{ "data_id": "34807", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2425", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2425", "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: CHEMBL2425 (TID: 10457), and it has 679 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 16:20:37", "update_comment": null, "last_update": "2016-07-15 16:20:37", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3539583\/data_53098.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2425", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2425 (TID: 10457), and it has 679 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": 679, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.6609779289534763, "Dimensionality": 0.10014727540500737, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 2.0735508100147277, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.3376202902654675, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.128911341120063, "Quartile2SkewnessOfNumericAtts": 0.2332163550110935, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.24099232804229415, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6999733728282027, "MinMeansOfNumericAtts": 0.051621502209131066, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 90.07772216783434, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.8756213842766423, "MaxMeansOfNumericAtts": 205.03528571428572, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 4.475349042709867, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.1605101937533027, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.004633855309463422, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.009531089489358, "MaxSkewnessOfNumericAtts": 8.677301594468616, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.0651243767760401, "Quartile3StdDevOfNumericAtts": 1.0213331640616594, "MaxStdDevOfNumericAtts": 74.5919395030904, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8703357879234163, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 3.030031983635421, "Quartile1SkewnessOfNumericAtts": -0.678676088709897, "MeanMeansOfNumericAtts": 9.15298892137252, "Quartile1StdDevOfNumericAtts": 0.08874472737745305, "AutoCorrelation": -0.07501327433628308, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "379", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "679", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SRW09", "index": "1", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "3" }, { "name": "SRW07", "index": "2", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "D.Dtr09", "index": "3", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "397", "mean": "35", "stdev": "57" }, { "name": "nR09", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "C.043", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "D.Dtr05", "index": "6", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "144", "mean": "19", "stdev": "28" }, { "name": "nR05", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SRW05", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin1_Bh.p.", "index": "9", "type": "numeric", "distinct": "153", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "D.Dtr10", "index": "10", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "307", "mean": "70", "stdev": "67" }, { "name": "nR10", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NaaO", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nFuranes", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaO", "index": "14", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "DECC", "index": "15", "type": "numeric", "distinct": "303", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "16", "type": "numeric", "distinct": "226", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nR06", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin2_Bh.i.", "index": "18", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nPyridines", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "20", "type": "numeric", "distinct": "209", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ICR", "index": "21", "type": "numeric", "distinct": "254", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_07_DL", "index": "22", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SpMin2_Bh.s.", "index": "23", "type": "numeric", "distinct": "244", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "24", "type": "numeric", "distinct": "177", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "25", "type": "numeric", "distinct": "178", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "26", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "27", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "28", "type": "numeric", "distinct": "369", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig06_EA.ed.", "index": "29", "type": "numeric", "distinct": "302", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "30", "type": "numeric", "distinct": "302", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpMin1_Bh.i.", "index": "31", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_PL", "index": "32", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "33", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "D.Dtr06", "index": "34", "type": "numeric", "distinct": "449", "missing": "0", "min": "58", "max": "588", "mean": "205", "stdev": "75" }, { "name": "Eig06_EA", "index": "35", "type": "numeric", "distinct": "269", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "36", "type": "numeric", "distinct": "269", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "NaaNH", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaNH", "index": "38", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig06_EA.bo.", "index": "39", "type": "numeric", "distinct": "308", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "40", "type": "numeric", "distinct": "271", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "41", "type": "numeric", "distinct": "346", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nArNR2", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "43", "type": "numeric", "distinct": "116", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "44", "type": "numeric", "distinct": "116", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "45", "type": "numeric", "distinct": "116", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "46", "type": "numeric", "distinct": "116", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "47", "type": "numeric", "distinct": "508", "missing": "0", "min": "8", "max": "58", "mean": "26", "stdev": "9" }, { "name": "P_VSA_LogP_4", "index": "48", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "263", "mean": "68", "stdev": "42" }, { "name": "X3A", "index": "49", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "JGI3", "index": "50", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC6s", "index": "51", "type": "numeric", "distinct": "666", "missing": "0", "min": "14", "max": "245", "mean": "50", "stdev": "37" }, { "name": "SpMin1_Bh.e.", "index": "52", "type": "numeric", "distinct": "178", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X4A", "index": "53", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA", "index": "54", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "55", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "56", "type": "numeric", "distinct": "162", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "57", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDE", "index": "58", "type": "numeric", "distinct": "335", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "59", "type": "numeric", "distinct": "205", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_DA", "index": "60", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS6i", "index": "61", "type": "numeric", "distinct": "384", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.s.", "index": "62", "type": "numeric", "distinct": "73", "missing": "0", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "Eig06_AEA.bo.", "index": "63", "type": "numeric", "distinct": "294", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "64", "type": "numeric", "distinct": "231", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "65", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI10", "index": "66", "type": "numeric", "distinct": "117", "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 }