{ "data_id": "26379", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2758", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2758", "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: CHEMBL2758 (TID: 11872), and it has 727 rows and 70 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": "2016-07-14 19:06:47", "update_comment": null, "last_update": "2016-07-14 19:06:47", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3301214\/data_53669.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2758", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2758 (TID: 11872), and it has 727 rows and 70 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": 727, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.2989766162310867, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.48985041650766703, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 161.24558275374395, "Quartile1SkewnessOfNumericAtts": -0.8870311212324812, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.26637133767560445, "AutoCorrelation": 0.663862258953168, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.12317950968283364, "Dimensionality": 0.09903713892709766, "MeanSkewnessOfNumericAtts": -0.2173873158531977, "Quartile2MeansOfNumericAtts": 3.3767661623108665, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 114.47973043624323, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.4514017141825289, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.0412018185749878, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.39028208420039134, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 3.794675659802667, "MinMeansOfNumericAtts": -0.11166712517193968, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 9475.573387895462, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.1309939053339986, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 14.792297111416772, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.385734040192471, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.9483476555418002, "MinStdDevOfNumericAtts": 0.063842196842413, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.35495652025735985, "MaxStdDevOfNumericAtts": 7381.543617894969, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.310273062876655, "Quartile3StdDevOfNumericAtts": 4.719783198705983 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "248", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "727", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin3_Bh.i.", "index": "1", "type": "numeric", "distinct": "445", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "2", "type": "numeric", "distinct": "432", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "3", "type": "numeric", "distinct": "437", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS2i", "index": "4", "type": "numeric", "distinct": "530", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "5", "type": "numeric", "distinct": "426", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.i.", "index": "6", "type": "numeric", "distinct": "425", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "7", "type": "numeric", "distinct": "437", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "8", "type": "numeric", "distinct": "441", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "9", "type": "numeric", "distinct": "415", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "10", "type": "numeric", "distinct": "441", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.e.", "index": "11", "type": "numeric", "distinct": "366", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.i.", "index": "12", "type": "numeric", "distinct": "430", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "13", "type": "numeric", "distinct": "409", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Mp", "index": "14", "type": "numeric", "distinct": "205", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.p.", "index": "15", "type": "numeric", "distinct": "427", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin5_Bh.v.", "index": "16", "type": "numeric", "distinct": "445", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "17", "type": "numeric", "distinct": "458", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.v.", "index": "18", "type": "numeric", "distinct": "458", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIC2", "index": "19", "type": "numeric", "distinct": "648", "missing": "0", "min": "48", "max": "307", "mean": "151", "stdev": "54" }, { "name": "SpMin4_Bh.s.", "index": "20", "type": "numeric", "distinct": "430", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "TIC3", "index": "21", "type": "numeric", "distinct": "585", "missing": "0", "min": "48", "max": "333", "mean": "168", "stdev": "59" }, { "name": "SpMax3_Bh.p.", "index": "22", "type": "numeric", "distinct": "481", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1i", "index": "23", "type": "numeric", "distinct": "502", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "24", "type": "numeric", "distinct": "419", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin5_Bh.e.", "index": "25", "type": "numeric", "distinct": "428", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "26", "type": "numeric", "distinct": "482", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MDDD", "index": "27", "type": "numeric", "distinct": "621", "missing": "0", "min": "3", "max": "53", "mean": "17", "stdev": "8" }, { "name": "SpMin8_Bh.m.", "index": "28", "type": "numeric", "distinct": "422", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CSI", "index": "29", "type": "numeric", "distinct": "432", "missing": "0", "min": "80", "max": "1391", "mean": "421", "stdev": "199" }, { "name": "IDMT", "index": "30", "type": "numeric", "distinct": "661", "missing": "0", "min": "463", "max": "55271", "mean": "9476", "stdev": "7382" }, { "name": "SpMin6_Bh.e.", "index": "31", "type": "numeric", "distinct": "414", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi1_EA.ed.", "index": "32", "type": "numeric", "distinct": "607", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SpMin5_Bh.p.", "index": "33", "type": "numeric", "distinct": "455", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Si", "index": "34", "type": "numeric", "distinct": "648", "missing": "0", "min": "14", "max": "75", "mean": "41", "stdev": "12" }, { "name": "Eta_betaS", "index": "35", "type": "numeric", "distinct": "72", "missing": "0", "min": "5", "max": "25", "mean": "14", "stdev": "4" }, { "name": "TIC1", "index": "36", "type": "numeric", "distinct": "653", "missing": "0", "min": "43", "max": "248", "mean": "125", "stdev": "41" }, { "name": "AECC", "index": "37", "type": "numeric", "distinct": "468", "missing": "0", "min": "4", "max": "17", "mean": "9", "stdev": "2" }, { "name": "nBT", "index": "38", "type": "numeric", "distinct": "56", "missing": "0", "min": "14", "max": "72", "mean": "38", "stdev": "11" }, { "name": "SpMin8_Bh.v.", "index": "39", "type": "numeric", "distinct": "423", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS2e", "index": "40", "type": "numeric", "distinct": "524", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "UNIP", "index": "41", "type": "numeric", "distinct": "135", "missing": "0", "min": "15", "max": "219", "mean": "71", "stdev": "32" }, { "name": "ECC", "index": "42", "type": "numeric", "distinct": "281", "missing": "0", "min": "39", "max": "654", "mean": "197", "stdev": "92" }, { "name": "Eig11_EA.bo.", "index": "43", "type": "numeric", "distinct": "524", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATS5i", "index": "44", "type": "numeric", "distinct": "599", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Xu", "index": "45", "type": "numeric", "distinct": "647", "missing": "0", "min": "9", "max": "36", "mean": "21", "stdev": "5" }, { "name": "Chi1_EA.ri.", "index": "46", "type": "numeric", "distinct": "701", "missing": "0", "min": "5", "max": "21", "mean": "12", "stdev": "3" }, { "name": "nH", "index": "47", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "31", "mean": "15", "stdev": "6" }, { "name": "RDCHI", "index": "48", "type": "numeric", "distinct": "553", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.p.", "index": "49", "type": "numeric", "distinct": "440", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS3e", "index": "50", "type": "numeric", "distinct": "532", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "51", "type": "numeric", "distinct": "670", "missing": "0", "min": "5", "max": "267", "mean": "129", "stdev": "39" }, { "name": "SpMin4_Bh.p.", "index": "52", "type": "numeric", "distinct": "403", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS3i", "index": "53", "type": "numeric", "distinct": "540", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "54", "type": "numeric", "distinct": "433", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "VAR", "index": "55", "type": "numeric", "distinct": "140", "missing": "0", "min": "11", "max": "237", "mean": "70", "stdev": "35" }, { "name": "ON1", "index": "56", "type": "numeric", "distinct": "225", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SpMax4_Bh.i.", "index": "57", "type": "numeric", "distinct": "442", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "LPRS", "index": "58", "type": "numeric", "distinct": "661", "missing": "0", "min": "27", "max": "222", "mean": "99", "stdev": "34" }, { "name": "ON0V", "index": "59", "type": "numeric", "distinct": "438", "missing": "0", "min": "3", "max": "13", "mean": "7", "stdev": "2" }, { "name": "Chi0_EA.ed.", "index": "60", "type": "numeric", "distinct": "631", "missing": "0", "min": "4", "max": "16", "mean": "9", "stdev": "2" }, { "name": "ISIZ", "index": "61", "type": "numeric", "distinct": "54", "missing": "0", "min": "48", "max": "399", "mean": "192", "stdev": "70" }, { "name": "nAT", "index": "62", "type": "numeric", "distinct": "54", "missing": "0", "min": "13", "max": "66", "mean": "36", "stdev": "11" }, { "name": "SpMin8_Bh.i.", "index": "63", "type": "numeric", "distinct": "354", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.s.", "index": "64", "type": "numeric", "distinct": "451", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS1e", "index": "65", "type": "numeric", "distinct": "488", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "66", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ON1V", "index": "67", "type": "numeric", "distinct": "587", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CIC0", "index": "68", "type": "numeric", "distinct": "534", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Sv", "index": "69", "type": "numeric", "distinct": "650", "missing": "0", "min": "11", "max": "43", "mean": "24", "stdev": "6" }, { "name": "SssNH", "index": "70", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" } ], "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 }