{ "data_id": "27368", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2411", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2411", "version": 8, "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: CHEMBL2411 (TID: 12020), and it has 118 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": "2016-07-14 21:24:45", "update_comment": null, "last_update": "2016-07-14 21:24:45", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3328247\/data_52605.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2411", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2411 (TID: 12020), and it has 118 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": 118, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.48950635593220365, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.4815459013678842, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.718642213983053, "Quartile1SkewnessOfNumericAtts": -0.27944998874369253, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1457495511884712, "AutoCorrelation": 0.1312564102564106, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.22438060552156935, "Dimensionality": 0.5508474576271186, "MeanSkewnessOfNumericAtts": 0.47629928713094716, "Quartile2MeansOfNumericAtts": 1.0260550847457628, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 7.892707408607222, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.41246784693228045, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.3958933498780364, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.42073267346831933, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 14.353338475551093, "MinMeansOfNumericAtts": -0.05433898305084746, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 154.73728813559325, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.716613802420209, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 4.801580508474577, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.1940645510705132, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.4817590405013075, "MinStdDevOfNumericAtts": 0.03668209149697966, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.3078361604890423, "MaxStdDevOfNumericAtts": 171.7042684212022, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5042099704822987, "Quartile3StdDevOfNumericAtts": 1.213201297852104 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "82", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "118", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS4e", "index": "1", "type": "numeric", "distinct": "107", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SIC5", "index": "2", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS4s", "index": "3", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "BIC5", "index": "4", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC5", "index": "5", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "BIC4", "index": "6", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_AA", "index": "7", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "8", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "67", "mean": "19", "stdev": "15" }, { "name": "CATS2D_06_AL", "index": "9", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "5", "stdev": "3" }, { "name": "MATS5v", "index": "10", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC4", "index": "11", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nN.CO.2", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "13", "type": "numeric", "distinct": "76", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA", "index": "14", "type": "numeric", "distinct": "63", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "15", "type": "numeric", "distinct": "63", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS4m", "index": "16", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI6", "index": "17", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr08", "index": "18", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "223", "mean": "17", "stdev": "42" }, { "name": "CATS2D_07_DA", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CIC4", "index": "20", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_AL", "index": "21", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "D.Dtr05", "index": "22", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "155", "mean": "57", "stdev": "51" }, { "name": "MATS5m", "index": "23", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS5v", "index": "24", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "25", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "N.068", "index": "26", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nRNR2", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "28", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "piPC10", "index": "29", "type": "numeric", "distinct": "89", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig03_EA.ri.", "index": "30", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig03_AEA.bo.", "index": "31", "type": "numeric", "distinct": "62", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMaxA_EA.bo.", "index": "32", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4e", "index": "33", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SRW09", "index": "34", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "3" }, { "name": "ATSC1p", "index": "35", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "14", "mean": "5", "stdev": "2" }, { "name": "N.067", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRNHR", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS7e", "index": "38", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.", "index": "39", "type": "numeric", "distinct": "58", "missing": "0", "min": "2", "max": "19", "mean": "8", "stdev": "3" }, { "name": "GGI5", "index": "40", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMAD_EA.dm.", "index": "41", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "42", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "43", "type": "numeric", "distinct": "61", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "D.Dtr10", "index": "44", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "950", "mean": "125", "stdev": "172" }, { "name": "CATS2D_07_DL", "index": "45", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "MATS4m", "index": "46", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS4s", "index": "47", "type": "numeric", "distinct": "107", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SRW07", "index": "48", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SpMin3_Bh.s.", "index": "49", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS6v", "index": "50", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "UNIP", "index": "51", "type": "numeric", "distinct": "68", "missing": "0", "min": "26", "max": "1032", "mean": "155", "stdev": "155" }, { "name": "GATS7v", "index": "52", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC2v", "index": "53", "type": "numeric", "distinct": "107", "missing": "0", "min": "5", "max": "30", "mean": "12", "stdev": "5" }, { "name": "SssNH", "index": "54", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "nCONN", "index": "55", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC4s", "index": "56", "type": "numeric", "distinct": "113", "missing": "0", "min": "15", "max": "118", "mean": "55", "stdev": "24" }, { "name": "CATS2D_06_DL", "index": "57", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nR08", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "C.041", "index": "59", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS2v", "index": "60", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC05", "index": "61", "type": "numeric", "distinct": "90", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC1m", "index": "62", "type": "numeric", "distinct": "93", "missing": "0", "min": "3", "max": "36", "mean": "13", "stdev": "6" }, { "name": "IC5", "index": "63", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "6", "mean": "5", "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 }