{ "data_id": "31413", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2731", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2731", "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: CHEMBL2731 (TID: 12886), and it has 81 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 07:31:01", "update_comment": null, "last_update": "2016-07-15 07:31:01", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3448471\/data_53256.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2731", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2731 (TID: 12886), and it has 81 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": 81, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 55.43110013520961, "MinMeansOfNumericAtts": 0.034716049382716045, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 13.719795001495475, "MaxMeansOfNumericAtts": 773.7414814814815, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 23.44421913580247, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.0104250436989584, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3SkewnessOfNumericAtts": 3.273407979256235, "MaxSkewnessOfNumericAtts": 6.99725853032517, "MinStdDevOfNumericAtts": 0.16475922668481358, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 21.65858464678881, "MaxStdDevOfNumericAtts": 639.5652520916739, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7681520849247899, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.727861111111111, "MeanKurtosisOfNumericAtts": 6.279956196418336, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 71.50636782861292, "Quartile1SkewnessOfNumericAtts": -0.30817608339272456, "AutoCorrelation": 0.4467500000000001, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.7740197945577815, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.8518518518518519, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.80220166324112, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.284399934402075, "Quartile2MeansOfNumericAtts": 5.592049382716049, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 65.46382162007848, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5199150781574591, "Quartile2StdDevOfNumericAtts": 2.29132850238889, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9386940589076176, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "37", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "81", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nRCONR2", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nArC.N", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "3", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "C.024", "index": "4", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "18", "mean": "7", "stdev": "5" }, { "name": "nCbH", "index": "5", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "18", "mean": "7", "stdev": "5" }, { "name": "SdsN", "index": "6", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "C.039", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NdsN", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NaaCH", "index": "9", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "5" }, { "name": "nBnz", "index": "10", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMin3_Bh.e.", "index": "11", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "12", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "13", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "125", "mean": "30", "stdev": "22" }, { "name": "CATS2D_05_AL", "index": "14", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "28", "mean": "8", "stdev": "6" }, { "name": "SpMax3_Bh.s.", "index": "15", "type": "numeric", "distinct": "49", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "MAXDN", "index": "16", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "nCsp2", "index": "17", "type": "numeric", "distinct": "21", "missing": "0", "min": "2", "max": "60", "mean": "16", "stdev": "9" }, { "name": "ATSC2e", "index": "18", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nCar", "index": "19", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "26", "mean": "12", "stdev": "6" }, { "name": "ATS2s", "index": "20", "type": "numeric", "distinct": "76", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMax7_Bh.s.", "index": "21", "type": "numeric", "distinct": "62", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "1" }, { "name": "CATS2D_08_LL", "index": "22", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "36", "mean": "8", "stdev": "8" }, { "name": "SpMin3_Bh.m.", "index": "23", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM05_EA.dm.", "index": "24", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "3" }, { "name": "SM07_EA.dm.", "index": "25", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "4" }, { "name": "P_VSA_i_2", "index": "26", "type": "numeric", "distinct": "70", "missing": "0", "min": "17", "max": "528", "mean": "134", "stdev": "85" }, { "name": "MLOGP2", "index": "27", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "299", "mean": "17", "stdev": "35" }, { "name": "D.Dtr09", "index": "28", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "1625", "mean": "118", "stdev": "257" }, { "name": "CATS2D_07_LL", "index": "29", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "29", "mean": "9", "stdev": "7" }, { "name": "Eig06_EA.dm.", "index": "30", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "31", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "32", "type": "numeric", "distinct": "63", "missing": "0", "min": "5", "max": "314", "mean": "103", "stdev": "62" }, { "name": "MATS8s", "index": "33", "type": "numeric", "distinct": "74", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ZM1Kup", "index": "34", "type": "numeric", "distinct": "71", "missing": "0", "min": "154", "max": "3828", "mean": "614", "stdev": "546" }, { "name": "SM09_EA.dm.", "index": "35", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "5" }, { "name": "CATS2D_06_LL", "index": "36", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "25", "mean": "8", "stdev": "6" }, { "name": "Eta_beta", "index": "37", "type": "numeric", "distinct": "57", "missing": "0", "min": "9", "max": "221", "mean": "40", "stdev": "31" }, { "name": "Eta_F", "index": "38", "type": "numeric", "distinct": "79", "missing": "0", "min": "5", "max": "438", "mean": "40", "stdev": "63" }, { "name": "Eta_FL", "index": "39", "type": "numeric", "distinct": "73", "missing": "0", "min": "2", "max": "45", "mean": "8", "stdev": "6" }, { "name": "SpMax4_Bh.i.", "index": "40", "type": "numeric", "distinct": "70", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig07_EA", "index": "41", "type": "numeric", "distinct": "62", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM15_AEA.bo.", "index": "42", "type": "numeric", "distinct": "62", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ATSC8s", "index": "43", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "2574", "mean": "171", "stdev": "383" }, { "name": "ATSC2i", "index": "44", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "45", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "174", "mean": "26", "stdev": "31" }, { "name": "P_VSA_s_4", "index": "46", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "294", "mean": "93", "stdev": "55" }, { "name": "MAXDP", "index": "47", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "2" }, { "name": "SpMax3_Bh.v.", "index": "48", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI3", "index": "49", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "2" }, { "name": "ATS8s", "index": "50", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "9", "mean": "6", "stdev": "1" }, { "name": "Psi_i_s", "index": "51", "type": "numeric", "distinct": "69", "missing": "0", "min": "23", "max": "615", "mean": "87", "stdev": "88" }, { "name": "ZM1MulPer", "index": "52", "type": "numeric", "distinct": "78", "missing": "0", "min": "136", "max": "3579", "mean": "572", "stdev": "504" }, { "name": "ZM1Per", "index": "53", "type": "numeric", "distinct": "77", "missing": "0", "min": "176", "max": "4548", "mean": "752", "stdev": "640" }, { "name": "ZM1V", "index": "54", "type": "numeric", "distinct": "66", "missing": "0", "min": "128", "max": "3282", "mean": "529", "stdev": "462" }, { "name": "ZM2Kup", "index": "55", "type": "numeric", "distinct": "73", "missing": "0", "min": "116", "max": "3036", "mean": "521", "stdev": "428" }, { "name": "ZM2Per", "index": "56", "type": "numeric", "distinct": "79", "missing": "0", "min": "169", "max": "4340", "mean": "774", "stdev": "610" }, { "name": "Eta_betaP", "index": "57", "type": "numeric", "distinct": "36", "missing": "0", "min": "1", "max": "80", "mean": "19", "stdev": "12" }, { "name": "SaaCH", "index": "58", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "31", "mean": "12", "stdev": "8" }, { "name": "SpMin3_Bh.v.", "index": "59", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.026", "index": "60", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "2" }, { "name": "Chi0_EA.dm.", "index": "61", "type": "numeric", "distinct": "69", "missing": "0", "min": "2", "max": "142", "mean": "25", "stdev": "21" }, { "name": "Eig10_AEA.ri.", "index": "62", "type": "numeric", "distinct": "68", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig10_EA.bo.", "index": "63", "type": "numeric", "distinct": "62", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "64", "type": "numeric", "distinct": "65", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "65", "type": "numeric", "distinct": "70", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "66", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "2" }, { "name": "nCb.", "index": "67", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "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 }