{ "data_id": "31506", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2870", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2870", "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: CHEMBL2870 (TID: 12818), and it has 86 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 07:45:22", "update_comment": null, "last_update": "2016-07-15 07:45:22", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3451418\/data_52569.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2870", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2870 (TID: 12818), and it has 86 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": 86, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 9.012120729662442, "MinMeansOfNumericAtts": -0.027651162790697667, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.3828156161257419, "MaxMeansOfNumericAtts": 18.80143023255814, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 3.774877906976744, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0188576077133715, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3SkewnessOfNumericAtts": 1.0507599511510328, "MaxSkewnessOfNumericAtts": 2.630884986805827, "MinStdDevOfNumericAtts": 0.021031915035688013, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 0.9918075536670758, "MaxStdDevOfNumericAtts": 12.066127899343291, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7966602587811562, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1395348837209307, "MeanKurtosisOfNumericAtts": -0.003268701463824686, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 2.7009305959302328, "Quartile1SkewnessOfNumericAtts": -0.39607037480824375, "AutoCorrelation": 0.3511529411764707, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.28258717309304193, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.7558139534883721, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.5194924316107548, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.22261823469313705, "Quartile2MeansOfNumericAtts": 2.1152383720930237, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.8834437516103816, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.19510897509314726, "Quartile2StdDevOfNumericAtts": 0.3960037810300746, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4753053933498468, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "68", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "86", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig07_AEA.bo.", "index": "1", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig07_AEA.dm.", "index": "2", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_03_PL", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_PL", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig07_AEA.ri.", "index": "5", "type": "numeric", "distinct": "76", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA", "index": "6", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig07_EA.ri.", "index": "7", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "8", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "9", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA", "index": "10", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA.ed.", "index": "11", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "12", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM03_AEA.ri.", "index": "13", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM15_AEA.bo.", "index": "14", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig05_EA", "index": "15", "type": "numeric", "distinct": "59", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "16", "type": "numeric", "distinct": "59", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "17", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "18", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "19", "type": "numeric", "distinct": "70", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig07_EA.ed.", "index": "20", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM02_AEA.ri.", "index": "21", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MATS2m", "index": "22", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "23", "type": "numeric", "distinct": "35", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "24", "type": "numeric", "distinct": "59", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "25", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig12_AEA.ed.", "index": "26", "type": "numeric", "distinct": "53", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "ATS6v", "index": "27", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig11_AEA.ed.", "index": "28", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.019", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.040", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_05_PL", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_AL", "index": "32", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "23", "mean": "7", "stdev": "6" }, { "name": "Eig08_AEA.dm.", "index": "33", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig08_AEA.ed.", "index": "34", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig10_AEA.ed.", "index": "35", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MAXDP", "index": "36", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "N.068", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCconj", "index": "38", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nDB", "index": "39", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "NdssC", "index": "40", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "nRCONH2", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nR.Cs", "index": "42", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nRNR2", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SdO", "index": "44", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "39", "mean": "19", "stdev": "12" }, { "name": "SpMaxA_EA.bo.", "index": "45", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_AL", "index": "46", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "16", "mean": "5", "stdev": "3" }, { "name": "Eig09_AEA.ed.", "index": "47", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig05_EA.ri.", "index": "48", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "49", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "50", "type": "numeric", "distinct": "56", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS7m", "index": "51", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.052", "index": "52", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "3" }, { "name": "nRCONHR", "index": "53", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssN", "index": "54", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SRW06", "index": "55", "type": "numeric", "distinct": "62", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SRW08", "index": "56", "type": "numeric", "distinct": "61", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "GATS5m", "index": "57", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS4p", "index": "58", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "59", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "60", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Eig06_EA", "index": "61", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "62", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "63", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "2", "mean": "2", "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 }