{ "data_id": "38851", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2326", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2326", "version": 12, "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: CHEMBL2326 (TID: 11060), and it has 380 rows and 69 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": "2016-07-16 05:44:22", "update_comment": null, "last_update": "2016-07-16 05:44:22", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3654712\/data_53505.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2326", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2326 (TID: 11060), and it has 380 rows and 69 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": 380, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 16.666825, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.497617875088606, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.38468200850199996, "MaxSkewnessOfNumericAtts": 3.9227860002983657, "MinStdDevOfNumericAtts": 0.06083976618139719, "Quartile1KurtosisOfNumericAtts": -0.06632195519786999, "Quartile3StdDevOfNumericAtts": 2.3714374779252805, "MaxStdDevOfNumericAtts": 44.62770835505787, "MinorityClassPercentage": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.9361842105263154, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 8.40488440073223, "Quartile1SkewnessOfNumericAtts": -2.679530476185549, "MeanMeansOfNumericAtts": 10.887775789473684, "Quartile1StdDevOfNumericAtts": 0.6004532524378363, "AutoCorrelation": -0.024021108179419784, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 3.311573363691143, "Dimensionality": 0.1868421052631579, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 5.0040736842105265, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -1.34225496964754, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.7020530846310415, "Quartile2SkewnessOfNumericAtts": -0.9811457930350553, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1412005374869492, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8986711425110636, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 36.903788505682094, "MinMeansOfNumericAtts": -2.774363157894736, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 10.94112489575214, "MaxMeansOfNumericAtts": 71.94758684210527, "MinMutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "299", "missing": "0", "target": "1", "min": "3", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "380", "missing": "0", "identifier": "1", "distr": [] }, { "name": "S.110", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "2", "type": "numeric", "distinct": "142", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "NddssS", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SddssS", "index": "4", "type": "numeric", "distinct": "205", "missing": "0", "min": "-10", "max": "0", "mean": "-3", "stdev": "2" }, { "name": "SpMax1_Bh.s.", "index": "5", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "9", "mean": "8", "stdev": "1" }, { "name": "MAXDN", "index": "6", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "P_VSA_s_1", "index": "7", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "Eta_sh_x", "index": "8", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.069", "index": "9", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AP", "index": "10", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DA", "index": "11", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "nS", "index": "12", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "13", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM11_AEA.ri.", "index": "14", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax_EA.bo.", "index": "15", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "nSO2N", "index": "16", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "17", "type": "numeric", "distinct": "278", "missing": "0", "min": "0", "max": "21", "mean": "19", "stdev": "3" }, { "name": "SM14_EA.bo.", "index": "18", "type": "numeric", "distinct": "276", "missing": "0", "min": "9", "max": "23", "mean": "21", "stdev": "2" }, { "name": "SM15_EA.bo.", "index": "19", "type": "numeric", "distinct": "262", "missing": "0", "min": "0", "max": "24", "mean": "22", "stdev": "3" }, { "name": "SM10_EA.bo.", "index": "20", "type": "numeric", "distinct": "294", "missing": "0", "min": "7", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM11_EA.bo.", "index": "21", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "18", "mean": "16", "stdev": "2" }, { "name": "SM12_EA.bo.", "index": "22", "type": "numeric", "distinct": "274", "missing": "0", "min": "8", "max": "20", "mean": "18", "stdev": "2" }, { "name": "SM09_EA.bo.", "index": "23", "type": "numeric", "distinct": "280", "missing": "0", "min": "0", "max": "15", "mean": "13", "stdev": "2" }, { "name": "SpDiam_AEA.dm.", "index": "24", "type": "numeric", "distinct": "171", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "P_VSA_i_1", "index": "25", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "88", "mean": "12", "stdev": "17" }, { "name": "Eig01_AEA.dm.", "index": "26", "type": "numeric", "distinct": "164", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax_AEA.dm.", "index": "27", "type": "numeric", "distinct": "164", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SsNH2", "index": "32", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "P_VSA_e_3", "index": "33", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "118", "mean": "40", "stdev": "32" }, { "name": "P_VSA_i_4", "index": "34", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "162", "mean": "46", "stdev": "37" }, { "name": "nHM", "index": "35", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_4", "index": "36", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "129", "mean": "18", "stdev": "25" }, { "name": "Eig01_AEA.bo.", "index": "37", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "38", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "39", "type": "numeric", "distinct": "296", "missing": "0", "min": "5", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "40", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "9", "mean": "8", "stdev": "1" }, { "name": "N.", "index": "41", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "29", "mean": "5", "stdev": "5" }, { "name": "Eig01_AEA.ed.", "index": "42", "type": "numeric", "distinct": "172", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "43", "type": "numeric", "distinct": "172", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "BLI", "index": "44", "type": "numeric", "distinct": "276", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X1Av", "index": "45", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "46", "type": "numeric", "distinct": "368", "missing": "0", "min": "4", "max": "294", "mean": "72", "stdev": "45" }, { "name": "Eig01_EA", "index": "47", "type": "numeric", "distinct": "177", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "48", "type": "numeric", "distinct": "177", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA", "index": "49", "type": "numeric", "distinct": "177", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nN", "index": "50", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SpMax1_Bh.p.", "index": "51", "type": "numeric", "distinct": "161", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "52", "type": "numeric", "distinct": "198", "missing": "0", "min": "3", "max": "18", "mean": "11", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "53", "type": "numeric", "distinct": "198", "missing": "0", "min": "3", "max": "18", "mean": "11", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "54", "type": "numeric", "distinct": "198", "missing": "0", "min": "3", "max": "18", "mean": "11", "stdev": "2" }, { "name": "SM06_EA.bo.", "index": "55", "type": "numeric", "distinct": "300", "missing": "0", "min": "4", "max": "11", "mean": "9", "stdev": "1" }, { "name": "O.058", "index": "56", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "GATS1e", "index": "57", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM15_AEA.ed.", "index": "58", "type": "numeric", "distinct": "281", "missing": "0", "min": "20", "max": "32", "mean": "29", "stdev": "2" }, { "name": "SdO", "index": "59", "type": "numeric", "distinct": "345", "missing": "0", "min": "0", "max": "59", "mean": "25", "stdev": "13" }, { "name": "SM14_AEA.ed.", "index": "60", "type": "numeric", "distinct": "280", "missing": "0", "min": "18", "max": "30", "mean": "27", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "61", "type": "numeric", "distinct": "270", "missing": "0", "min": "0", "max": "38", "mean": "31", "stdev": "5" }, { "name": "SM14_EA.ed.", "index": "62", "type": "numeric", "distinct": "271", "missing": "0", "min": "18", "max": "40", "mean": "34", "stdev": "3" }, { "name": "SM15_EA.ed.", "index": "63", "type": "numeric", "distinct": "261", "missing": "0", "min": "0", "max": "43", "mean": "36", "stdev": "5" }, { "name": "SpMax2_Bh.s.", "index": "64", "type": "numeric", "distinct": "95", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpDiam_EA.bo.", "index": "65", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SM09_EA.ed.", "index": "66", "type": "numeric", "distinct": "275", "missing": "0", "min": "0", "max": "26", "mean": "22", "stdev": "3" }, { "name": "SM10_EA.ed.", "index": "67", "type": "numeric", "distinct": "283", "missing": "0", "min": "13", "max": "29", "mean": "24", "stdev": "2" }, { "name": "NdO", "index": "68", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "69", "type": "numeric", "distinct": "276", "missing": "0", "min": "0", "max": "32", "mean": "26", "stdev": "4" } ], "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 }