{ "data_id": "29201", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL204", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL204", "version": 7, "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: CHEMBL204 (TID: 11), and it has 5742 rows and 72 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 01:54:54", "update_comment": null, "last_update": "2016-07-15 01:54:54", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3386015\/data_53771.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL204", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL204 (TID: 11), and it has 5742 rows and 72 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": 5742, "NumberOfFeatures": 74, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 73, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.012887495646116336, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.3634811696748348, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.101740499752089, "Quartile2MeansOfNumericAtts": 4.159984848484848, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.8667214522255895, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.251207809437206, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0402492683709665, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5839954506774505, "MaxKurtosisOfNumericAtts": 305.37725280649835, "MinMeansOfNumericAtts": 0.034482758620689176, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 133.92109195402296, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 6.701398498223405, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.64864864864865, "Quartile3MeansOfNumericAtts": 7.069461511668408, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.11667990830098, "PercentageOfSymbolicFeatures": 1.3513513513513513, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 14.584016851415097, "MinStdDevOfNumericAtts": 0.08801873825981832, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.0718587192916535, "MaxStdDevOfNumericAtts": 114.98303252343882, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.022407853408212608, "Quartile3StdDevOfNumericAtts": 2.001697549339152, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.735481539533265, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 19.410281367513125, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.25242962215447, "Quartile1SkewnessOfNumericAtts": -0.4873451535594608, "AutoCorrelation": -0.42313203274690553, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.30931769353693944 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "73", "type": "numeric", "distinct": "1387", "missing": "0", "target": "1", "min": "-6", "max": "11", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "5742", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nRCONR2", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "SpDiam_EA.ed.", "index": "2", "type": "numeric", "distinct": "2113", "missing": "0", "min": "12", "max": "31", "mean": "19", "stdev": "2" }, { "name": "Eig01_AEA.dm.", "index": "3", "type": "numeric", "distinct": "988", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "4", "type": "numeric", "distinct": "988", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "5", "type": "numeric", "distinct": "1033", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "6", "type": "numeric", "distinct": "1033", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "7", "type": "numeric", "distinct": "1301", "missing": "0", "min": "0", "max": "21", "mean": "8", "stdev": "4" }, { "name": "SM13_EA.dm.", "index": "8", "type": "numeric", "distinct": "852", "missing": "0", "min": "0", "max": "22", "mean": "8", "stdev": "5" }, { "name": "SpDiam_AEA.dm.", "index": "9", "type": "numeric", "distinct": "1005", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM14_EA.dm.", "index": "10", "type": "numeric", "distinct": "1189", "missing": "0", "min": "0", "max": "24", "mean": "10", "stdev": "5" }, { "name": "SM15_EA.dm.", "index": "11", "type": "numeric", "distinct": "803", "missing": "0", "min": "0", "max": "26", "mean": "9", "stdev": "5" }, { "name": "Eig01_EA.ed.", "index": "12", "type": "numeric", "distinct": "1686", "missing": "0", "min": "7", "max": "20", "mean": "12", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "13", "type": "numeric", "distinct": "1686", "missing": "0", "min": "7", "max": "20", "mean": "12", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "14", "type": "numeric", "distinct": "1686", "missing": "0", "min": "7", "max": "20", "mean": "12", "stdev": "1" }, { "name": "CATS2D_06_DD", "index": "15", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "57", "mean": "1", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "16", "type": "numeric", "distinct": "939", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "SM10_EA.dm.", "index": "17", "type": "numeric", "distinct": "1384", "missing": "0", "min": "0", "max": "18", "mean": "7", "stdev": "3" }, { "name": "Eig01_EA.dm.", "index": "18", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "19", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "20", "type": "numeric", "distinct": "465", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "21", "type": "numeric", "distinct": "840", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "22", "type": "numeric", "distinct": "911", "missing": "0", "min": "0", "max": "15", "mean": "6", "stdev": "3" }, { "name": "Eig03_EA.dm.", "index": "23", "type": "numeric", "distinct": "349", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "24", "type": "numeric", "distinct": "848", "missing": "0", "min": "0", "max": "841", "mean": "96", "stdev": "49" }, { "name": "NsssCH", "index": "25", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "29", "mean": "2", "stdev": "2" }, { "name": "F.082", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "0" }, { "name": "C.012", "index": "27", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "nPyrrolidines", "index": "28", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "29", "type": "numeric", "distinct": "374", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_2", "index": "30", "type": "numeric", "distinct": "935", "missing": "0", "min": "0", "max": "1972", "mean": "134", "stdev": "115" }, { "name": "piPC06", "index": "31", "type": "numeric", "distinct": "1857", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "P_VSA_LogP_2", "index": "32", "type": "numeric", "distinct": "1579", "missing": "0", "min": "0", "max": "901", "mean": "61", "stdev": "48" }, { "name": "SpDiam_EA", "index": "33", "type": "numeric", "distinct": "786", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "34", "type": "numeric", "distinct": "346", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_i_4", "index": "35", "type": "numeric", "distinct": "1065", "missing": "0", "min": "0", "max": "841", "mean": "100", "stdev": "50" }, { "name": "Eig01_EA.bo.", "index": "36", "type": "numeric", "distinct": "987", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "37", "type": "numeric", "distinct": "987", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "38", "type": "numeric", "distinct": "987", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "H.", "index": "39", "type": "numeric", "distinct": "275", "missing": "0", "min": "11", "max": "60", "mean": "44", "stdev": "5" }, { "name": "SM08_EA.dm.", "index": "40", "type": "numeric", "distinct": "1556", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "3" }, { "name": "Eig01_EA", "index": "41", "type": "numeric", "distinct": "781", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "42", "type": "numeric", "distinct": "781", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA", "index": "43", "type": "numeric", "distinct": "781", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "44", "type": "numeric", "distinct": "1395", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "45", "type": "numeric", "distinct": "1023", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMin3_Bh.s.", "index": "46", "type": "numeric", "distinct": "736", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CMC.50", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "48", "type": "numeric", "distinct": "392", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Depressant.80", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAdon", "index": "50", "type": "numeric", "distinct": "369", "missing": "0", "min": "0", "max": "1714", "mean": "92", "stdev": "76" }, { "name": "Eta_beta_A", "index": "51", "type": "numeric", "distinct": "639", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_AA", "index": "52", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "40", "mean": "2", "stdev": "1" }, { "name": "N.067", "index": "53", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "54", "type": "numeric", "distinct": "1712", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM11_EA.dm.", "index": "55", "type": "numeric", "distinct": "895", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "4" }, { "name": "Eig03_EA.bo.", "index": "56", "type": "numeric", "distinct": "1148", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "57", "type": "numeric", "distinct": "1148", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "Hypnotic.80", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "59", "type": "numeric", "distinct": "805", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "60", "type": "numeric", "distinct": "805", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM06_EA.dm.", "index": "61", "type": "numeric", "distinct": "1669", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "Neoplastic.50", "index": "62", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "63", "type": "numeric", "distinct": "878", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Infective.50", "index": "64", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS7v", "index": "65", "type": "numeric", "distinct": "1804", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax1_Bh.s.", "index": "66", "type": "numeric", "distinct": "200", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "67", "type": "numeric", "distinct": "1037", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "68", "type": "numeric", "distinct": "488", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS8v", "index": "69", "type": "numeric", "distinct": "1893", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "Eig02_AEA.ed.", "index": "70", "type": "numeric", "distinct": "1090", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "71", "type": "numeric", "distinct": "1042", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "72", "type": "numeric", "distinct": "327", "missing": "0", "min": "0", "max": "99", "mean": "10", "stdev": "13" } ], "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 }