{ "data_id": "34857", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1977", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1977", "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: CHEMBL1977 (TID: 64), and it has 358 rows and 65 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 16:28:37", "update_comment": null, "last_update": "2016-07-15 16:28:37", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3540965\/data_52924.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-CHEMBL1977", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1977 (TID: 64), and it has 358 rows and 65 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": 358, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.07468531313933, "MinStdDevOfNumericAtts": 0.01977099875053126, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8687136362284812, "MaxStdDevOfNumericAtts": 82.19080310267296, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.1328469362980071, "Quartile3StdDevOfNumericAtts": 1.2192023985205314, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4986033519553073, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.4914142177409868, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.84524915354664, "Quartile1SkewnessOfNumericAtts": -0.11855714821693855, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4532006922517814, "AutoCorrelation": 0.5574985994397762, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.6651485200209999, "Dimensionality": 0.1871508379888268, "MeanSkewnessOfNumericAtts": 0.40917274141993965, "Quartile2MeansOfNumericAtts": 0.9895684357541896, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.8822459755268306, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5355026631428363, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7814637760186165, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8159573851143742, "MaxKurtosisOfNumericAtts": 4.242082796772348, "MinMeansOfNumericAtts": -0.22574581005586564, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 129.81559217877094, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.20051179975566769, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 2.216240921787711, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0576988148127195, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "164", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "358", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig04_EA.dm.", "index": "1", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NdO", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "CATS2D_01_AA", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "N.076", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArNO2", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NddsN", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.061", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nROH", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.056", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NsOH", "index": "10", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.058", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "2" }, { "name": "C.040", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nHet", "index": "13", "type": "numeric", "distinct": "12", "missing": "0", "min": "2", "max": "14", "mean": "6", "stdev": "3" }, { "name": "CATS2D_04_AA", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.004", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nCq", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AA", "index": "17", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "MATS1s", "index": "18", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nOHs", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NssssC", "index": "20", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.s.", "index": "21", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC1", "index": "22", "type": "numeric", "distinct": "230", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.016", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "NdsCH", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "nR.Cs", "index": "25", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "NaaCH", "index": "26", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "4" }, { "name": "NddssS", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "S.110", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SdsCH", "index": "29", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "nBnz", "index": "30", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Me", "index": "31", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCrq", "index": "32", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nS", "index": "33", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "C.005", "index": "34", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MATS1i", "index": "35", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2s", "index": "36", "type": "numeric", "distinct": "193", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.026", "index": "37", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "H.050", "index": "38", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "nHDon", "index": "39", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_3", "index": "40", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "171", "mean": "74", "stdev": "48" }, { "name": "GATS5p", "index": "41", "type": "numeric", "distinct": "198", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IC4", "index": "42", "type": "numeric", "distinct": "212", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "43", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArCONHR", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS3m", "index": "45", "type": "numeric", "distinct": "189", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_AEA.ed.", "index": "46", "type": "numeric", "distinct": "168", "missing": "0", "min": "28", "max": "33", "mean": "31", "stdev": "1" }, { "name": "C.015", "index": "47", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NdCH2", "index": "48", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nR.Cp", "index": "49", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Hypertens.80", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nRCONR2", "index": "52", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "53", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM14_AEA.ed.", "index": "54", "type": "numeric", "distinct": "172", "missing": "0", "min": "26", "max": "30", "mean": "29", "stdev": "1" }, { "name": "SM08_EA.ed.", "index": "55", "type": "numeric", "distinct": "171", "missing": "0", "min": "18", "max": "23", "mean": "21", "stdev": "1" }, { "name": "CATS2D_07_DA", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ATSC5s", "index": "57", "type": "numeric", "distinct": "273", "missing": "0", "min": "17", "max": "379", "mean": "130", "stdev": "82" }, { "name": "DLS_05", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS2e", "index": "59", "type": "numeric", "distinct": "203", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM13_AEA.ed.", "index": "60", "type": "numeric", "distinct": "169", "missing": "0", "min": "24", "max": "28", "mean": "27", "stdev": "1" }, { "name": "SM12_AEA.ed.", "index": "61", "type": "numeric", "distinct": "176", "missing": "0", "min": "23", "max": "26", "mean": "25", "stdev": "1" }, { "name": "O.", "index": "62", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "18", "mean": "7", "stdev": "4" }, { "name": "SddsN", "index": "63", "type": "numeric", "distinct": "66", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM11_AEA.ed.", "index": "64", "type": "numeric", "distinct": "183", "missing": "0", "min": "21", "max": "24", "mean": "23", "stdev": "1" }, { "name": "SM10_AEA.ed.", "index": "65", "type": "numeric", "distinct": "175", "missing": "0", "min": "19", "max": "22", "mean": "21", "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 }