{ "data_id": "29092", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4261", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4261", "version": 9, "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: CHEMBL4261 (TID: 100325), and it has 217 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 01:38:52", "update_comment": null, "last_update": "2016-07-15 01:38:52", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3382978\/data_53052.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4261", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4261 (TID: 100325), and it has 217 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": 217, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 99.88020276225983, "MinMeansOfNumericAtts": 0.07468663594470046, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.532225298195037, "MaxMeansOfNumericAtts": 156.17130875576035, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 10.281539170506912, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.4890592981080393, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3SkewnessOfNumericAtts": 1.444555303192329, "MaxSkewnessOfNumericAtts": 8.65707601688206, "MinStdDevOfNumericAtts": 0.006977042792669322, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 0.6773370705070852, "MaxStdDevOfNumericAtts": 120.00479305679126, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.2270951285620697, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.0610967741935484, "MeanKurtosisOfNumericAtts": 5.13339640424911, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 9.367909347272853, "Quartile1SkewnessOfNumericAtts": 0.0667677863489529, "AutoCorrelation": 0.36160185185185223, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.24597719405787705, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.31336405529953915, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.3419345921657744, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.8167386212628902, "Quartile2MeansOfNumericAtts": 5.289622119815668, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.564288810568587, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4005159931234923, "Quartile2StdDevOfNumericAtts": 0.4456035728314542, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2769498721520407, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "160", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "217", "missing": "0", "identifier": "1", "distr": [] }, { "name": "X3A", "index": "1", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2A", "index": "2", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5A", "index": "3", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NNRS", "index": "4", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Rbrid", "index": "5", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "RCI", "index": "6", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "7", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCIR", "index": "8", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "30", "mean": "5", "stdev": "3" }, { "name": "D.Dtr12", "index": "9", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "801", "mean": "18", "stdev": "65" }, { "name": "piPC09", "index": "10", "type": "numeric", "distinct": "168", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "nR09", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.bo.", "index": "12", "type": "numeric", "distinct": "79", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "13", "type": "numeric", "distinct": "79", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC09", "index": "14", "type": "numeric", "distinct": "127", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "MPC08", "index": "15", "type": "numeric", "distinct": "105", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "X4A", "index": "16", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW4", "index": "17", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCIC", "index": "18", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "1" }, { "name": "TRS", "index": "19", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "56", "mean": "22", "stdev": "7" }, { "name": "SaaO", "index": "20", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "D.Dtr09", "index": "21", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "614", "mean": "26", "stdev": "65" }, { "name": "MPC04", "index": "22", "type": "numeric", "distinct": "76", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "C.034", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "piPC04", "index": "24", "type": "numeric", "distinct": "157", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC05", "index": "25", "type": "numeric", "distinct": "159", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "26", "type": "numeric", "distinct": "151", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "27", "type": "numeric", "distinct": "160", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "28", "type": "numeric", "distinct": "153", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "29", "type": "numeric", "distinct": "160", "missing": "0", "min": "15", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "30", "type": "numeric", "distinct": "161", "missing": "0", "min": "16", "max": "20", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "31", "type": "numeric", "distinct": "162", "missing": "0", "min": "17", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "32", "type": "numeric", "distinct": "160", "missing": "0", "min": "18", "max": "23", "mean": "21", "stdev": "1" }, { "name": "MPC06", "index": "33", "type": "numeric", "distinct": "100", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MWC04", "index": "34", "type": "numeric", "distinct": "136", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "35", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "36", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "37", "type": "numeric", "distinct": "90", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "38", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC05", "index": "39", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "X5v", "index": "40", "type": "numeric", "distinct": "204", "missing": "0", "min": "1", "max": "16", "mean": "3", "stdev": "2" }, { "name": "GATS3s", "index": "41", "type": "numeric", "distinct": "176", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MWC07", "index": "42", "type": "numeric", "distinct": "154", "missing": "0", "min": "9", "max": "11", "mean": "9", "stdev": "0" }, { "name": "piPC07", "index": "43", "type": "numeric", "distinct": "172", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "MWC08", "index": "44", "type": "numeric", "distinct": "158", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "45", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MWC05", "index": "46", "type": "numeric", "distinct": "150", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM06_EA.ri.", "index": "47", "type": "numeric", "distinct": "192", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "1" }, { "name": "GNar", "index": "48", "type": "numeric", "distinct": "106", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MWC10", "index": "49", "type": "numeric", "distinct": "162", "missing": "0", "min": "11", "max": "14", "mean": "12", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "50", "type": "numeric", "distinct": "170", "missing": "0", "min": "69", "max": "692", "mean": "156", "stdev": "120" }, { "name": "Qindex", "index": "51", "type": "numeric", "distinct": "29", "missing": "0", "min": "8", "max": "71", "mean": "23", "stdev": "12" }, { "name": "SpMax1_Bh.i.", "index": "52", "type": "numeric", "distinct": "91", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC06", "index": "53", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "piPC08", "index": "54", "type": "numeric", "distinct": "170", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "TPC", "index": "55", "type": "numeric", "distinct": "135", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "X4v", "index": "56", "type": "numeric", "distinct": "204", "missing": "0", "min": "1", "max": "18", "mean": "4", "stdev": "3" }, { "name": "SM08_EA.ri.", "index": "57", "type": "numeric", "distinct": "189", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "MWC09", "index": "58", "type": "numeric", "distinct": "160", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "0" }, { "name": "TWC", "index": "59", "type": "numeric", "distinct": "165", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "MWC06", "index": "60", "type": "numeric", "distinct": "158", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SRW08", "index": "61", "type": "numeric", "distinct": "145", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "MPC03", "index": "62", "type": "numeric", "distinct": "57", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "63", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "64", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piID", "index": "65", "type": "numeric", "distinct": "163", "missing": "0", "min": "7", "max": "13", "mean": "10", "stdev": "1" }, { "name": "GATS5s", "index": "66", "type": "numeric", "distinct": "193", "missing": "0", "min": "0", "max": "2", "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 }