{ "data_id": "32944", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5036", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5036", "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: CHEMBL5036 (TID: 20158), and it has 257 rows and 63 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 11:30:27", "update_comment": null, "last_update": "2016-07-15 11:30:27", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3492966\/data_52594.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5036", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5036 (TID: 20158), and it has 257 rows and 63 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": 257, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.2529182879377432, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.1753157189073602, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.08136114412790484, "Quartile2MeansOfNumericAtts": 4.045282101167315, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.158018929934706, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.013570675905128756, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9767817745754506, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.30916660467142487, "MaxKurtosisOfNumericAtts": 22.987331623403026, "MinMeansOfNumericAtts": -0.08105836575875486, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 206.1124280155642, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.35046550806548826, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 13.896070038910505, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.4559291410227875, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.3686350369825537, "MinStdDevOfNumericAtts": 0.020510500478140792, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3287443438148165, "MaxStdDevOfNumericAtts": 65.72143023601849, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9944921882214806, "Quartile3StdDevOfNumericAtts": 1.9843461321478668, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.8164338521400778, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.6187065097337946, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 20.058364421206225, "Quartile1SkewnessOfNumericAtts": -0.38851441383064045, "AutoCorrelation": 0.24514062499999967, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.19576383539904793 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "146", "missing": "0", "target": "1", "min": "5", "max": "11", "mean": "9", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "257", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax1_Bh.i.", "index": "1", "type": "numeric", "distinct": "52", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "2", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "134", "mean": "62", "stdev": "24" }, { "name": "CATS2D_05_AL", "index": "3", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "4" }, { "name": "SaaaC", "index": "4", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATSC6i", "index": "5", "type": "numeric", "distinct": "220", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "D.Dtr09", "index": "6", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "189", "mean": "76", "stdev": "66" }, { "name": "SpMin4_Bh.m.", "index": "7", "type": "numeric", "distinct": "145", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "8", "type": "numeric", "distinct": "209", "missing": "0", "min": "140", "max": "288", "mean": "206", "stdev": "37" }, { "name": "ATSC1i", "index": "9", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X2sol", "index": "10", "type": "numeric", "distinct": "181", "missing": "0", "min": "9", "max": "21", "mean": "13", "stdev": "2" }, { "name": "Eig01_EA.bo.", "index": "11", "type": "numeric", "distinct": "37", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "12", "type": "numeric", "distinct": "37", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "13", "type": "numeric", "distinct": "37", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "14", "type": "numeric", "distinct": "37", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MAXDP", "index": "15", "type": "numeric", "distinct": "211", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig11_EA", "index": "16", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM05_AEA.dm.", "index": "17", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS6s", "index": "18", "type": "numeric", "distinct": "210", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "19", "type": "numeric", "distinct": "68", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0sol", "index": "20", "type": "numeric", "distinct": "104", "missing": "0", "min": "15", "max": "29", "mean": "20", "stdev": "3" }, { "name": "ATS6v", "index": "21", "type": "numeric", "distinct": "202", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "22", "type": "numeric", "distinct": "199", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA.ri.", "index": "23", "type": "numeric", "distinct": "198", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax5_Bh.p.", "index": "24", "type": "numeric", "distinct": "164", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MATS7i", "index": "25", "type": "numeric", "distinct": "174", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "26", "type": "numeric", "distinct": "153", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ATS3m", "index": "27", "type": "numeric", "distinct": "194", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin8_Bh.m.", "index": "28", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Psi_e_0", "index": "29", "type": "numeric", "distinct": "228", "missing": "0", "min": "8", "max": "16", "mean": "11", "stdev": "2" }, { "name": "SsF", "index": "30", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "43", "mean": "14", "stdev": "6" }, { "name": "SpMax8_Bh.m.", "index": "31", "type": "numeric", "distinct": "121", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "S0K", "index": "32", "type": "numeric", "distinct": "106", "missing": "0", "min": "88", "max": "219", "mean": "141", "stdev": "26" }, { "name": "Eig15_AEA.bo.", "index": "33", "type": "numeric", "distinct": "116", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax8_Bh.e.", "index": "34", "type": "numeric", "distinct": "110", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "35", "type": "numeric", "distinct": "95", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SNar", "index": "36", "type": "numeric", "distinct": "69", "missing": "0", "min": "16", "max": "33", "mean": "23", "stdev": "3" }, { "name": "TIC1", "index": "37", "type": "numeric", "distinct": "211", "missing": "0", "min": "123", "max": "287", "mean": "198", "stdev": "31" }, { "name": "Eig08_AEA.ri.", "index": "38", "type": "numeric", "distinct": "189", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "AMR", "index": "39", "type": "numeric", "distinct": "228", "missing": "0", "min": "80", "max": "165", "mean": "119", "stdev": "16" }, { "name": "SpMax5_Bh.v.", "index": "40", "type": "numeric", "distinct": "175", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "41", "type": "numeric", "distinct": "149", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpAD_EA.ri.", "index": "42", "type": "numeric", "distinct": "243", "missing": "0", "min": "34", "max": "68", "mean": "49", "stdev": "7" }, { "name": "Eig03_AEA.bo.", "index": "43", "type": "numeric", "distinct": "96", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "44", "type": "numeric", "distinct": "187", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "NaaaC", "index": "45", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nR09", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PCD", "index": "47", "type": "numeric", "distinct": "149", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "48", "type": "numeric", "distinct": "138", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "49", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X1Mad", "index": "50", "type": "numeric", "distinct": "239", "missing": "0", "min": "10", "max": "20", "mean": "14", "stdev": "2" }, { "name": "Chi1_EA.ri.", "index": "51", "type": "numeric", "distinct": "240", "missing": "0", "min": "12", "max": "25", "mean": "18", "stdev": "2" }, { "name": "SpAD_AEA.bo.", "index": "52", "type": "numeric", "distinct": "193", "missing": "0", "min": "36", "max": "72", "mean": "52", "stdev": "7" }, { "name": "SpAD_AEA.ri.", "index": "53", "type": "numeric", "distinct": "244", "missing": "0", "min": "36", "max": "72", "mean": "51", "stdev": "7" }, { "name": "SpAD_EA", "index": "54", "type": "numeric", "distinct": "184", "missing": "0", "min": "36", "max": "72", "mean": "51", "stdev": "7" }, { "name": "Eig14_AEA.ed.", "index": "55", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ICR", "index": "56", "type": "numeric", "distinct": "133", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "57", "type": "numeric", "distinct": "143", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "nPyrimidines", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS1m", "index": "59", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X1sol", "index": "60", "type": "numeric", "distinct": "158", "missing": "0", "min": "10", "max": "21", "mean": "14", "stdev": "2" }, { "name": "Eig10_AEA.dm.", "index": "61", "type": "numeric", "distinct": "145", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "62", "type": "numeric", "distinct": "161", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig14_EA", "index": "63", "type": "numeric", "distinct": "95", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" } ], "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 }