{ "data_id": "35691", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4588", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4588", "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: CHEMBL4588 (TID: 11110), and it has 969 rows and 69 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 18:44:08", "update_comment": null, "last_update": "2016-07-15 18:44:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3565738\/data_53575.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4588", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4588 (TID: 11110), and it has 969 rows and 69 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": 969, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.07327141382868937, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 4.965832413594843, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.20728899996427186, "Quartile2MeansOfNumericAtts": 6.050703302373581, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 530.559855000825, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.06418479334275518, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6799337835688926, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8833405419306593, "MaxKurtosisOfNumericAtts": 36.355051222199315, "MinMeansOfNumericAtts": 1.2028152734778121, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 28483.971104231143, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 10.493302540304597, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 35.398351393188854, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.628759554906763, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.247624775034376, "MinStdDevOfNumericAtts": 0.18224241775094108, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.3243816345613841, "MaxStdDevOfNumericAtts": 35591.341972944945, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 2.798573098311616, "Quartile3StdDevOfNumericAtts": 15.74267337722964, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.412986068111455, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 7.43464202948741, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 464.08021015774705, "Quartile1SkewnessOfNumericAtts": -2.0542429071236277, "AutoCorrelation": -0.3285444214876021, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3462103122622779 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "369", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "969", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC5s", "index": "1", "type": "numeric", "distinct": "861", "missing": "0", "min": "4", "max": "1315", "mean": "206", "stdev": "111" }, { "name": "ATS1m", "index": "2", "type": "numeric", "distinct": "548", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "3", "type": "numeric", "distinct": "356", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4m", "index": "4", "type": "numeric", "distinct": "616", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2s", "index": "5", "type": "numeric", "distinct": "569", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SAtot", "index": "6", "type": "numeric", "distinct": "788", "missing": "0", "min": "148", "max": "1811", "mean": "574", "stdev": "172" }, { "name": "X1v", "index": "7", "type": "numeric", "distinct": "785", "missing": "0", "min": "3", "max": "30", "mean": "11", "stdev": "3" }, { "name": "DELS", "index": "8", "type": "numeric", "distinct": "855", "missing": "0", "min": "13", "max": "237", "mean": "56", "stdev": "22" }, { "name": "SpMax4_Bh.v.", "index": "9", "type": "numeric", "distinct": "445", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "10", "type": "numeric", "distinct": "440", "missing": "0", "min": "1", "max": "8", "mean": "5", "stdev": "1" }, { "name": "VAR", "index": "11", "type": "numeric", "distinct": "259", "missing": "0", "min": "6", "max": "873", "mean": "155", "stdev": "104" }, { "name": "ATSC5e", "index": "12", "type": "numeric", "distinct": "693", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.e.", "index": "13", "type": "numeric", "distinct": "405", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X2sol", "index": "14", "type": "numeric", "distinct": "743", "missing": "0", "min": "4", "max": "36", "mean": "14", "stdev": "4" }, { "name": "Eig13_AEA.ed.", "index": "15", "type": "numeric", "distinct": "428", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Psi_e_1", "index": "16", "type": "numeric", "distinct": "770", "missing": "0", "min": "1", "max": "18", "mean": "6", "stdev": "2" }, { "name": "ZM2Mad", "index": "17", "type": "numeric", "distinct": "830", "missing": "0", "min": "63", "max": "536", "mean": "245", "stdev": "75" }, { "name": "SM04_EA", "index": "18", "type": "numeric", "distinct": "296", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Psi_i_s", "index": "19", "type": "numeric", "distinct": "579", "missing": "0", "min": "25", "max": "219", "mean": "84", "stdev": "24" }, { "name": "VvdwMG", "index": "20", "type": "numeric", "distinct": "705", "missing": "0", "min": "50", "max": "636", "mean": "222", "stdev": "68" }, { "name": "Vx", "index": "21", "type": "numeric", "distinct": "705", "missing": "0", "min": "114", "max": "1545", "mean": "534", "stdev": "165" }, { "name": "GGI1", "index": "22", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "22", "mean": "8", "stdev": "2" }, { "name": "SpMax4_Bh.p.", "index": "23", "type": "numeric", "distinct": "442", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "24", "type": "numeric", "distinct": "406", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "25", "type": "numeric", "distinct": "516", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "MDDD", "index": "26", "type": "numeric", "distinct": "731", "missing": "0", "min": "2", "max": "205", "mean": "35", "stdev": "23" }, { "name": "X0sol", "index": "27", "type": "numeric", "distinct": "570", "missing": "0", "min": "5", "max": "63", "mean": "23", "stdev": "7" }, { "name": "VvdwZAZ", "index": "28", "type": "numeric", "distinct": "721", "missing": "0", "min": "82", "max": "1179", "mean": "396", "stdev": "122" }, { "name": "SpMax3_Bh.i.", "index": "29", "type": "numeric", "distinct": "351", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X5v", "index": "30", "type": "numeric", "distinct": "773", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "1" }, { "name": "SpMax4_Bh.i.", "index": "31", "type": "numeric", "distinct": "420", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.ed.", "index": "32", "type": "numeric", "distinct": "412", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "33", "type": "numeric", "distinct": "464", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "34", "type": "numeric", "distinct": "469", "missing": "0", "min": "-1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin5_Bh.e.", "index": "35", "type": "numeric", "distinct": "469", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Psi_e_0", "index": "36", "type": "numeric", "distinct": "813", "missing": "0", "min": "2", "max": "32", "mean": "12", "stdev": "4" }, { "name": "SMTIV", "index": "37", "type": "numeric", "distinct": "810", "missing": "0", "min": "380", "max": "421930", "mean": "28484", "stdev": "35591" }, { "name": "Eig14_AEA.ed.", "index": "38", "type": "numeric", "distinct": "452", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMax3_Bh.p.", "index": "39", "type": "numeric", "distinct": "406", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ISIZ", "index": "40", "type": "numeric", "distinct": "101", "missing": "0", "min": "38", "max": "1331", "mean": "324", "stdev": "139" }, { "name": "nAT", "index": "41", "type": "numeric", "distinct": "101", "missing": "0", "min": "11", "max": "178", "mean": "55", "stdev": "19" }, { "name": "IDDM", "index": "42", "type": "numeric", "distinct": "359", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "nSK", "index": "43", "type": "numeric", "distinct": "67", "missing": "0", "min": "6", "max": "83", "mean": "31", "stdev": "10" }, { "name": "SpMin4_Bh.i.", "index": "44", "type": "numeric", "distinct": "422", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.p.", "index": "45", "type": "numeric", "distinct": "487", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "46", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Sv", "index": "47", "type": "numeric", "distinct": "721", "missing": "0", "min": "6", "max": "101", "mean": "35", "stdev": "11" }, { "name": "SpMax8_Bh.e.", "index": "48", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X1sol", "index": "49", "type": "numeric", "distinct": "684", "missing": "0", "min": "3", "max": "40", "mean": "15", "stdev": "5" }, { "name": "Eig11_AEA.ed.", "index": "50", "type": "numeric", "distinct": "461", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Psi_i_0", "index": "51", "type": "numeric", "distinct": "766", "missing": "0", "min": "4", "max": "59", "mean": "21", "stdev": "7" }, { "name": "Eig03_EA", "index": "52", "type": "numeric", "distinct": "427", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "53", "type": "numeric", "distinct": "427", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Pol", "index": "54", "type": "numeric", "distinct": "97", "missing": "0", "min": "3", "max": "143", "mean": "49", "stdev": "17" }, { "name": "BID", "index": "55", "type": "numeric", "distinct": "149", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM02_AEA.ed.", "index": "56", "type": "numeric", "distinct": "245", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "X5sol", "index": "57", "type": "numeric", "distinct": "736", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "3" }, { "name": "SM04_AEA.bo.", "index": "58", "type": "numeric", "distinct": "527", "missing": "0", "min": "6", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Psi_i_1", "index": "59", "type": "numeric", "distinct": "810", "missing": "0", "min": "2", "max": "50", "mean": "17", "stdev": "6" }, { "name": "SpAD_EA.ri.", "index": "60", "type": "numeric", "distinct": "851", "missing": "0", "min": "7", "max": "127", "mean": "47", "stdev": "15" }, { "name": "ZM1Mad", "index": "61", "type": "numeric", "distinct": "796", "missing": "0", "min": "62", "max": "463", "mean": "216", "stdev": "65" }, { "name": "Eig04_AEA.ed.", "index": "62", "type": "numeric", "distinct": "467", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "1" }, { "name": "Eig15_AEA.ed.", "index": "63", "type": "numeric", "distinct": "435", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig12_AEA.ed.", "index": "64", "type": "numeric", "distinct": "439", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin4_Bh.e.", "index": "65", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "S2K", "index": "66", "type": "numeric", "distinct": "713", "missing": "0", "min": "2", "max": "36", "mean": "10", "stdev": "4" }, { "name": "SpMax3_Bh.m.", "index": "67", "type": "numeric", "distinct": "395", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ECC", "index": "68", "type": "numeric", "distinct": "436", "missing": "0", "min": "16", "max": "3184", "mean": "406", "stdev": "302" }, { "name": "ATSC7m", "index": "69", "type": "numeric", "distinct": "846", "missing": "0", "min": "0", "max": "172", "mean": "36", "stdev": "20" } ], "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 }