{ "data_id": "32133", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4130", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4130", "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: CHEMBL4130 (TID: 12789), and it has 309 rows and 65 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 09:24:17", "update_comment": null, "last_update": "2016-07-15 09:24:17", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3471125\/data_53019.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4130", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4130 (TID: 12789), and it has 309 rows and 65 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": 309, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.2168284789644013, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.13478105247288652, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.106699575053621, "Quartile2MeansOfNumericAtts": 3.6922313915857607, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.940267875377533, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.0355720304895257, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1127747403004216, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.36384378889995345, "MaxKurtosisOfNumericAtts": 198.83537787220286, "MinMeansOfNumericAtts": -0.0776537216828479, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 320.2880809061489, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.046162282978406, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 9.513794498381877, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.1613530190507295, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 12.692571623990148, "MinStdDevOfNumericAtts": 0.02308917929418747, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.4043293705067454, "MaxStdDevOfNumericAtts": 155.70049311308887, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6205717090173309, "Quartile3StdDevOfNumericAtts": 1.0948615966477284, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 5.122393221897637, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.830700009806806, "Quartile1SkewnessOfNumericAtts": 0.30432410752908207, "AutoCorrelation": -0.35442857142857215, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1286628241796913 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "194", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "309", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM12_EA.ed.", "index": "1", "type": "numeric", "distinct": "179", "missing": "0", "min": "28", "max": "32", "mean": "30", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "2", "type": "numeric", "distinct": "177", "missing": "0", "min": "30", "max": "35", "mean": "32", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "3", "type": "numeric", "distinct": "176", "missing": "0", "min": "32", "max": "38", "mean": "34", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "4", "type": "numeric", "distinct": "173", "missing": "0", "min": "25", "max": "30", "mean": "27", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "5", "type": "numeric", "distinct": "173", "missing": "0", "min": "35", "max": "40", "mean": "37", "stdev": "1" }, { "name": "Eig02_EA", "index": "6", "type": "numeric", "distinct": "99", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.bo.", "index": "7", "type": "numeric", "distinct": "99", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA", "index": "8", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "9", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "10", "type": "numeric", "distinct": "82", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "11", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "12", "type": "numeric", "distinct": "144", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "13", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "14", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_02_AA", "index": "15", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "SpMax5_Bh.m.", "index": "16", "type": "numeric", "distinct": "155", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nHM", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "C.032", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nPyrimidines", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM10_AEA.ed.", "index": "20", "type": "numeric", "distinct": "175", "missing": "0", "min": "19", "max": "21", "mean": "20", "stdev": "0" }, { "name": "SM11_AEA.ed.", "index": "21", "type": "numeric", "distinct": "188", "missing": "0", "min": "21", "max": "23", "mean": "22", "stdev": "0" }, { "name": "C.027", "index": "22", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_09_DL", "index": "23", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "48", "mean": "9", "stdev": "10" }, { "name": "SaaN", "index": "24", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "22", "mean": "4", "stdev": "7" }, { "name": "ZM1Mad", "index": "25", "type": "numeric", "distinct": "257", "missing": "0", "min": "182", "max": "1053", "mean": "320", "stdev": "156" }, { "name": "P_VSA_MR_7", "index": "26", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "129", "mean": "24", "stdev": "38" }, { "name": "P_VSA_i_1", "index": "27", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "153", "mean": "10", "stdev": "29" }, { "name": "SpMax1_Bh.p.", "index": "28", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_AEA.dm.", "index": "29", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "30", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "H.049", "index": "31", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "32", "type": "numeric", "distinct": "198", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "N.075", "index": "33", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "NaaN", "index": "34", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "MAXDN", "index": "35", "type": "numeric", "distinct": "225", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nS", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "37", "type": "numeric", "distinct": "129", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "GATS2i", "index": "38", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM08_AEA.ed.", "index": "39", "type": "numeric", "distinct": "193", "missing": "0", "min": "16", "max": "18", "mean": "17", "stdev": "0" }, { "name": "ATS1m", "index": "40", "type": "numeric", "distinct": "200", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM07_EA", "index": "41", "type": "numeric", "distinct": "189", "missing": "0", "min": "9", "max": "10", "mean": "9", "stdev": "0" }, { "name": "MATS2i", "index": "42", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "43", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "44", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "piPC10", "index": "45", "type": "numeric", "distinct": "203", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "46", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "P_VSA_MR_8", "index": "47", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "184", "mean": "19", "stdev": "35" }, { "name": "SM08_EA", "index": "48", "type": "numeric", "distinct": "198", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "MATS8m", "index": "49", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM04_EA.ed.", "index": "50", "type": "numeric", "distinct": "205", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "MATS6s", "index": "51", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AAC", "index": "52", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "53", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "54", "type": "numeric", "distinct": "48", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig02_AEA.ed.", "index": "55", "type": "numeric", "distinct": "76", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "56", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "21", "mean": "4", "stdev": "4" }, { "name": "MATS8e", "index": "57", "type": "numeric", "distinct": "186", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.ed.", "index": "58", "type": "numeric", "distinct": "150", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SAdon", "index": "59", "type": "numeric", "distinct": "44", "missing": "0", "min": "16", "max": "801", "mean": "147", "stdev": "149" }, { "name": "C.029", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eta_sh_y", "index": "61", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1s", "index": "62", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.070", "index": "63", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nSO2N", "index": "64", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "65", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "1", "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 }