{ "data_id": "33486", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5658", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5658", "version": 8, "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: CHEMBL5658 (TID: 101277), and it has 452 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 12:54:13", "update_comment": null, "last_update": "2016-07-15 12:54:13", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3506470\/data_53179.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5658", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5658 (TID: 101277), and it has 452 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": 452, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MeanKurtosisOfNumericAtts": 1.0623201288846715, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.31090008459136, "Quartile1SkewnessOfNumericAtts": -0.09999563057131974, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2990389531057069, "AutoCorrelation": 0.3208558758314854, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.0352571248625686, "Dimensionality": 0.15265486725663716, "MeanSkewnessOfNumericAtts": 0.36225727848940026, "Quartile2MeansOfNumericAtts": 4.568752212389381, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 4.982346098828213, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.04043471809349469, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2450519415798698, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4105923878305076, "MaxKurtosisOfNumericAtts": 14.255519467104824, "MinMeansOfNumericAtts": -0.5450110619469026, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 205.24759955752214, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9208300234416331, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 7.678316924778761, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3828491442046462, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.9263985564429933, "MinStdDevOfNumericAtts": 0.023868272769295686, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5490559735901214, "MaxStdDevOfNumericAtts": 77.74353948723036, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.41520051094913435, "Quartile3StdDevOfNumericAtts": 0.9215401616683391, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.232867256637168, "StdvNominalAttDistinctValues": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "258", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "452", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MPC07", "index": "1", "type": "numeric", "distinct": "164", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "StN", "index": "2", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "28", "mean": "1", "stdev": "4" }, { "name": "MPC08", "index": "3", "type": "numeric", "distinct": "189", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MPC10", "index": "4", "type": "numeric", "distinct": "211", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "piPC09", "index": "5", "type": "numeric", "distinct": "351", "missing": "0", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "Qindex", "index": "6", "type": "numeric", "distinct": "30", "missing": "0", "min": "10", "max": "39", "mean": "22", "stdev": "6" }, { "name": "MPC09", "index": "7", "type": "numeric", "distinct": "207", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "nCIR", "index": "8", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "15", "mean": "5", "stdev": "3" }, { "name": "MPC06", "index": "9", "type": "numeric", "distinct": "145", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "10", "type": "numeric", "distinct": "289", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TPC", "index": "11", "type": "numeric", "distinct": "292", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "piPC08", "index": "12", "type": "numeric", "distinct": "348", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "13", "type": "numeric", "distinct": "199", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "14", "type": "numeric", "distinct": "323", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "15", "type": "numeric", "distinct": "207", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nArCN", "index": "16", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NtN", "index": "17", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "MWC10", "index": "18", "type": "numeric", "distinct": "321", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "MWC09", "index": "19", "type": "numeric", "distinct": "316", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "TWC", "index": "20", "type": "numeric", "distinct": "322", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "21", "type": "numeric", "distinct": "176", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "D.Dtr09", "index": "22", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "343", "mean": "42", "stdev": "61" }, { "name": "SpMaxA_AEA.dm.", "index": "23", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5v", "index": "24", "type": "numeric", "distinct": "401", "missing": "0", "min": "1", "max": "9", "mean": "3", "stdev": "1" }, { "name": "Eig09_AEA.ed.", "index": "25", "type": "numeric", "distinct": "285", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "26", "type": "numeric", "distinct": "294", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "27", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "50", "mean": "11", "stdev": "8" }, { "name": "piPC03", "index": "28", "type": "numeric", "distinct": "289", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MWC05", "index": "29", "type": "numeric", "distinct": "285", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "30", "type": "numeric", "distinct": "331", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MPC05", "index": "31", "type": "numeric", "distinct": "121", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MATS5i", "index": "32", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MPC04", "index": "33", "type": "numeric", "distinct": "87", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "34", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "135", "mean": "45", "stdev": "28" }, { "name": "TRS", "index": "35", "type": "numeric", "distinct": "20", "missing": "0", "min": "5", "max": "36", "mean": "22", "stdev": "6" }, { "name": "piPC05", "index": "36", "type": "numeric", "distinct": "323", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MWC08", "index": "37", "type": "numeric", "distinct": "313", "missing": "0", "min": "10", "max": "11", "mean": "10", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "38", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "39", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "40", "type": "numeric", "distinct": "195", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "41", "type": "numeric", "distinct": "195", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "42", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "142", "mean": "43", "stdev": "31" }, { "name": "Eig10_AEA.ed.", "index": "43", "type": "numeric", "distinct": "258", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.ed.", "index": "44", "type": "numeric", "distinct": "296", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "P_VSA_s_5", "index": "45", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "118", "mean": "27", "stdev": "25" }, { "name": "SdssC", "index": "46", "type": "numeric", "distinct": "310", "missing": "0", "min": "-5", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "MPC03", "index": "47", "type": "numeric", "distinct": "62", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "48", "type": "numeric", "distinct": "258", "missing": "0", "min": "0", "max": "128", "mean": "40", "stdev": "23" }, { "name": "Eig09_AEA.bo.", "index": "49", "type": "numeric", "distinct": "273", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "piPC02", "index": "50", "type": "numeric", "distinct": "188", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "51", "type": "numeric", "distinct": "188", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3m", "index": "52", "type": "numeric", "distinct": "311", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig12_EA.ed.", "index": "53", "type": "numeric", "distinct": "239", "missing": "0", "min": "-3", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM07_AEA.ri.", "index": "54", "type": "numeric", "distinct": "239", "missing": "0", "min": "-3", "max": "5", "mean": "2", "stdev": "1" }, { "name": "ATS7m", "index": "55", "type": "numeric", "distinct": "366", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X4", "index": "56", "type": "numeric", "distinct": "357", "missing": "0", "min": "4", "max": "15", "mean": "9", "stdev": "2" }, { "name": "ZM1Mad", "index": "57", "type": "numeric", "distinct": "364", "missing": "0", "min": "106", "max": "336", "mean": "205", "stdev": "41" }, { "name": "Eig04_EA.bo.", "index": "58", "type": "numeric", "distinct": "282", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "59", "type": "numeric", "distinct": "282", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "D.Dtr10", "index": "60", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "403", "mean": "48", "stdev": "78" }, { "name": "SpMin1_Bh.e.", "index": "61", "type": "numeric", "distinct": "153", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "62", "type": "numeric", "distinct": "139", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "N.074", "index": "63", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "GGI5", "index": "64", "type": "numeric", "distinct": "257", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATS3v", "index": "65", "type": "numeric", "distinct": "304", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "66", "type": "numeric", "distinct": "310", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "67", "type": "numeric", "distinct": "310", "missing": "0", "min": "2", "max": "4", "mean": "3", "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 }