{ "data_id": "31640", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2128", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2128", "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: CHEMBL2128 (TID: 10958), and it has 107 rows and 62 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 08:07:20", "update_comment": null, "last_update": "2016-07-15 08:07:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3455280\/data_52371.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2128", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2128 (TID: 10958), and it has 107 rows and 62 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": 107, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 12.315813982592958, "MinMeansOfNumericAtts": -0.10878504672897196, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.622562119770253, "MaxMeansOfNumericAtts": 30424.635514018686, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 10.2883738317757, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.172092419786261, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3SkewnessOfNumericAtts": 0.0176265342247324, "MaxSkewnessOfNumericAtts": 2.77790527857087, "MinStdDevOfNumericAtts": 0.010337728467670008, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 0.8440614333251724, "MaxStdDevOfNumericAtts": 26689.202673497548, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.0511671699808125, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.935429906542056, "MeanKurtosisOfNumericAtts": 1.4525106060041695, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 491.14103842159915, "Quartile1SkewnessOfNumericAtts": -0.9475528346281988, "AutoCorrelation": -0.34544339622641473, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3558179112958509, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.5981308411214953, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.7173876836781194, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.44086276863230817, "Quartile2MeansOfNumericAtts": 6.081392523364486, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 425.34536098861355, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.7042690970580772, "Quartile2StdDevOfNumericAtts": 0.5111024195804644, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.940591554918845, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "77", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "107", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM11_EA.bo.", "index": "1", "type": "numeric", "distinct": "92", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "2", "type": "numeric", "distinct": "93", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "3", "type": "numeric", "distinct": "92", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "4", "type": "numeric", "distinct": "90", "missing": "0", "min": "18", "max": "22", "mean": "21", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "5", "type": "numeric", "distinct": "93", "missing": "0", "min": "19", "max": "24", "mean": "22", "stdev": "1" }, { "name": "MPC08", "index": "6", "type": "numeric", "distinct": "69", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MPC06", "index": "7", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC8e", "index": "8", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATSC8s", "index": "9", "type": "numeric", "distinct": "98", "missing": "0", "min": "20", "max": "502", "mean": "88", "stdev": "69" }, { "name": "TPC", "index": "10", "type": "numeric", "distinct": "85", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "1" }, { "name": "piPC04", "index": "11", "type": "numeric", "distinct": "87", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC05", "index": "12", "type": "numeric", "distinct": "61", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MWC06", "index": "13", "type": "numeric", "distinct": "88", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "14", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "15", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "16", "type": "numeric", "distinct": "63", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "17", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "18", "type": "numeric", "distinct": "93", "missing": "0", "min": "12", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "19", "type": "numeric", "distinct": "90", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "20", "type": "numeric", "distinct": "91", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "1" }, { "name": "X3A", "index": "21", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "22", "type": "numeric", "distinct": "93", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "Eig10_AEA.bo.", "index": "23", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "1" }, { "name": "Eig04_EA.ed.", "index": "24", "type": "numeric", "distinct": "71", "missing": "0", "min": "3", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM13_AEA.dm.", "index": "25", "type": "numeric", "distinct": "71", "missing": "0", "min": "3", "max": "12", "mean": "8", "stdev": "1" }, { "name": "piPC06", "index": "26", "type": "numeric", "distinct": "90", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "27", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "MWC07", "index": "28", "type": "numeric", "distinct": "91", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "MWC08", "index": "29", "type": "numeric", "distinct": "86", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SIC5", "index": "30", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS4s", "index": "31", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC05", "index": "32", "type": "numeric", "distinct": "89", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MPC07", "index": "33", "type": "numeric", "distinct": "70", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MWC09", "index": "34", "type": "numeric", "distinct": "89", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "TWC", "index": "35", "type": "numeric", "distinct": "89", "missing": "0", "min": "11", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM05_EA.bo.", "index": "36", "type": "numeric", "distinct": "85", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "37", "type": "numeric", "distinct": "79", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "X5sol", "index": "38", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "11", "mean": "7", "stdev": "2" }, { "name": "IC3", "index": "39", "type": "numeric", "distinct": "90", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MWC10", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "41", "type": "numeric", "distinct": "67", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "42", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Wap", "index": "43", "type": "numeric", "distinct": "90", "missing": "0", "min": "699", "max": "154193", "mean": "30425", "stdev": "26689" }, { "name": "SM04_EA.bo.", "index": "44", "type": "numeric", "distinct": "87", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "45", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SRW10", "index": "46", "type": "numeric", "distinct": "87", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MPC09", "index": "47", "type": "numeric", "distinct": "68", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC08", "index": "48", "type": "numeric", "distinct": "94", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "49", "type": "numeric", "distinct": "90", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "50", "type": "numeric", "distinct": "69", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS8s", "index": "51", "type": "numeric", "distinct": "95", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig10_EA.bo.", "index": "52", "type": "numeric", "distinct": "50", "missing": "0", "min": "-2", "max": "2", "mean": "2", "stdev": "1" }, { "name": "Eig11_AEA.bo.", "index": "53", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig11_EA.bo.", "index": "54", "type": "numeric", "distinct": "59", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "X5", "index": "55", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "11", "mean": "7", "stdev": "2" }, { "name": "Eig12_AEA.ed.", "index": "56", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig02_EA.bo.", "index": "57", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "58", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piID", "index": "59", "type": "numeric", "distinct": "90", "missing": "0", "min": "6", "max": "16", "mean": "11", "stdev": "2" }, { "name": "PCD", "index": "60", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "MPC04", "index": "61", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_FL", "index": "62", "type": "numeric", "distinct": "91", "missing": "0", "min": "3", "max": "11", "mean": "8", "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 }