{ "data_id": "31762", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2803", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2803", "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: CHEMBL2803 (TID: 12214), and it has 330 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 08:26:01", "update_comment": null, "last_update": "2016-07-15 08:26:01", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3458996\/data_53409.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2803", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2803 (TID: 12214), and it has 330 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": 330, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.727775573670476, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9868644642658861, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 113.24047554377334, "MinMeansOfNumericAtts": -0.05618181818181818, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.461182051140526, "MaxMeansOfNumericAtts": 178.25350303030305, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 6.620695454545454, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.714174320828168, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.4221918160249167, "MaxSkewnessOfNumericAtts": 9.811044682177684, "MinStdDevOfNumericAtts": 0.009143181164816515, "Quartile1KurtosisOfNumericAtts": -0.42886517888370346, "Quartile3StdDevOfNumericAtts": 2.706384188206723, "MaxStdDevOfNumericAtts": 142.49013105055357, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 0.680790909090909, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 11.600191789261737, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": 0.13638853605724674, "MeanMeansOfNumericAtts": 13.535487395696093, "Quartile1StdDevOfNumericAtts": 0.18111172117979557, "AutoCorrelation": 0.25780851063829785, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 0.8082279314641183, "Dimensionality": 0.21212121212121213, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 1.9430636363636358, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.4755412340902423, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.184324579556693, "Quartile2SkewnessOfNumericAtts": 0.5043738064200739, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "146", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "330", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Chi1_EA.dm.", "index": "1", "type": "numeric", "distinct": "296", "missing": "0", "min": "2", "max": "113", "mean": "39", "stdev": "16" }, { "name": "PW4", "index": "2", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SssNH", "index": "3", "type": "numeric", "distinct": "264", "missing": "0", "min": "0", "max": "43", "mean": "5", "stdev": "4" }, { "name": "MCD", "index": "4", "type": "numeric", "distinct": "151", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "piPC09", "index": "5", "type": "numeric", "distinct": "264", "missing": "0", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "SssO", "index": "6", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "35", "mean": "6", "stdev": "6" }, { "name": "piPC10", "index": "7", "type": "numeric", "distinct": "263", "missing": "0", "min": "0", "max": "10", "mean": "8", "stdev": "1" }, { "name": "P_VSA_LogP_1", "index": "8", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "97", "mean": "19", "stdev": "14" }, { "name": "C.005", "index": "9", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nArOR", "index": "10", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NssO", "index": "11", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "NaasC", "index": "12", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "12", "mean": "6", "stdev": "2" }, { "name": "CATS2D_08_DA", "index": "13", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "38", "mean": "2", "stdev": "3" }, { "name": "PCD", "index": "14", "type": "numeric", "distinct": "259", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "GATS3i", "index": "15", "type": "numeric", "distinct": "231", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2v", "index": "16", "type": "numeric", "distinct": "210", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nArNHR", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "18", "type": "numeric", "distinct": "168", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "19", "type": "numeric", "distinct": "168", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "20", "type": "numeric", "distinct": "168", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SaaN", "index": "21", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "22", "mean": "9", "stdev": "4" }, { "name": "nPyrimidines", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "23", "type": "numeric", "distinct": "231", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "CATS2D_05_DL", "index": "24", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "46", "mean": "4", "stdev": "5" }, { "name": "CATS2D_04_DD", "index": "25", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GNar", "index": "26", "type": "numeric", "distinct": "152", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SaaO", "index": "27", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "GATS1p", "index": "28", "type": "numeric", "distinct": "244", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS2p", "index": "29", "type": "numeric", "distinct": "203", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2A", "index": "30", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.", "index": "31", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "24", "mean": "9", "stdev": "3" }, { "name": "ATSC2e", "index": "32", "type": "numeric", "distinct": "261", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "0" }, { "name": "MATS2e", "index": "33", "type": "numeric", "distinct": "248", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "34", "type": "numeric", "distinct": "258", "missing": "0", "min": "21", "max": "25", "mean": "22", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "35", "type": "numeric", "distinct": "259", "missing": "0", "min": "19", "max": "24", "mean": "21", "stdev": "1" }, { "name": "SM03_EA.dm.", "index": "36", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "N.073", "index": "37", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_p_4", "index": "38", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "60", "mean": "1", "stdev": "7" }, { "name": "GATS2e", "index": "39", "type": "numeric", "distinct": "258", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X3A", "index": "40", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS2v", "index": "41", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_NL", "index": "42", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "MATS4s", "index": "43", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaO", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "45", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "HNar", "index": "46", "type": "numeric", "distinct": "147", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_04_DA", "index": "47", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "3" }, { "name": "SM05_EA.dm.", "index": "48", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "PW3", "index": "49", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC06", "index": "50", "type": "numeric", "distinct": "251", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "PCR", "index": "51", "type": "numeric", "distinct": "181", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "52", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "53", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "54", "mean": "8", "stdev": "7" }, { "name": "MATS5e", "index": "54", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "55", "type": "numeric", "distinct": "263", "missing": "0", "min": "18", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM07_EA.dm.", "index": "56", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "3" }, { "name": "piPC08", "index": "57", "type": "numeric", "distinct": "266", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax6_Bh.s.", "index": "58", "type": "numeric", "distinct": "219", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATSC1s", "index": "59", "type": "numeric", "distinct": "315", "missing": "0", "min": "4", "max": "278", "mean": "24", "stdev": "26" }, { "name": "X0A", "index": "60", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "61", "type": "numeric", "distinct": "207", "missing": "0", "min": "25", "max": "1518", "mean": "154", "stdev": "123" }, { "name": "Eig01_AEA.bo.", "index": "62", "type": "numeric", "distinct": "167", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "63", "type": "numeric", "distinct": "167", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "64", "type": "numeric", "distinct": "211", "missing": "0", "min": "49", "max": "1248", "mean": "129", "stdev": "96" }, { "name": "SpMaxA_EA.dm.", "index": "65", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC07", "index": "66", "type": "numeric", "distinct": "256", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "P_VSA_p_2", "index": "67", "type": "numeric", "distinct": "211", "missing": "0", "min": "60", "max": "1845", "mean": "169", "stdev": "142" }, { "name": "P_VSA_v_2", "index": "68", "type": "numeric", "distinct": "232", "missing": "0", "min": "60", "max": "1845", "mean": "178", "stdev": "142" } ], "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 }