{ "data_id": "32692", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4086", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4086", "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: CHEMBL4086 (TID: 20104), and it has 116 rows and 60 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 10:52:09", "update_comment": null, "last_update": "2016-07-15 10:52:09", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3487208\/data_52084.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-CHEMBL4086", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4086 (TID: 20104), and it has 116 rows and 60 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": 116, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.2188613327721907, "MinStdDevOfNumericAtts": 0.002463450974679155, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.203753372399667, "MaxStdDevOfNumericAtts": 89.45480253804746, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.03550469093086828, "Quartile3StdDevOfNumericAtts": 1.1203973856425833, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.3537586206896552, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.7981142594175111, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.527562323346523, "Quartile1SkewnessOfNumericAtts": -0.6710429202569004, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.16876725892060396, "AutoCorrelation": 0.3456695652173911, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.4140674107956701, "Dimensionality": 0.5344827586206896, "MeanSkewnessOfNumericAtts": 0.28492156361312804, "Quartile2MeansOfNumericAtts": 1.8706896551724144, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.550094130373719, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5431855573018357, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.311709539099755, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4058390697366846, "MaxKurtosisOfNumericAtts": 8.889025613809533, "MinMeansOfNumericAtts": -0.7491034482758626, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 120.11102586206897, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.4498880302181827, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 4.383818965517241, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5758409302862295, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "84", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "116", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig01_AEA.bo.", "index": "1", "type": "numeric", "distinct": "41", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "2", "type": "numeric", "distinct": "41", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SRW07", "index": "3", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SRW09", "index": "4", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "3" }, { "name": "SddssS", "index": "5", "type": "numeric", "distinct": "26", "missing": "0", "min": "-4", "max": "0", "mean": "-1", "stdev": "1" }, { "name": "BIC5", "index": "6", "type": "numeric", "distinct": "49", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "7", "type": "numeric", "distinct": "44", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_sh_x", "index": "8", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1e", "index": "9", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1m", "index": "10", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCrs", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "NddssS", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nSO2N", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "S.110", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC5", "index": "16", "type": "numeric", "distinct": "57", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "17", "type": "numeric", "distinct": "62", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "18", "type": "numeric", "distinct": "44", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS1p", "index": "19", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NdssC", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "21", "type": "numeric", "distinct": "33", "missing": "0", "min": "16", "max": "22", "mean": "17", "stdev": "1" }, { "name": "CATS2D_08_DL", "index": "22", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "MATS1s", "index": "23", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CIC5", "index": "24", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NdO", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "O.058", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SdO", "index": "27", "type": "numeric", "distinct": "110", "missing": "0", "min": "11", "max": "48", "mean": "25", "stdev": "7" }, { "name": "SIC4", "index": "28", "type": "numeric", "distinct": "59", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "29", "type": "numeric", "distinct": "54", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "30", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "31", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "32", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "33", "type": "numeric", "distinct": "90", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "34", "type": "numeric", "distinct": "45", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "D.Dtr05", "index": "35", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "340", "mean": "120", "stdev": "89" }, { "name": "nR05", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SRW05", "index": "37", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "N.072", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CIC4", "index": "39", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "JGI8", "index": "40", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SsssCH", "index": "41", "type": "numeric", "distinct": "91", "missing": "0", "min": "-2", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.008", "index": "42", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "43", "type": "numeric", "distinct": "70", "missing": "0", "min": "18", "max": "23", "mean": "21", "stdev": "1" }, { "name": "MATS1i", "index": "44", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.068", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Yindex", "index": "46", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "47", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "H.050", "index": "48", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Hy", "index": "49", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nHDon", "index": "50", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SAdon", "index": "51", "type": "numeric", "distinct": "7", "missing": "0", "min": "16", "max": "128", "mean": "79", "stdev": "19" }, { "name": "CATS2D_03_DL", "index": "52", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "CATS2D_06_AL", "index": "53", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "4" }, { "name": "NsssCH", "index": "54", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eta_sh_y", "index": "55", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SsOH", "index": "56", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "29", "mean": "17", "stdev": "5" }, { "name": "SpDiam_AEA.ed.", "index": "57", "type": "numeric", "distinct": "38", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "CIC3", "index": "58", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "59", "type": "numeric", "distinct": "46", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "60", "type": "numeric", "distinct": "47", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" } ], "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 }