{ "data_id": "33368", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL205", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL205", "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: CHEMBL205 (TID: 15), and it has 3666 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 12:36:02", "update_comment": null, "last_update": "2016-07-15 12:36:02", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3503742\/data_53769.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL205", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL205 (TID: 15), and it has 3666 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": 3666, "NumberOfFeatures": 74, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 73, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 5.2693924629851026, "MinStdDevOfNumericAtts": 0.06351312676058804, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.5296509297890946, "MaxStdDevOfNumericAtts": 107.62349520443871, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 3.262533722233166, "Quartile3StdDevOfNumericAtts": 1.754232735906337, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.5297326786688479, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 19.127739146363147, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 10.310125126112592, "Quartile1SkewnessOfNumericAtts": -2.6921067988257508, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4761328095215683, "AutoCorrelation": -0.18303219645293417, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 14.145597181517722, "Dimensionality": 0.020185488270594652, "MeanSkewnessOfNumericAtts": -0.6267988120803476, "Quartile2MeansOfNumericAtts": 4.575069558101473, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.6008283398108345, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.42066379703338963, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5033336639161439, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6852067110871558, "MaxKurtosisOfNumericAtts": 85.02195688782619, "MinMeansOfNumericAtts": -4.441017457719585, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 115.96765657392253, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 26.952485670545514, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.64864864864865, "Quartile3MeansOfNumericAtts": 11.563112111292963, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -7.864250440080454, "PercentageOfSymbolicFeatures": 1.3513513513513513, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "73", "type": "numeric", "distinct": "1255", "missing": "0", "target": "1", "min": "-4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "3666", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_02_AP", "index": "1", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "N.069", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "4", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "6", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "S.107", "index": "7", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "NaaS", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "9", "type": "numeric", "distinct": "557", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "10", "type": "numeric", "distinct": "557", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_03_AP", "index": "11", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "S.110", "index": "12", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NddssS", "index": "13", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nS", "index": "14", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_4", "index": "15", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "251", "mean": "24", "stdev": "27" }, { "name": "SpMax1_Bh.m.", "index": "16", "type": "numeric", "distinct": "388", "missing": "0", "min": "3", "max": "11", "mean": "5", "stdev": "1" }, { "name": "nR05", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SRW05", "index": "18", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_i_1", "index": "19", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "251", "mean": "20", "stdev": "24" }, { "name": "SpDiam_AEA.dm.", "index": "20", "type": "numeric", "distinct": "721", "missing": "0", "min": "0", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "21", "type": "numeric", "distinct": "585", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "22", "type": "numeric", "distinct": "585", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.044", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.ed.", "index": "24", "type": "numeric", "distinct": "602", "missing": "0", "min": "0", "max": "11", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "25", "type": "numeric", "distinct": "602", "missing": "0", "min": "0", "max": "11", "mean": "7", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "26", "type": "numeric", "distinct": "1326", "missing": "0", "min": "0", "max": "11", "mean": "10", "stdev": "1" }, { "name": "Eig01_EA.ed.", "index": "27", "type": "numeric", "distinct": "855", "missing": "0", "min": "0", "max": "31", "mean": "12", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "28", "type": "numeric", "distinct": "855", "missing": "0", "min": "0", "max": "31", "mean": "12", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "29", "type": "numeric", "distinct": "855", "missing": "0", "min": "0", "max": "31", "mean": "12", "stdev": "2" }, { "name": "Eig01_EA", "index": "30", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "31", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA", "index": "32", "type": "numeric", "distinct": "588", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "33", "type": "numeric", "distinct": "535", "missing": "0", "min": "0", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "34", "type": "numeric", "distinct": "535", "missing": "0", "min": "0", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "35", "type": "numeric", "distinct": "535", "missing": "0", "min": "0", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nSO2N", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eta_sh_x", "index": "37", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpDiam_EA", "index": "38", "type": "numeric", "distinct": "635", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "39", "type": "numeric", "distinct": "596", "missing": "0", "min": "0", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SpDiam_EA.ed.", "index": "40", "type": "numeric", "distinct": "1209", "missing": "0", "min": "0", "max": "42", "mean": "19", "stdev": "3" }, { "name": "CATS2D_03_PL", "index": "41", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "O.058", "index": "42", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "SddssS", "index": "43", "type": "numeric", "distinct": "1374", "missing": "0", "min": "-19", "max": "0", "mean": "-4", "stdev": "3" }, { "name": "NdO", "index": "44", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "nHM", "index": "45", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "46", "type": "numeric", "distinct": "815", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "1" }, { "name": "ATSC1s", "index": "47", "type": "numeric", "distinct": "3167", "missing": "0", "min": "1", "max": "430", "mean": "47", "stdev": "54" }, { "name": "SpMax1_Bh.s.", "index": "48", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "49", "type": "numeric", "distinct": "1299", "missing": "0", "min": "0", "max": "26", "mean": "23", "stdev": "2" }, { "name": "SM14_EA.bo.", "index": "50", "type": "numeric", "distinct": "1317", "missing": "0", "min": "0", "max": "24", "mean": "21", "stdev": "1" }, { "name": "P_VSA_s_1", "index": "51", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "29", "mean": "7", "stdev": "4" }, { "name": "SM10_EA.bo.", "index": "52", "type": "numeric", "distinct": "1357", "missing": "0", "min": "0", "max": "17", "mean": "16", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "53", "type": "numeric", "distinct": "1302", "missing": "0", "min": "0", "max": "22", "mean": "20", "stdev": "2" }, { "name": "SpMax1_Bh.p.", "index": "54", "type": "numeric", "distinct": "478", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "55", "type": "numeric", "distinct": "493", "missing": "0", "min": "0", "max": "396", "mean": "98", "stdev": "50" }, { "name": "IVDE", "index": "56", "type": "numeric", "distinct": "450", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "57", "type": "numeric", "distinct": "1352", "missing": "0", "min": "0", "max": "21", "mean": "18", "stdev": "1" }, { "name": "D.Dtr05", "index": "58", "type": "numeric", "distinct": "966", "missing": "0", "min": "0", "max": "463", "mean": "33", "stdev": "59" }, { "name": "SM11_EA.bo.", "index": "59", "type": "numeric", "distinct": "1331", "missing": "0", "min": "0", "max": "19", "mean": "17", "stdev": "1" }, { "name": "Eig01_AEA.ri.", "index": "60", "type": "numeric", "distinct": "644", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "61", "type": "numeric", "distinct": "644", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "62", "type": "numeric", "distinct": "303", "missing": "0", "min": "0", "max": "203", "mean": "23", "stdev": "25" }, { "name": "MAXDN", "index": "63", "type": "numeric", "distinct": "1427", "missing": "0", "min": "0", "max": "10", "mean": "5", "stdev": "1" }, { "name": "SM03_EA", "index": "64", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATSC2s", "index": "65", "type": "numeric", "distinct": "3379", "missing": "0", "min": "0", "max": "891", "mean": "116", "stdev": "108" }, { "name": "nThiazoles", "index": "66", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "67", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "Eig02_EA.bo.", "index": "68", "type": "numeric", "distinct": "1015", "missing": "0", "min": "-2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM12_AEA.ri.", "index": "69", "type": "numeric", "distinct": "1015", "missing": "0", "min": "-2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "70", "type": "numeric", "distinct": "812", "missing": "0", "min": "0", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM07_EA.bo.", "index": "71", "type": "numeric", "distinct": "1302", "missing": "0", "min": "0", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "72", "type": "numeric", "distinct": "1509", "missing": "0", "min": "0", "max": "45", "mean": "32", "stdev": "3" } ], "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 }