", "stdev": "76" }, { "name": "SpMaxA_EA.bo.", "index": "23", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4i", "index": "24", "type": "numeric", "distinct": "199", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "D.Dtr10", "index": "25", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "304", "mean": "57", "stdev": "53" }, { "name": "Eig09_AEA.bo.", "index": "26", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ATS7v", "index": "27", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "ATS8s", "index": "28", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "Eig01_EA.ri.", "index": "29", "type": "numeric", "distinct": "174", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "30", "type": "numeric", "distinct": "174", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "31", "type": "numeric", "distinct": "174", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "32", "type": "numeric", "distinct": "255", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "33", "type": "numeric", "distinct": "245", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "P_VSA_s_3", "index": "34", "type": "numeric", "distinct": "226", "missing": "0", "min": "12", "max": "77", "mean": "38", "stdev": "15" }, { "name": "ATSC8i", "index": "35", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATS4s", "index": "36", "type": "numeric", "distinct": "254", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "37", "type": "numeric", "distinct": "212", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM13_EA.ri.", "index": "38", "type": "numeric", "distinct": "266", "missing": "0", "min": "13", "max": "17", "mean": "16", "stdev": "1" }, { "name": "Eta_F", "index": "39", "type": "numeric", "distinct": "294", "missing": "0", "min": "6", "max": "46", "mean": "21", "stdev": "8" }, { "name": "ATSC1e", "index": "40", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM14_EA.ri.", "index": "41", "type": "numeric", "distinct": "271", "missing": "0", "min": "14", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "42", "type": "numeric", "distinct": "261", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "ATS1s", "index": "43", "type": "numeric", "distinct": "237", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS1p", "index": "44", "type": "numeric", "distinct": "213", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nDB", "index": "45", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "Xindex", "index": "46", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "47", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "16", "mean": "10", "stdev": "4" }, { "name": "DELS", "index": "48", "type": "numeric", "distinct": "293", "missing": "0", "min": "4", "max": "91", "mean": "35", "stdev": "16" }, { "name": "SM09_EA.ri.", "index": "49", "type": "numeric", "distinct": "255", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SM10_EA.ri.", "index": "50", "type": "numeric", "distinct": "273", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM11_EA.ri.", "index": "51", "type": "numeric", "distinct": "264", "missing": "0", "min": "11", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "52", "type": "numeric", "distinct": "260", "missing": "0", "min": "12", "max": "16", "mean": "15", "stdev": "1" }, { "name": "ATSC1s", "index": "53", "type": "numeric", "distinct": "268", "missing": "0", "min": "3", "max": "106", "mean": "21", "stdev": "18" }, { "name": "nCconj", "index": "54", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "JGI10", "index": "55", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8m", "index": "56", "type": "numeric", "distinct": "218", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SRW10", "index": "57", "type": "numeric", "distinct": "204", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "nHet", "index": "58", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "16", "mean": "6", "stdev": "2" }, { "name": "X1v", "index": "59", "type": "numeric", "distinct": "263", "missing": "0", "min": "4", "max": "13", "mean": "7", "stdev": "2" }, { "name": "Eig01_AEA.ri.", "index": "60", "type": "numeric", "distinct": "160", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "61", "type": "numeric", "distinct": "160", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MWC09", "index": "62", "type": "numeric", "distinct": "211", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "MWC10", "index": "63", "type": "numeric", "distinct": "204", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "TWC", "index": "64", "type": "numeric", "distinct": "208", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "MAXDN", "index": "65", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "66", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "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 }