{ "data_id": "27896", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3446", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3446", "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: CHEMBL3446 (TID: 17005), and it has 128 rows and 61 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": "2016-07-14 22:39:25", "update_comment": null, "last_update": "2016-07-14 22:39:25", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3343438\/data_52286.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3446", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3446 (TID: 17005), and it has 128 rows and 61 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": 128, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.82421875, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.7481202948278249, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.798259324596774, "Quartile1SkewnessOfNumericAtts": -0.43497416355511137, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1366663035127147, "AutoCorrelation": -0.039850393700787454, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.914785821052438, "Dimensionality": 0.4921875, "MeanSkewnessOfNumericAtts": -0.13523813179748845, "Quartile2MeansOfNumericAtts": 4.550921875, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 0.9059345134602982, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.1983887606563256, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -2.0320000000000005, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.43418920069190936, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 2.973358659046662, "MinMeansOfNumericAtts": -0.14828125, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 22.587828125, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.32136297038779815, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 7.2267109375, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.747512402069958, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 0.9176021037211309, "MinStdDevOfNumericAtts": 0.0063951068585508, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.043547854132613736, "MaxStdDevOfNumericAtts": 14.373094963908617, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.3743192935647177, "Quartile3StdDevOfNumericAtts": 0.9247589344567317 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "78", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "128", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NNRS", "index": "1", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RCI", "index": "2", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "3", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC06", "index": "4", "type": "numeric", "distinct": "102", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "5", "type": "numeric", "distinct": "108", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC08", "index": "6", "type": "numeric", "distinct": "108", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC09", "index": "7", "type": "numeric", "distinct": "112", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "piPC10", "index": "8", "type": "numeric", "distinct": "112", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "piPC05", "index": "9", "type": "numeric", "distinct": "100", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "PCR", "index": "10", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piPC04", "index": "11", "type": "numeric", "distinct": "100", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "NaaaC", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "nPyrazines", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "14", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "15", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "16", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nPyrroles", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "SaaaC", "index": "18", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "Eig01_EA.bo.", "index": "19", "type": "numeric", "distinct": "38", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "20", "type": "numeric", "distinct": "101", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM09_EA.bo.", "index": "21", "type": "numeric", "distinct": "93", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "22", "type": "numeric", "distinct": "94", "missing": "0", "min": "14", "max": "16", "mean": "15", "stdev": "1" }, { "name": "SM11_AEA.ri.", "index": "23", "type": "numeric", "distinct": "38", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "24", "type": "numeric", "distinct": "92", "missing": "0", "min": "15", "max": "18", "mean": "17", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "25", "type": "numeric", "distinct": "89", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "26", "type": "numeric", "distinct": "92", "missing": "0", "min": "17", "max": "21", "mean": "20", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "27", "type": "numeric", "distinct": "87", "missing": "0", "min": "19", "max": "23", "mean": "21", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "28", "type": "numeric", "distinct": "82", "missing": "0", "min": "20", "max": "24", "mean": "23", "stdev": "1" }, { "name": "SpDiam_EA.bo.", "index": "29", "type": "numeric", "distinct": "38", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "30", "type": "numeric", "distinct": "38", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS4v", "index": "31", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "32", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "33", "type": "numeric", "distinct": "52", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "PCD", "index": "34", "type": "numeric", "distinct": "111", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "C.033", "index": "35", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "H.048", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS4p", "index": "37", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nAB", "index": "38", "type": "numeric", "distinct": "12", "missing": "0", "min": "6", "max": "27", "mean": "15", "stdev": "6" }, { "name": "SaaN", "index": "39", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "SM07_EA.bo.", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "MPC07", "index": "41", "type": "numeric", "distinct": "77", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC08", "index": "42", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "43", "type": "numeric", "distinct": "42", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "44", "type": "numeric", "distinct": "51", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "45", "type": "numeric", "distinct": "42", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS6v", "index": "46", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "47", "type": "numeric", "distinct": "107", "missing": "0", "min": "8", "max": "10", "mean": "10", "stdev": "0" }, { "name": "N.073", "index": "48", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "MATS6v", "index": "49", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC03", "index": "50", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC09", "index": "51", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "52", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eta_betaP", "index": "53", "type": "numeric", "distinct": "29", "missing": "0", "min": "7", "max": "25", "mean": "15", "stdev": "4" }, { "name": "PW5", "index": "54", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4A", "index": "55", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM05_EA.bo.", "index": "56", "type": "numeric", "distinct": "92", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "ARR", "index": "57", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.029", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_LogP_6", "index": "59", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "54", "mean": "15", "stdev": "14" }, { "name": "X2A", "index": "60", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS5s", "index": "61", "type": "numeric", "distinct": "102", "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 }