{ "data_id": "32501", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4158", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4158", "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: CHEMBL4158 (TID: 11535), and it has 176 rows and 68 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 10:22:42", "update_comment": null, "last_update": "2016-07-15 10:22:42", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3482709\/data_53318.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4158", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4158 (TID: 11535), and it has 176 rows and 68 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": 176, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3977272727272727, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8312414118046436, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.05908719559045905, "Quartile2MeansOfNumericAtts": 3.6160681818181817, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 670.2229499917592, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.22531612786698033, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.578789184714991, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6292853831720756, "MaxKurtosisOfNumericAtts": 15.806586073864947, "MinMeansOfNumericAtts": 0.22120454545454546, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 37270.31818181818, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.7264890469074676, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 7.147096590909091, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.3153261063467157, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.712935401417845, "MinStdDevOfNumericAtts": 0.020436387683698945, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8247922983306154, "MaxStdDevOfNumericAtts": 46079.80470197838, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.19331647272447205, "Quartile3StdDevOfNumericAtts": 2.3556891386879832, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.5304204545454545, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.7748689533550845, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 547.4763686594201, "Quartile1SkewnessOfNumericAtts": -0.8213493600464639, "AutoCorrelation": 0.372457142857143, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.22902269673232828 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "145", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "176", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Yindex", "index": "1", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "PCD", "index": "2", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpMax2_Bh.i.", "index": "3", "type": "numeric", "distinct": "106", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "4", "type": "numeric", "distinct": "112", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "5", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "6", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "27", "mean": "9", "stdev": "6" }, { "name": "piPC10", "index": "7", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMin4_Bh.i.", "index": "8", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DECC", "index": "9", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "6", "mean": "2", "stdev": "1" }, { "name": "piPC08", "index": "10", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Vindex", "index": "11", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "12", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMAD_EA.dm.", "index": "13", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ICR", "index": "14", "type": "numeric", "distinct": "128", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "15", "type": "numeric", "distinct": "101", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Xindex", "index": "16", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "17", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "piPC09", "index": "18", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "9", "mean": "7", "stdev": "1" }, { "name": "piID", "index": "19", "type": "numeric", "distinct": "148", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "2" }, { "name": "SaaCH", "index": "20", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "29", "mean": "12", "stdev": "7" }, { "name": "nCar", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "25", "mean": "13", "stdev": "5" }, { "name": "CATS2D_01_LL", "index": "22", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "24", "mean": "11", "stdev": "5" }, { "name": "C.028", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC07", "index": "24", "type": "numeric", "distinct": "150", "missing": "0", "min": "3", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "25", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "nAB", "index": "26", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "28", "mean": "14", "stdev": "6" }, { "name": "SaaN", "index": "27", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "4" }, { "name": "HVcpx", "index": "28", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "5", "mean": "3", "stdev": "0" }, { "name": "Psi_e_A", "index": "29", "type": "numeric", "distinct": "146", "missing": "0", "min": "8", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "30", "type": "numeric", "distinct": "146", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_EA.dm.", "index": "31", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "SaaaC", "index": "32", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.075", "index": "33", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "34", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "C.024", "index": "35", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "16", "mean": "6", "stdev": "4" }, { "name": "NaaCH", "index": "36", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "7", "stdev": "4" }, { "name": "SpMin4_Bh.p.", "index": "37", "type": "numeric", "distinct": "131", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "38", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "39", "type": "numeric", "distinct": "146", "missing": "0", "min": "1", "max": "187", "mean": "95", "stdev": "37" }, { "name": "SpMin4_Bh.v.", "index": "40", "type": "numeric", "distinct": "125", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM08_EA.dm.", "index": "41", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "14", "mean": "7", "stdev": "3" }, { "name": "SpMax2_Bh.p.", "index": "42", "type": "numeric", "distinct": "110", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_i_2", "index": "43", "type": "numeric", "distinct": "160", "missing": "0", "min": "29", "max": "245", "mean": "122", "stdev": "36" }, { "name": "Wap", "index": "44", "type": "numeric", "distinct": "151", "missing": "0", "min": "539", "max": "222359", "mean": "37270", "stdev": "46080" }, { "name": "AECC", "index": "45", "type": "numeric", "distinct": "143", "missing": "0", "min": "6", "max": "37", "mean": "12", "stdev": "4" }, { "name": "IDE", "index": "46", "type": "numeric", "distinct": "149", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NaaaC", "index": "47", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "TPC", "index": "48", "type": "numeric", "distinct": "140", "missing": "0", "min": "5", "max": "10", "mean": "8", "stdev": "1" }, { "name": "PCR", "index": "49", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piPC04", "index": "50", "type": "numeric", "distinct": "145", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC05", "index": "51", "type": "numeric", "distinct": "142", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "Me", "index": "52", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "53", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "3" }, { "name": "SpMax3_Bh.v.", "index": "54", "type": "numeric", "distinct": "140", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin5_Bh.m.", "index": "55", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS6e", "index": "56", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "57", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "4" }, { "name": "Eig07_EA.bo.", "index": "58", "type": "numeric", "distinct": "136", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax4_Bh.s.", "index": "59", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMin5_Bh.v.", "index": "60", "type": "numeric", "distinct": "134", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MAXDN", "index": "61", "type": "numeric", "distinct": "158", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "O.", "index": "62", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "24", "mean": "8", "stdev": "5" }, { "name": "SpMin6_Bh.e.", "index": "63", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "IC3", "index": "64", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM14_EA.dm.", "index": "65", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "25", "mean": "11", "stdev": "5" }, { "name": "SpMax3_Bh.p.", "index": "66", "type": "numeric", "distinct": "134", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "67", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "68", "type": "numeric", "distinct": "133", "missing": "0", "min": "-3", "max": "8", "mean": "3", "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 }