{ "data_id": "30014", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL275", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL275", "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: CHEMBL275 (TID: 10599), and it has 695 rows and 68 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 03:56:29", "update_comment": null, "last_update": "2016-07-15 03:56:29", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3408468\/data_53348.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL275", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL275 (TID: 10599), and it has 695 rows and 68 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": 695, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.10071942446043165, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.07121085640090419, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.004924371137878069, "Quartile2MeansOfNumericAtts": 7.8419122302158275, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.10458921228474, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.0451442758368176, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0890559786305019, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4222082440054431, "MaxKurtosisOfNumericAtts": 26.435960428379367, "MinMeansOfNumericAtts": 0.6316474820143885, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 220.56869352517987, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.5079629208647687, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 12.98814964028777, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0049778676387249, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.2815690192586535, "MinStdDevOfNumericAtts": 0.17645138160726628, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.07596358772667902, "MaxStdDevOfNumericAtts": 58.012242118234035, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.3176216489708166, "Quartile3StdDevOfNumericAtts": 0.6132174940532416, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 4.5457676258992805, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.9669925220593076, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.298146032739027, "Quartile1SkewnessOfNumericAtts": -0.23948397015181988, "AutoCorrelation": 0.03846253602305391, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.33006613784763755 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "422", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "695", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig02_EA", "index": "1", "type": "numeric", "distinct": "284", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.bo.", "index": "2", "type": "numeric", "distinct": "284", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "3", "type": "numeric", "distinct": "428", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM03_EA.ed.", "index": "4", "type": "numeric", "distinct": "283", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM05_EA", "index": "5", "type": "numeric", "distinct": "121", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "6", "type": "numeric", "distinct": "418", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM07_EA", "index": "7", "type": "numeric", "distinct": "356", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "8", "type": "numeric", "distinct": "121", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM06_EA", "index": "9", "type": "numeric", "distinct": "415", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM06_AEA.ed.", "index": "10", "type": "numeric", "distinct": "405", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM08_AEA.ed.", "index": "11", "type": "numeric", "distinct": "410", "missing": "0", "min": "15", "max": "18", "mean": "16", "stdev": "0" }, { "name": "SM08_EA", "index": "12", "type": "numeric", "distinct": "427", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "13", "type": "numeric", "distinct": "443", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM03_EA", "index": "14", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "15", "type": "numeric", "distinct": "379", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig02_AEA.ri.", "index": "16", "type": "numeric", "distinct": "335", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "17", "type": "numeric", "distinct": "377", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "18", "type": "numeric", "distinct": "377", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM05_AEA.ed.", "index": "19", "type": "numeric", "distinct": "409", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM07_AEA.ed.", "index": "20", "type": "numeric", "distinct": "418", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "0" }, { "name": "SM09_AEA.ed.", "index": "21", "type": "numeric", "distinct": "414", "missing": "0", "min": "17", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM09_EA", "index": "22", "type": "numeric", "distinct": "415", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SM10_EA", "index": "23", "type": "numeric", "distinct": "439", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SM13_EA", "index": "24", "type": "numeric", "distinct": "432", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM04_EA.ed.", "index": "25", "type": "numeric", "distinct": "432", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "26", "type": "numeric", "distinct": "371", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM05_EA.ed.", "index": "27", "type": "numeric", "distinct": "421", "missing": "0", "min": "11", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM04_AEA.ed.", "index": "28", "type": "numeric", "distinct": "391", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SM11_AEA.ed.", "index": "29", "type": "numeric", "distinct": "421", "missing": "0", "min": "20", "max": "24", "mean": "22", "stdev": "1" }, { "name": "SM11_EA", "index": "30", "type": "numeric", "distinct": "421", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "1" }, { "name": "SM12_EA", "index": "31", "type": "numeric", "distinct": "441", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM10_AEA.ed.", "index": "32", "type": "numeric", "distinct": "417", "missing": "0", "min": "19", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM12_AEA.ed.", "index": "33", "type": "numeric", "distinct": "420", "missing": "0", "min": "22", "max": "26", "mean": "24", "stdev": "1" }, { "name": "SM06_EA.ed.", "index": "34", "type": "numeric", "distinct": "434", "missing": "0", "min": "14", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM14_EA", "index": "35", "type": "numeric", "distinct": "451", "missing": "0", "min": "15", "max": "20", "mean": "17", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "36", "type": "numeric", "distinct": "412", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig02_EA.ed.", "index": "37", "type": "numeric", "distinct": "336", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "1" }, { "name": "SM11_AEA.dm.", "index": "38", "type": "numeric", "distinct": "336", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "1" }, { "name": "SM13_AEA.ed.", "index": "39", "type": "numeric", "distinct": "410", "missing": "0", "min": "24", "max": "29", "mean": "26", "stdev": "1" }, { "name": "Eig02_AEA.ed.", "index": "40", "type": "numeric", "distinct": "256", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "41", "type": "numeric", "distinct": "412", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "ATS1m", "index": "42", "type": "numeric", "distinct": "418", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ZM2Mad", "index": "43", "type": "numeric", "distinct": "633", "missing": "0", "min": "70", "max": "700", "mean": "221", "stdev": "58" }, { "name": "Eig02_AEA.bo.", "index": "44", "type": "numeric", "distinct": "318", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig07_EA.ed.", "index": "45", "type": "numeric", "distinct": "408", "missing": "0", "min": "-1", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SM02_AEA.ri.", "index": "46", "type": "numeric", "distinct": "408", "missing": "0", "min": "-1", "max": "9", "mean": "5", "stdev": "1" }, { "name": "Eig06_EA.bo.", "index": "47", "type": "numeric", "distinct": "341", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Eig03_AEA.ed.", "index": "48", "type": "numeric", "distinct": "321", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "49", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "174", "mean": "63", "stdev": "38" }, { "name": "piPC03", "index": "50", "type": "numeric", "distinct": "342", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM05_EA.ri.", "index": "51", "type": "numeric", "distinct": "463", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "ATSC6e", "index": "52", "type": "numeric", "distinct": "478", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "0" }, { "name": "Eta_F_A", "index": "53", "type": "numeric", "distinct": "414", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MPC09", "index": "54", "type": "numeric", "distinct": "235", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "55", "type": "numeric", "distinct": "255", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC02", "index": "56", "type": "numeric", "distinct": "228", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "57", "type": "numeric", "distinct": "228", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_EA.ri.", "index": "58", "type": "numeric", "distinct": "474", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM07_EA.ri.", "index": "59", "type": "numeric", "distinct": "501", "missing": "0", "min": "7", "max": "10", "mean": "9", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "60", "type": "numeric", "distinct": "323", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.ed.", "index": "61", "type": "numeric", "distinct": "400", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SRW10", "index": "62", "type": "numeric", "distinct": "390", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "0" }, { "name": "X2sol", "index": "63", "type": "numeric", "distinct": "473", "missing": "0", "min": "5", "max": "46", "mean": "13", "stdev": "3" }, { "name": "MPC07", "index": "64", "type": "numeric", "distinct": "184", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC05", "index": "65", "type": "numeric", "distinct": "422", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "66", "type": "numeric", "distinct": "398", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piID", "index": "67", "type": "numeric", "distinct": "459", "missing": "0", "min": "7", "max": "14", "mean": "11", "stdev": "2" }, { "name": "Pol", "index": "68", "type": "numeric", "distinct": "61", "missing": "0", "min": "15", "max": "179", "mean": "49", "stdev": "14" } ], "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 }