{ "data_id": "32931", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3198", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3198", "version": 11, "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: CHEMBL3198 (TID: 10666), and it has 229 rows and 63 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 11:28:32", "update_comment": null, "last_update": "2016-07-15 11:28:32", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3492709\/data_52560.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-CHEMBL3198", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3198 (TID: 10666), and it has 229 rows and 63 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": 229, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.227348179998118, "MinStdDevOfNumericAtts": 0.08863507365210828, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3822009948171403, "MaxStdDevOfNumericAtts": 151.00644454755533, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.1633008375773375, "Quartile3StdDevOfNumericAtts": 1.13055207019188, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.8182237991266375, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 5.980290113363762, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 19.27044323144105, "Quartile1SkewnessOfNumericAtts": -2.419470271375021, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.241833053119839, "AutoCorrelation": -0.21981578947368394, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.847299357590948, "Dimensionality": 0.2838427947598253, "MeanSkewnessOfNumericAtts": -0.8131229750525117, "Quartile2MeansOfNumericAtts": 3.7430742358078604, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.130107526183917, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.31509088408274544, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8972818812457468, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.46952768989159965, "MaxKurtosisOfNumericAtts": 23.69439829815252, "MinMeansOfNumericAtts": -0.030986899563318775, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 536.3117030567686, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.97149793699746, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 8.343912663755459, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.8004965013064713, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "159", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "229", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr08", "index": "1", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "352", "mean": "22", "stdev": "50" }, { "name": "Eig04_AEA.bo.", "index": "2", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "3", "type": "numeric", "distinct": "151", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Chi0_EA.dm.", "index": "4", "type": "numeric", "distinct": "148", "missing": "0", "min": "3", "max": "38", "mean": "23", "stdev": "7" }, { "name": "D.Dtr12", "index": "5", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "213", "mean": "31", "stdev": "68" }, { "name": "SM15_EA.ri.", "index": "6", "type": "numeric", "distinct": "167", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "7", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "52", "mean": "28", "stdev": "10" }, { "name": "Eig05_AEA.bo.", "index": "8", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "D.Dtr05", "index": "9", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "226", "mean": "48", "stdev": "55" }, { "name": "GATS4s", "index": "10", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM11_EA.ed.", "index": "11", "type": "numeric", "distinct": "130", "missing": "0", "min": "23", "max": "30", "mean": "27", "stdev": "2" }, { "name": "GGI9", "index": "12", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "13", "type": "numeric", "distinct": "152", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "14", "type": "numeric", "distinct": "156", "missing": "0", "min": "7", "max": "9", "mean": "9", "stdev": "0" }, { "name": "GGI3", "index": "15", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MATS6p", "index": "16", "type": "numeric", "distinct": "157", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "17", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MATS6v", "index": "18", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_AEA.bo.", "index": "19", "type": "numeric", "distinct": "128", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS8m", "index": "20", "type": "numeric", "distinct": "186", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "GGI8", "index": "21", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI1", "index": "22", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "10", "mean": "6", "stdev": "2" }, { "name": "piPC05", "index": "23", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SM06_AEA.bo.", "index": "24", "type": "numeric", "distinct": "154", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "25", "type": "numeric", "distinct": "165", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "26", "type": "numeric", "distinct": "172", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "MPC10", "index": "27", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig06_EA", "index": "28", "type": "numeric", "distinct": "142", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "29", "type": "numeric", "distinct": "142", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piPC06", "index": "30", "type": "numeric", "distinct": "166", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "PCD", "index": "31", "type": "numeric", "distinct": "163", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "MATS6m", "index": "32", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5i", "index": "33", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "34", "type": "numeric", "distinct": "160", "missing": "0", "min": "42", "max": "355", "mean": "149", "stdev": "44" }, { "name": "SpMax3_Bh.v.", "index": "35", "type": "numeric", "distinct": "120", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM03_EA", "index": "36", "type": "numeric", "distinct": "16", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA", "index": "37", "type": "numeric", "distinct": "142", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "GGI6", "index": "38", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "39", "type": "numeric", "distinct": "142", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "40", "type": "numeric", "distinct": "111", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "41", "type": "numeric", "distinct": "101", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS6v", "index": "42", "type": "numeric", "distinct": "155", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piPC10", "index": "43", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "piPC03", "index": "44", "type": "numeric", "distinct": "127", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC04", "index": "45", "type": "numeric", "distinct": "156", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC07", "index": "46", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig09_AEA.bo.", "index": "47", "type": "numeric", "distinct": "116", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "48", "type": "numeric", "distinct": "110", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "GGI2", "index": "49", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SRW09", "index": "50", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "4" }, { "name": "Eig05_AEA.ri.", "index": "51", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_EA.ri.", "index": "52", "type": "numeric", "distinct": "167", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "53", "type": "numeric", "distinct": "168", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "GATS3i", "index": "54", "type": "numeric", "distinct": "139", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "55", "type": "numeric", "distinct": "116", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NssCH2", "index": "56", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "24", "mean": "7", "stdev": "3" }, { "name": "SM04_EA.bo.", "index": "57", "type": "numeric", "distinct": "149", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SssssC", "index": "58", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_i_2", "index": "59", "type": "numeric", "distinct": "157", "missing": "0", "min": "39", "max": "233", "mean": "133", "stdev": "37" }, { "name": "ZM2Per", "index": "60", "type": "numeric", "distinct": "203", "missing": "0", "min": "94", "max": "1028", "mean": "536", "stdev": "151" }, { "name": "GATS6p", "index": "61", "type": "numeric", "distinct": "157", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "62", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig10_EA", "index": "63", "type": "numeric", "distinct": "88", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" } ], "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 }