{ "data_id": "29888", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3385", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3385", "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: CHEMBL3385 (TID: 11639), and it has 201 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 03:37:38", "update_comment": null, "last_update": "2016-07-15 03:37:38", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3404758\/data_53281.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3385", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3385 (TID: 11639), and it has 201 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": 201, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3482587064676617, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.240352353369035, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.2774672129060811, "Quartile2MeansOfNumericAtts": 1.628955223880597, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 10.534607353884638, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.732722285307271, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1502832755283054, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5917699365555377, "MaxKurtosisOfNumericAtts": 168.45048717975237, "MinMeansOfNumericAtts": -0.1355024875621891, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 376.8905472636816, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.475603989219074, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 6.1230422885572136, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -9.591536230669075, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 12.433020997865643, "MinStdDevOfNumericAtts": 0.00949566279626117, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.8612485151998488, "MaxStdDevOfNumericAtts": 239.22614397301774, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.39172026323908593, "Quartile3StdDevOfNumericAtts": 3.2466961868919917, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.34084577114427866, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 16.564137550426576, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 19.317700122575527, "Quartile1SkewnessOfNumericAtts": -0.08992558253781374, "AutoCorrelation": 0.40817499999999995, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3172848723135174 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "72", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "201", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nArCNO", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "2", "type": "numeric", "distinct": "140", "missing": "0", "min": "-18", "max": "3", "mean": "0", "stdev": "1" }, { "name": "NdsN", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "MATS1e", "index": "4", "type": "numeric", "distinct": "149", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.039", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SaasC", "index": "6", "type": "numeric", "distinct": "196", "missing": "0", "min": "-47", "max": "9", "mean": "3", "stdev": "4" }, { "name": "P_VSA_LogP_5", "index": "7", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "185", "mean": "63", "stdev": "35" }, { "name": "CATS2D_01_DA", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Yindex", "index": "9", "type": "numeric", "distinct": "162", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nPyrazoles", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NdO", "index": "11", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "O.058", "index": "12", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "1" }, { "name": "SdO", "index": "13", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "142", "mean": "13", "stdev": "16" }, { "name": "MATS1s", "index": "14", "type": "numeric", "distinct": "141", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SdsN", "index": "15", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SpMax1_Bh.s.", "index": "16", "type": "numeric", "distinct": "60", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Vindex", "index": "17", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS3s", "index": "18", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS7s", "index": "19", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "C.025", "index": "20", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "DECC", "index": "21", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "MATS7i", "index": "22", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nROH", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_AA", "index": "24", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_LL", "index": "25", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "38", "mean": "8", "stdev": "6" }, { "name": "ICR", "index": "26", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.074", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "28", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "Eig02_AEA.dm.", "index": "29", "type": "numeric", "distinct": "166", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Xindex", "index": "30", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsOH", "index": "31", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "261", "mean": "6", "stdev": "19" }, { "name": "AECC", "index": "32", "type": "numeric", "distinct": "177", "missing": "0", "min": "4", "max": "22", "mean": "12", "stdev": "3" }, { "name": "ATSC6e", "index": "33", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_LL", "index": "34", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "32", "mean": "6", "stdev": "5" }, { "name": "HVcpx", "index": "35", "type": "numeric", "distinct": "174", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_e_2", "index": "36", "type": "numeric", "distinct": "194", "missing": "0", "min": "49", "max": "324", "mean": "135", "stdev": "40" }, { "name": "P_VSA_s_3", "index": "37", "type": "numeric", "distinct": "186", "missing": "0", "min": "7", "max": "135", "mean": "41", "stdev": "18" }, { "name": "ATSC7e", "index": "38", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Eig02_EA.bo.", "index": "39", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "40", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IDE", "index": "41", "type": "numeric", "distinct": "176", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "42", "type": "numeric", "distinct": "184", "missing": "0", "min": "3", "max": "15", "mean": "7", "stdev": "2" }, { "name": "MATS1i", "index": "43", "type": "numeric", "distinct": "162", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.072", "index": "44", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS7i", "index": "45", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "46", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "NRS", "index": "47", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "1" }, { "name": "Eig09_AEA.dm.", "index": "48", "type": "numeric", "distinct": "171", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig08_AEA.dm.", "index": "49", "type": "numeric", "distinct": "178", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "TRS", "index": "50", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "66", "mean": "24", "stdev": "8" }, { "name": "Eta_sh_p", "index": "51", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "H.049", "index": "52", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "X2A", "index": "53", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS3e", "index": "54", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS7p", "index": "55", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X3A", "index": "56", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "57", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "1401", "mean": "90", "stdev": "97" }, { "name": "MAXDP", "index": "58", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "8", "mean": "5", "stdev": "1" }, { "name": "PDI", "index": "59", "type": "numeric", "distinct": "118", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SRW09", "index": "60", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "3" }, { "name": "MDDD", "index": "61", "type": "numeric", "distinct": "188", "missing": "0", "min": "3", "max": "286", "mean": "33", "stdev": "24" }, { "name": "P_VSA_p_3", "index": "62", "type": "numeric", "distinct": "194", "missing": "0", "min": "46", "max": "324", "mean": "148", "stdev": "47" }, { "name": "P_VSA_v_3", "index": "63", "type": "numeric", "distinct": "194", "missing": "0", "min": "46", "max": "324", "mean": "148", "stdev": "47" }, { "name": "nCIC", "index": "64", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "65", "type": "numeric", "distinct": "179", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SaaN", "index": "66", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "22", "mean": "8", "stdev": "5" }, { "name": "UNIP", "index": "67", "type": "numeric", "distinct": "120", "missing": "0", "min": "20", "max": "963", "mean": "133", "stdev": "84" }, { "name": "ECC", "index": "68", "type": "numeric", "distinct": "156", "missing": "0", "min": "45", "max": "2668", "mean": "377", "stdev": "239" } ], "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 }