DEVELOPMENT... { "data_id": "29386", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4649", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4649", "version": 11, "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: CHEMBL4649 (TID: 10796), and it has 536 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": "unknown", "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 02:22:22", "update_comment": null, "last_update": "2016-07-15 02:22:22", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3391140\/data_53163.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4649", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4649 (TID: 10796), and it has 536 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": 536, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.52941176470588, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.07435516482712279, "Quartile1MeansOfNumericAtts": 0.9464664179104477, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.2058521204644839, "Quartile1StdDevOfNumericAtts": 0.08623797582667773, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.0060423558290594, "Quartile2MeansOfNumericAtts": 2.9813432835820897, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.6508960802600596, "Quartile2StdDevOfNumericAtts": 0.311612995647411, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 12.919017922406363, "Quartile3MeansOfNumericAtts": 6.940298507462681, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 2.065310941026227, "Quartile3StdDevOfNumericAtts": 2.193371874203386, "AutoCorrelation": 0.09298130841121581, "MeanMeansOfNumericAtts": 10.246431610603699, "ClassEntropy": null, "Dimensionality": 0.12686567164179105, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 129.24029874185925, "MaxMeansOfNumericAtts": 200.40506529850748, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 11.286024137341611, "MaxStdDevOfNumericAtts": 139.86333509872995, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 21.70760627207881, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 2.1207293759951034, "MeanStdDevOfNumericAtts": 6.045705629074604, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1283173770827704, "MinMeansOfNumericAtts": -0.10229477611940299, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -6.296408079821677, "MinStdDevOfNumericAtts": 0.011747603727245952, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "301", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "50", "type": "numeric", "distinct": "97", "missing": "0", "min": "31", "max": "50", "mean": "39", "stdev": "3" }, { "name": "SM13_AEA.ri.", "index": "35", "type": "numeric", "distinct": "237", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "D.Dtr06", "index": "49", "type": "numeric", "distinct": "316", "missing": "0", "min": "85", "max": "1815", "mean": "200", "stdev": "140" }, { "name": "SpMaxA_AEA.dm.", "index": "48", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DLS_04", "index": "47", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_3", "index": "46", "type": "numeric", "distinct": "359", "missing": "0", "min": "12", "max": "429", "mean": "36", "stdev": "31" }, { "name": "SdO", "index": "45", "type": "numeric", "distinct": "279", "missing": "0", "min": "0", "max": "739", "mean": "15", "stdev": "59" }, { "name": "SpAD_EA.bo.", "index": "44", "type": "numeric", "distinct": "345", "missing": "0", "min": "36", "max": "563", "mean": "57", "stdev": "40" }, { "name": "SpMin2_Bh.e.", "index": "43", "type": "numeric", "distinct": "181", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS7i", "index": "42", "type": "numeric", "distinct": "329", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "41", "type": "numeric", "distinct": "134", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "40", "type": "numeric", "distinct": "183", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCXr.", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCconjX", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.020", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "36", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "34", "type": "numeric", "distinct": "237", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS3i", "index": "51", "type": "numeric", "distinct": "315", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SdsCH", "index": "52", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "GATS7i", "index": "53", "type": "numeric", "distinct": "347", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "54", "type": "numeric", "distinct": "141", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCbH", "index": "55", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "SpMax2_Bh.v.", "index": "56", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ARR", "index": "57", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "58", "type": "numeric", "distinct": "245", "missing": "0", "min": "15", "max": "23", "mean": "19", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "59", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "60", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "61", "type": "numeric", "distinct": "164", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "62", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_s_4", "index": "63", "type": "numeric", "distinct": "234", "missing": "0", "min": "30", "max": "343", "mean": "76", "stdev": "31" }, { "name": "Eig01_EA.ed.", "index": "64", "type": "numeric", "distinct": "213", "missing": "0", "min": "9", "max": "15", "mean": "12", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "65", "type": "numeric", "distinct": "213", "missing": "0", "min": "9", "max": "15", "mean": "12", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "66", "type": "numeric", "distinct": "269", "missing": "0", "min": "33", "max": "41", "mean": "37", "stdev": "1" }, { "name": "P_VSA_LogP_3", "index": "8", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "279", "mean": "31", "stdev": "26" }, { "name": "CATS2D_02_LL", "index": "16", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "44", "mean": "7", "stdev": "5" }, { "name": "SpMin3_Bh.i.", "index": "15", "type": "numeric", "distinct": "216", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nBnz", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATSC3e", "index": "13", "type": "numeric", "distinct": "358", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "12", "type": "numeric", "distinct": "187", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Ui", "index": "11", "type": "numeric", "distinct": "20", "missing": "0", "min": "3", "max": "6", "mean": "3", "stdev": "0" }, { "name": "nCsp2", "index": "10", "type": "numeric", "distinct": "20", "missing": "0", "min": "7", "max": "67", "mean": "12", "stdev": "5" }, { "name": "C.024", "index": "9", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "PCR", "index": "17", "type": "numeric", "distinct": "153", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RBF", "index": "7", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaCH", "index": "6", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "SaaCH", "index": "5", "type": "numeric", "distinct": "469", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "4" }, { "name": "Eta_beta_A", "index": "4", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "3", "type": "numeric", "distinct": "202", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCar", "index": "2", "type": "numeric", "distinct": "16", "missing": "0", "min": "4", "max": "23", "mean": "9", "stdev": "4" }, { "name": "Eta_betaP_A", "index": "1", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCb.", "index": "25", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "X3v", "index": "33", "type": "numeric", "distinct": "445", "missing": "0", "min": "3", "max": "55", "mean": "5", "stdev": "4" }, { "name": "MATS1p", "index": "32", "type": "numeric", "distinct": "193", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "31", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "MATS1v", "index": "30", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssCH2", "index": "29", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "59", "mean": "3", "stdev": "5" }, { "name": "PDI", "index": "28", "type": "numeric", "distinct": "107", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCsp3", "index": "27", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "141", "mean": "9", "stdev": "11" }, { "name": "Mi", "index": "26", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "536", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eta_C_A", "index": "24", "type": "numeric", "distinct": "257", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SssCH2", "index": "23", "type": "numeric", "distinct": "433", "missing": "0", "min": "-24", "max": "8", "mean": "2", "stdev": "3" }, { "name": "SpMaxA_EA.ed.", "index": "22", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "21", "type": "numeric", "distinct": "185", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "20", "type": "numeric", "distinct": "224", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "RBN", "index": "19", "type": "numeric", "distinct": "14", "missing": "0", "min": "1", "max": "163", "mean": "7", "stdev": "12" }, { "name": "MATS3i", "index": "18", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "0", "mean": "0", "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 }