{ "data_id": "29176", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2319", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2319", "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: CHEMBL2319 (TID: 13005), and it has 124 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": "2016-07-15 01:51:20", "update_comment": null, "last_update": "2016-07-15 01:51:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3385476\/data_53086.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2319", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2319 (TID: 13005), and it has 124 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": 124, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.5483870967741935, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.12607075001468715, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.18695219588566236, "Quartile2MeansOfNumericAtts": 3.590427419354839, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.2341943374804196, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.04587139549598009, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4931662702836828, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4530833839874604, "MaxKurtosisOfNumericAtts": 74.94968226879826, "MinMeansOfNumericAtts": -0.06021774193548386, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 135.63840322580646, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.6778545726182426, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 5.57183064516129, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.602698827485334, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 7.445171647961169, "MinStdDevOfNumericAtts": 0.008165062169438112, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7288226877694249, "MaxStdDevOfNumericAtts": 46.31053835044063, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.535061790608462, "Quartile3StdDevOfNumericAtts": 1.108182496632738, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8709677419354839, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.910489423772424, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 10.197283822821378, "Quartile1SkewnessOfNumericAtts": -0.6484581135770349, "AutoCorrelation": -0.08651219512195162, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.15791872309883498 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "80", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "124", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax2_Bh.p.", "index": "1", "type": "numeric", "distinct": "78", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "2", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "3", "type": "numeric", "distinct": "62", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "4", "type": "numeric", "distinct": "74", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "5", "type": "numeric", "distinct": "103", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "PCR", "index": "6", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "7", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "222", "mean": "112", "stdev": "44" }, { "name": "MATS1e", "index": "8", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.069", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NaasN", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "PCD", "index": "11", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "P_VSA_s_4", "index": "12", "type": "numeric", "distinct": "72", "missing": "0", "min": "38", "max": "208", "mean": "118", "stdev": "30" }, { "name": "piID", "index": "13", "type": "numeric", "distinct": "101", "missing": "0", "min": "6", "max": "15", "mean": "12", "stdev": "2" }, { "name": "C.028", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS6s", "index": "16", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AP", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "PDI", "index": "18", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Ui", "index": "19", "type": "numeric", "distinct": "24", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC05", "index": "20", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "nPyrazoles", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "22", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "23", "type": "numeric", "distinct": "107", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "1" }, { "name": "H.051", "index": "24", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.bo.", "index": "25", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "26", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "27", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_05_PL", "index": "28", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS3v", "index": "29", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.024", "index": "30", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "20", "mean": "10", "stdev": "4" }, { "name": "MATS6m", "index": "31", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.dm.", "index": "32", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax_AEA.dm.", "index": "33", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MATS6e", "index": "34", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nSO2N", "index": "35", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "MATS1v", "index": "36", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.034", "index": "37", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.i.", "index": "38", "type": "numeric", "distinct": "85", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "H.050", "index": "39", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "2" }, { "name": "nHDon", "index": "40", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "2" }, { "name": "CATS2D_06_PL", "index": "41", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "piPC04", "index": "42", "type": "numeric", "distinct": "91", "missing": "0", "min": "4", "max": "6", "mean": "6", "stdev": "0" }, { "name": "PW5", "index": "43", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1e", "index": "44", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "45", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "46", "type": "numeric", "distinct": "105", "missing": "0", "min": "10", "max": "14", "mean": "13", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "47", "type": "numeric", "distinct": "86", "missing": "0", "min": "18", "max": "232", "mean": "136", "stdev": "46" }, { "name": "nAB", "index": "48", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "28", "mean": "19", "stdev": "7" }, { "name": "SpMin5_Bh.v.", "index": "49", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS1i", "index": "50", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "51", "type": "numeric", "distinct": "25", "missing": "0", "min": "5", "max": "33", "mean": "22", "stdev": "7" }, { "name": "Uc", "index": "52", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "53", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "273", "mean": "55", "stdev": "44" }, { "name": "SpMAD_EA.bo.", "index": "54", "type": "numeric", "distinct": "99", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS1v", "index": "55", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS6e", "index": "56", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig09_AEA.ed.", "index": "57", "type": "numeric", "distinct": "97", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "58", "type": "numeric", "distinct": "97", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "1" }, { "name": "SM09_EA.bo.", "index": "59", "type": "numeric", "distinct": "104", "missing": "0", "min": "11", "max": "15", "mean": "14", "stdev": "1" }, { "name": "Eig02_EA.bo.", "index": "60", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "61", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "62", "type": "numeric", "distinct": "102", "missing": "0", "min": "14", "max": "18", "mean": "17", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "63", "type": "numeric", "distinct": "102", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "GATS6i", "index": "64", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nBnz", "index": "65", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "NdO", "index": "66", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" } ], "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 }