{ "data_id": "28948", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2232", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2232", "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: CHEMBL2232 (TID: 11126), and it has 14 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 01:17:25", "update_comment": null, "last_update": "2016-07-15 01:17:25", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3378538\/data_52016.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2232", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2232 (TID: 11126), and it has 14 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": 14, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.31621428571428567, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.0776331940695701, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 34.583279859484776, "Quartile1SkewnessOfNumericAtts": -0.47730854343651485, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.07201373828140033, "AutoCorrelation": 0.3688461538461537, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.7402305205140025, "Dimensionality": 4.428571428571429, "MeanSkewnessOfNumericAtts": 0.005397174031693377, "Quartile2MeansOfNumericAtts": 2.7537142857142856, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 18.15413834538058, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.026365666309863096, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -2.0911922852218257, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5524165940724386, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 7.271733833447272, "MinMeansOfNumericAtts": -6.398785714285714, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 849.9836428571429, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.588921659988661, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 11.392785714285715, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.4727364546206845, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.4052993411728285, "MinStdDevOfNumericAtts": 0.017950481336715746, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.51548230597788, "MaxStdDevOfNumericAtts": 452.969672189007, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.4812237894106437, "Quartile3StdDevOfNumericAtts": 5.759860847203408 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "12", "missing": "0", "target": "1", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "14", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ARR", "index": "1", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC3p", "index": "2", "type": "numeric", "distinct": "14", "missing": "0", "min": "7", "max": "38", "mean": "23", "stdev": "11" }, { "name": "ATSC4p", "index": "3", "type": "numeric", "distinct": "14", "missing": "0", "min": "8", "max": "39", "mean": "24", "stdev": "12" }, { "name": "ATSC5p", "index": "4", "type": "numeric", "distinct": "14", "missing": "0", "min": "7", "max": "44", "mean": "26", "stdev": "14" }, { "name": "BIC0", "index": "5", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BIC1", "index": "6", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_NL", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_05_NL", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_LL", "index": "9", "type": "numeric", "distinct": "9", "missing": "0", "min": "7", "max": "20", "mean": "15", "stdev": "4" }, { "name": "D.Dtr06", "index": "10", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "591", "mean": "276", "stdev": "212" }, { "name": "Eta_beta_A", "index": "11", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "12", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_C_A", "index": "13", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_FL_A", "index": "14", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_L_A", "index": "15", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1p", "index": "16", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS6m", "index": "17", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS3e", "index": "18", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3v", "index": "19", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5e", "index": "20", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5m", "index": "21", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCsp3", "index": "22", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "45", "mean": "27", "stdev": "16" }, { "name": "PDI", "index": "23", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_i_3", "index": "24", "type": "numeric", "distinct": "13", "missing": "0", "min": "275", "max": "1408", "mean": "850", "stdev": "453" }, { "name": "P_VSA_MR_1", "index": "25", "type": "numeric", "distinct": "11", "missing": "0", "min": "118", "max": "471", "mean": "358", "stdev": "117" }, { "name": "SdsN", "index": "26", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "20", "mean": "12", "stdev": "8" }, { "name": "SIC0", "index": "27", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC1", "index": "28", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "29", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "30", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.s.", "index": "31", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.m.", "index": "32", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "33", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X3v", "index": "34", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "18", "mean": "11", "stdev": "6" }, { "name": "CATS2D_05_AL", "index": "35", "type": "numeric", "distinct": "8", "missing": "0", "min": "2", "max": "14", "mean": "10", "stdev": "3" }, { "name": "GGI4", "index": "36", "type": "numeric", "distinct": "13", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "2" }, { "name": "S2K", "index": "37", "type": "numeric", "distinct": "14", "missing": "0", "min": "6", "max": "57", "mean": "33", "stdev": "20" }, { "name": "S3K", "index": "38", "type": "numeric", "distinct": "14", "missing": "0", "min": "3", "max": "43", "mean": "25", "stdev": "16" }, { "name": "Eig03_AEA.bo.", "index": "39", "type": "numeric", "distinct": "12", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SdssC", "index": "40", "type": "numeric", "distinct": "14", "missing": "0", "min": "-14", "max": "1", "mean": "-6", "stdev": "6" }, { "name": "SM05_EA.bo.", "index": "41", "type": "numeric", "distinct": "14", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "42", "type": "numeric", "distinct": "11", "missing": "0", "min": "2", "max": "28", "mean": "15", "stdev": "9" }, { "name": "CATS2D_06_AL", "index": "43", "type": "numeric", "distinct": "8", "missing": "0", "min": "4", "max": "17", "mean": "9", "stdev": "5" }, { "name": "Eig06_EA.ed.", "index": "44", "type": "numeric", "distinct": "12", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "2" }, { "name": "MATS3p", "index": "45", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM15_AEA.dm.", "index": "46", "type": "numeric", "distinct": "12", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "2" }, { "name": "Eig03_EA.ri.", "index": "47", "type": "numeric", "distinct": "13", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_08_LL", "index": "48", "type": "numeric", "distinct": "9", "missing": "0", "min": "5", "max": "17", "mean": "11", "stdev": "4" }, { "name": "MATS3m", "index": "49", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_F_A", "index": "50", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS2v", "index": "51", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.bo.", "index": "52", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AECC", "index": "53", "type": "numeric", "distinct": "13", "missing": "0", "min": "8", "max": "31", "mean": "21", "stdev": "8" }, { "name": "ALOGP2", "index": "54", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "98", "mean": "34", "stdev": "35" }, { "name": "AMR", "index": "55", "type": "numeric", "distinct": "14", "missing": "0", "min": "86", "max": "424", "mean": "257", "stdev": "132" }, { "name": "ATS1e", "index": "56", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATS1i", "index": "57", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATS1m", "index": "58", "type": "numeric", "distinct": "14", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS1p", "index": "59", "type": "numeric", "distinct": "14", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS1s", "index": "60", "type": "numeric", "distinct": "13", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" } ], "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 }