{ "data_id": "33159", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4973", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4973", "version": 10, "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: CHEMBL4973 (TID: 12640), and it has 80 rows and 62 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 12:03:44", "update_comment": null, "last_update": "2016-07-15 12:03:44", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3498287\/data_52450.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4973", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4973 (TID: 12640), and it has 80 rows and 62 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": 80, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.8, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.34527972027971954, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.612594244744953, "Quartile2MeansOfNumericAtts": 0.825, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.965735053150434, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5625581706669033, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9538517748236415, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4623481618702621, "MaxKurtosisOfNumericAtts": 12.52279544497823, "MinMeansOfNumericAtts": -0.11087499999999999, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 158.934975, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.8596368427222076, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 2.8192875, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.4388840321026806, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.495530249944469, "MinStdDevOfNumericAtts": 0.006550570078583266, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.548634897644162, "MaxStdDevOfNumericAtts": 65.09158908536547, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6381859960352982, "Quartile3StdDevOfNumericAtts": 1.1922783080824926, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.19999999999999996, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.7128934526189509, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.855892460317461, "Quartile1SkewnessOfNumericAtts": -0.3962287898008629, "AutoCorrelation": 0.20137974683544266, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.39277493797177815 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "50", "missing": "0", "target": "1", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "80", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC3s", "index": "1", "type": "numeric", "distinct": "75", "missing": "0", "min": "40", "max": "366", "mean": "102", "stdev": "46" }, { "name": "CATS2D_06_AL", "index": "2", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "4" }, { "name": "P_VSA_LogP_2", "index": "3", "type": "numeric", "distinct": "18", "missing": "0", "min": "2", "max": "61", "mean": "43", "stdev": "12" }, { "name": "C.017", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.019", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.020", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AP", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_AA", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_DN", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_DD", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_AP", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "JGI1", "index": "13", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1s", "index": "14", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCconj", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NdssC", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nR.Cs", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nR.Ct", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NRS", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "StN", "index": "20", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "4" }, { "name": "StsC", "index": "21", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC1e", "index": "22", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "23", "type": "numeric", "distinct": "74", "missing": "0", "min": "16", "max": "288", "mean": "77", "stdev": "51" }, { "name": "CATS2D_04_AL", "index": "24", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "Eig15_AEA.ri.", "index": "25", "type": "numeric", "distinct": "49", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eta_B_A", "index": "26", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_sh_p", "index": "27", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "JGT", "index": "28", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS2s", "index": "29", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_s_6", "index": "30", "type": "numeric", "distinct": "28", "missing": "0", "min": "100", "max": "250", "mean": "159", "stdev": "34" }, { "name": "SpMax3_Bh.v.", "index": "31", "type": "numeric", "distinct": "61", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "32", "type": "numeric", "distinct": "62", "missing": "0", "min": "22", "max": "260", "mean": "124", "stdev": "65" }, { "name": "P_VSA_e_5", "index": "33", "type": "numeric", "distinct": "14", "missing": "0", "min": "36", "max": "178", "mean": "108", "stdev": "39" }, { "name": "P_VSA_LogP_4", "index": "34", "type": "numeric", "distinct": "11", "missing": "0", "min": "63", "max": "180", "mean": "114", "stdev": "32" }, { "name": "N.072", "index": "35", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "HVcpx", "index": "36", "type": "numeric", "distinct": "69", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "N.074", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRCN", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nTB", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NtN", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NtsC", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "43", "type": "numeric", "distinct": "56", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "44", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "P_VSA_e_2", "index": "45", "type": "numeric", "distinct": "62", "missing": "0", "min": "4", "max": "196", "mean": "79", "stdev": "54" }, { "name": "SM13_AEA.ri.", "index": "46", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMin3_Bh.e.", "index": "47", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "48", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "49", "type": "numeric", "distinct": "57", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "NssNH", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.038", "index": "51", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AL", "index": "52", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "CATS2D_02_DA", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_DN", "index": "54", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DD", "index": "55", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_PL", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig05_EA.dm.", "index": "57", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRCO", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "59", "type": "numeric", "distinct": "13", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SssO", "index": "60", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "17", "mean": "2", "stdev": "4" }, { "name": "CATS2D_01_AN", "index": "61", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "62", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "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 }