{ "data_id": "38347", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741217", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741217", "version": 12, "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: CHEMBL1741217 (TID: 104013), and it has 1001 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 03:51:46", "update_comment": null, "last_update": "2016-07-16 03:51:46", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3637631\/data_53704.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1741217", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1741217 (TID: 104013), and it has 1001 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": 1001, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 14.140467659617556, "MinMeansOfNumericAtts": -0.0947962037962038, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7966466265461953, "MaxMeansOfNumericAtts": 174.4461058941059, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 6.888147852147852, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7529794299756011, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3SkewnessOfNumericAtts": 1.2489560777608328, "MaxSkewnessOfNumericAtts": 3.9392161202026985, "MinStdDevOfNumericAtts": 0.017567492001557168, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.8515836959621357, "MaxStdDevOfNumericAtts": 50.88311252137372, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.18965263315813896, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6503496503496505, "MeanKurtosisOfNumericAtts": 2.135485485351116, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 17.01461643989813, "Quartile1SkewnessOfNumericAtts": 0.2791316118095442, "AutoCorrelation": 0.49898799999999954, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2450790061118305, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.07192807192807193, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9939435228069575, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.8254315656208532, "Quartile2MeansOfNumericAtts": 2.1882587412587413, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.760967040764181, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.588054973608637, "Quartile2StdDevOfNumericAtts": 0.6597108877565803, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7568423010641705, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "621", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1001", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nN.", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "2", "type": "numeric", "distinct": "432", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SsSH", "index": "3", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "P_VSA_s_3", "index": "4", "type": "numeric", "distinct": "910", "missing": "0", "min": "3", "max": "156", "mean": "38", "stdev": "23" }, { "name": "Psi_e_A", "index": "5", "type": "numeric", "distinct": "596", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "6", "type": "numeric", "distinct": "596", "missing": "0", "min": "2", "max": "4", "mean": "2", "stdev": "0" }, { "name": "MATS1p", "index": "7", "type": "numeric", "distinct": "313", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NsSH", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "S.106", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "AMW", "index": "10", "type": "numeric", "distinct": "813", "missing": "0", "min": "5", "max": "15", "mean": "8", "stdev": "1" }, { "name": "MATS1m", "index": "11", "type": "numeric", "distinct": "290", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "12", "type": "numeric", "distinct": "635", "missing": "0", "min": "0", "max": "321", "mean": "89", "stdev": "37" }, { "name": "DELS", "index": "13", "type": "numeric", "distinct": "987", "missing": "0", "min": "2", "max": "82", "mean": "25", "stdev": "14" }, { "name": "SAacc", "index": "14", "type": "numeric", "distinct": "581", "missing": "0", "min": "0", "max": "326", "mean": "86", "stdev": "43" }, { "name": "GATS1m", "index": "15", "type": "numeric", "distinct": "428", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "16", "type": "numeric", "distinct": "709", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_02_PL", "index": "17", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "O.058", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "P_VSA_v_2", "index": "19", "type": "numeric", "distinct": "622", "missing": "0", "min": "0", "max": "328", "mean": "89", "stdev": "43" }, { "name": "SpMax4_Bh.s.", "index": "20", "type": "numeric", "distinct": "626", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "P_VSA_p_2", "index": "21", "type": "numeric", "distinct": "582", "missing": "0", "min": "0", "max": "328", "mean": "86", "stdev": "43" }, { "name": "N.079", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "N.072", "index": "23", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax3_Bh.s.", "index": "24", "type": "numeric", "distinct": "528", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "H.", "index": "25", "type": "numeric", "distinct": "237", "missing": "0", "min": "19", "max": "65", "mean": "42", "stdev": "7" }, { "name": "Eta_epsi_A", "index": "26", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaasN", "index": "27", "type": "numeric", "distinct": "294", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Mv", "index": "28", "type": "numeric", "distinct": "218", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SdO", "index": "29", "type": "numeric", "distinct": "632", "missing": "0", "min": "0", "max": "84", "mean": "15", "stdev": "15" }, { "name": "P_VSA_e_5", "index": "30", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "292", "mean": "47", "stdev": "39" }, { "name": "GATS2s", "index": "31", "type": "numeric", "distinct": "475", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "AAC", "index": "32", "type": "numeric", "distinct": "541", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "33", "type": "numeric", "distinct": "541", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MAXDN", "index": "34", "type": "numeric", "distinct": "813", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "ATSC3s", "index": "35", "type": "numeric", "distinct": "996", "missing": "0", "min": "7", "max": "278", "mean": "38", "stdev": "27" }, { "name": "P_VSA_m_3", "index": "36", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "292", "mean": "50", "stdev": "40" }, { "name": "NaasN", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig05_EA.ed.", "index": "38", "type": "numeric", "distinct": "840", "missing": "0", "min": "-2", "max": "9", "mean": "5", "stdev": "2" }, { "name": "SM14_AEA.dm.", "index": "39", "type": "numeric", "distinct": "840", "missing": "0", "min": "-2", "max": "9", "mean": "5", "stdev": "2" }, { "name": "SpMax1_Bh.s.", "index": "40", "type": "numeric", "distinct": "256", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "41", "type": "numeric", "distinct": "538", "missing": "0", "min": "0", "max": "305", "mean": "94", "stdev": "42" }, { "name": "SpDiam_AEA.dm.", "index": "42", "type": "numeric", "distinct": "489", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "C.040", "index": "43", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "44", "type": "numeric", "distinct": "418", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "1" }, { "name": "GATS1s", "index": "45", "type": "numeric", "distinct": "453", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nNq", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NssssN.", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SssssN.", "index": "48", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.dm.", "index": "49", "type": "numeric", "distinct": "477", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "50", "type": "numeric", "distinct": "477", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SdssC", "index": "51", "type": "numeric", "distinct": "572", "missing": "0", "min": "-6", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "52", "type": "numeric", "distinct": "721", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NdO", "index": "53", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "ZM2Mad", "index": "54", "type": "numeric", "distinct": "978", "missing": "0", "min": "41", "max": "367", "mean": "174", "stdev": "51" }, { "name": "Mp", "index": "55", "type": "numeric", "distinct": "210", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "56", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SIC0", "index": "57", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.", "index": "58", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "24", "mean": "5", "stdev": "4" }, { "name": "Me", "index": "59", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig07_AEA.dm.", "index": "60", "type": "numeric", "distinct": "718", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig05_AEA.ed.", "index": "61", "type": "numeric", "distinct": "714", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "nHAcc", "index": "62", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "2" }, { "name": "GATS1v", "index": "63", "type": "numeric", "distinct": "444", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "64", "type": "numeric", "distinct": "747", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MATS1v", "index": "65", "type": "numeric", "distinct": "197", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "66", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "ATS2m", "index": "67", "type": "numeric", "distinct": "629", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ZM1Mad", "index": "68", "type": "numeric", "distinct": "950", "missing": "0", "min": "40", "max": "337", "mean": "158", "stdev": "45" }, { "name": "BIC0", "index": "69", "type": "numeric", "distinct": "218", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC4s", "index": "70", "type": "numeric", "distinct": "998", "missing": "0", "min": "4", "max": "290", "mean": "54", "stdev": "41" } ], "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 }