{ "data_id": "35205", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3728", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3728", "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: CHEMBL3728 (TID: 12879), and it has 267 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 17:24:45", "update_comment": null, "last_update": "2016-07-15 17:24:45", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3550938\/data_53251.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3728", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3728 (TID: 12879), and it has 267 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": 267, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.7143431055295575, "Dimensionality": 0.25842696629213485, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 1.682187265917603, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6667205026641918, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.075978764711525, "Quartile2SkewnessOfNumericAtts": 0.31892244945358195, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.32339938118151673, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8292241234114002, "MinMeansOfNumericAtts": -0.09394756554307117, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 22.239922420044163, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.251192088663703, "MaxMeansOfNumericAtts": 682.4194756554307, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 4.71244382022472, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -1.894249190363323, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.02492071231945593, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6323301161344523, "MaxSkewnessOfNumericAtts": 3.731792850542096, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.03457402486610062, "Quartile3StdDevOfNumericAtts": 2.093966089896325, "MaxStdDevOfNumericAtts": 255.93899809738352, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6457855805243445, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.695256590158469, "Quartile1SkewnessOfNumericAtts": -0.31097646716865196, "MeanMeansOfNumericAtts": 21.228053150473674, "Quartile1StdDevOfNumericAtts": 0.15154152096774035, "AutoCorrelation": 0.9069624060150375, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "38", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "267", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nIsoxazoles", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS1s", "index": "2", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1s", "index": "3", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "D.Dtr09", "index": "4", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "225", "mean": "29", "stdev": "56" }, { "name": "SpMin5_Bh.s.", "index": "5", "type": "numeric", "distinct": "178", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Yindex", "index": "6", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS5i", "index": "7", "type": "numeric", "distinct": "209", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NssCH2", "index": "8", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "nCrt", "index": "9", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "SsF", "index": "10", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "40", "mean": "3", "stdev": "7" }, { "name": "Vindex", "index": "11", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.003", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nCt", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "SssCH2", "index": "14", "type": "numeric", "distinct": "159", "missing": "0", "min": "-1", "max": "11", "mean": "1", "stdev": "2" }, { "name": "Xindex", "index": "15", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "16", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "F.084", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCsp3", "index": "18", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "3", "stdev": "3" }, { "name": "H.052", "index": "19", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "ATS3i", "index": "20", "type": "numeric", "distinct": "219", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "nCconj", "index": "21", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "nF", "index": "22", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "NsF", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_e_6", "index": "24", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "45", "mean": "3", "stdev": "8" }, { "name": "SpMax1_Bh.s.", "index": "25", "type": "numeric", "distinct": "43", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "0" }, { "name": "ICR", "index": "26", "type": "numeric", "distinct": "184", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "27", "type": "numeric", "distinct": "190", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "28", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nRCONR2", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "30", "type": "numeric", "distinct": "192", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS3e", "index": "31", "type": "numeric", "distinct": "227", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATSC3i", "index": "32", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CSI", "index": "33", "type": "numeric", "distinct": "214", "missing": "0", "min": "135", "max": "1440", "mean": "682", "stdev": "256" }, { "name": "Eta_L_A", "index": "34", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC1i", "index": "35", "type": "numeric", "distinct": "201", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "36", "type": "numeric", "distinct": "183", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "37", "type": "numeric", "distinct": "176", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_L", "index": "38", "type": "numeric", "distinct": "254", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "Eig01_EA.bo.", "index": "39", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "40", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "41", "type": "numeric", "distinct": "157", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "42", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ECC", "index": "43", "type": "numeric", "distinct": "180", "missing": "0", "min": "71", "max": "662", "mean": "320", "stdev": "116" }, { "name": "P_VSA_LogP_6", "index": "44", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "53", "mean": "9", "stdev": "11" }, { "name": "SpMin1_Bh.s.", "index": "45", "type": "numeric", "distinct": "163", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "46", "type": "numeric", "distinct": "184", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS6s", "index": "47", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "AECC", "index": "48", "type": "numeric", "distinct": "223", "missing": "0", "min": "5", "max": "17", "mean": "11", "stdev": "2" }, { "name": "SpDiam_EA.ri.", "index": "49", "type": "numeric", "distinct": "159", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC3v", "index": "50", "type": "numeric", "distinct": "257", "missing": "0", "min": "3", "max": "25", "mean": "9", "stdev": "4" }, { "name": "ATSC2i", "index": "51", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "HVcpx", "index": "52", "type": "numeric", "distinct": "208", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "D.Dtr06", "index": "53", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "641", "mean": "231", "stdev": "115" }, { "name": "Eta_betaS_A", "index": "54", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "55", "type": "numeric", "distinct": "158", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "56", "type": "numeric", "distinct": "158", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5v", "index": "57", "type": "numeric", "distinct": "265", "missing": "0", "min": "2", "max": "23", "mean": "9", "stdev": "4" }, { "name": "Eta_FL_A", "index": "58", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ON1V", "index": "59", "type": "numeric", "distinct": "223", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SaaO", "index": "60", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "3" }, { "name": "SpMin3_Bh.v.", "index": "61", "type": "numeric", "distinct": "181", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_beta_A", "index": "62", "type": "numeric", "distinct": "153", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC4v", "index": "63", "type": "numeric", "distinct": "266", "missing": "0", "min": "2", "max": "30", "mean": "9", "stdev": "4" }, { "name": "ATSC6v", "index": "64", "type": "numeric", "distinct": "263", "missing": "0", "min": "1", "max": "24", "mean": "8", "stdev": "4" }, { "name": "Chi1_EA.bo.", "index": "65", "type": "numeric", "distinct": "242", "missing": "0", "min": "5", "max": "20", "mean": "11", "stdev": "3" }, { "name": "GATS3i", "index": "66", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS4i", "index": "67", "type": "numeric", "distinct": "234", "missing": "0", "min": "4", "max": "6", "mean": "5", "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 }