{ "data_id": "27609", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3863", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3863", "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: CHEMBL3863 (TID: 10903), and it has 192 rows and 66 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 21:58:56", "update_comment": null, "last_update": "2016-07-14 21:58:56", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3335531\/data_53091.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3863", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3863 (TID: 10903), and it has 192 rows and 66 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": 192, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.639078125, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.6970825914905734, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 18.288970071517415, "Quartile1SkewnessOfNumericAtts": 0.02129157499700335, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.10295726429524318, "AutoCorrelation": 0.3377801047120417, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.959796322865444, "Dimensionality": 0.3541666666666667, "MeanSkewnessOfNumericAtts": 0.6898019221474507, "Quartile2MeansOfNumericAtts": 1.5728385416666666, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 4.485665254166821, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6052960262245982, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.9559869691866352, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.28340826266434493, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 60.45522371994777, "MinMeansOfNumericAtts": -0.03339062499999999, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 463.15569791666667, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7011761238959786, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 4.393239583333333, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3420303626949175, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 7.049216455347039, "MinStdDevOfNumericAtts": 0.006493634871793116, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1007414164221099, "MaxStdDevOfNumericAtts": 125.68601921543383, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.2850029102891818, "Quartile3StdDevOfNumericAtts": 0.6392679283243599 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "106", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "192", "missing": "0", "identifier": "1", "distr": [] }, { "name": "BIC0", "index": "1", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC0", "index": "2", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_epsi_A", "index": "3", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "AAC", "index": "4", "type": "numeric", "distinct": "144", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "5", "type": "numeric", "distinct": "144", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Me", "index": "6", "type": "numeric", "distinct": "49", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.026", "index": "7", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "H.", "index": "8", "type": "numeric", "distinct": "92", "missing": "0", "min": "24", "max": "52", "mean": "45", "stdev": "5" }, { "name": "AMW", "index": "9", "type": "numeric", "distinct": "159", "missing": "0", "min": "6", "max": "12", "mean": "8", "stdev": "1" }, { "name": "Mv", "index": "10", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1m", "index": "11", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "12", "type": "numeric", "distinct": "114", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "13", "type": "numeric", "distinct": "114", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "N.071", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ZM1MulPer", "index": "15", "type": "numeric", "distinct": "187", "missing": "0", "min": "245", "max": "815", "mean": "452", "stdev": "109" }, { "name": "ATSC6e", "index": "16", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "JGI4", "index": "17", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin5_Bh.s.", "index": "18", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SsssCH", "index": "19", "type": "numeric", "distinct": "97", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArNR2", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC1", "index": "21", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC0", "index": "22", "type": "numeric", "distinct": "163", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "23", "type": "numeric", "distinct": "138", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "24", "type": "numeric", "distinct": "138", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nPyridines", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin2_Bh.s.", "index": "26", "type": "numeric", "distinct": "134", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "27", "type": "numeric", "distinct": "124", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "28", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "29", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "30", "type": "numeric", "distinct": "107", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "31", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax6_Bh.s.", "index": "32", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "8", "mean": "4", "stdev": "0" }, { "name": "GATS2i", "index": "33", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "34", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "DLS_cons", "index": "35", "type": "numeric", "distinct": "27", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "36", "type": "numeric", "distinct": "152", "missing": "0", "min": "11", "max": "14", "mean": "12", "stdev": "0" }, { "name": "GATS2m", "index": "37", "type": "numeric", "distinct": "152", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "38", "type": "numeric", "distinct": "141", "missing": "0", "min": "21", "max": "25", "mean": "22", "stdev": "1" }, { "name": "BIC1", "index": "39", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.052", "index": "40", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "GATS6p", "index": "41", "type": "numeric", "distinct": "157", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "42", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "43", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "164", "mean": "42", "stdev": "30" }, { "name": "ATSC1e", "index": "44", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ZM1Kup", "index": "45", "type": "numeric", "distinct": "180", "missing": "0", "min": "253", "max": "1014", "mean": "463", "stdev": "126" }, { "name": "SM13_EA.bo.", "index": "46", "type": "numeric", "distinct": "140", "missing": "0", "min": "18", "max": "22", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "47", "type": "numeric", "distinct": "144", "missing": "0", "min": "20", "max": "24", "mean": "21", "stdev": "1" }, { "name": "nCrs", "index": "48", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "3" }, { "name": "CIC5", "index": "49", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1s", "index": "50", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CIC1", "index": "51", "type": "numeric", "distinct": "174", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ON1V", "index": "52", "type": "numeric", "distinct": "175", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "IC1", "index": "53", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "54", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "55", "type": "numeric", "distinct": "152", "missing": "0", "min": "14", "max": "17", "mean": "15", "stdev": "1" }, { "name": "GATS2v", "index": "56", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "JGI3", "index": "57", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "58", "type": "numeric", "distinct": "117", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "Psi_e_A", "index": "59", "type": "numeric", "distinct": "160", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "60", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "C.029", "index": "61", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATSC3v", "index": "62", "type": "numeric", "distinct": "186", "missing": "0", "min": "5", "max": "26", "mean": "15", "stdev": "5" }, { "name": "RCI", "index": "63", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "64", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "65", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SIC5", "index": "66", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" } ], "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 }