{ "data_id": "25952", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3762", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3762", "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: CHEMBL3762 (TID: 10514), and it has 95 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": "2016-07-14 18:07:24", "update_comment": null, "last_update": "2016-07-14 18:07:24", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3289081\/data_52451.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3762", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3762 (TID: 10514), and it has 95 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": 95, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 4.216621052631579, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.5892685943807262, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 431.80908721804514, "Quartile1SkewnessOfNumericAtts": -0.6435225377889116, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.35044813895397514, "AutoCorrelation": 0.13076595744680852, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.5385680436714977, "Dimensionality": 0.6736842105263158, "MeanSkewnessOfNumericAtts": -0.3396128789138068, "Quartile2MeansOfNumericAtts": 6.932084210526316, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 355.06965290938535, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.512083261936712, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.3929096849837168, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8547988470868236, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 4.782277586889757, "MinMeansOfNumericAtts": 0.07189473684210526, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 26111.97894736842, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.3732725521888889, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 13.041747368421053, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.9956461946394181, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.5879502740142757, "MinStdDevOfNumericAtts": 0.0075208556612143315, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": -0.2677310648511956, "MaxStdDevOfNumericAtts": 22120.606769013804, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.067684261106732, "Quartile3StdDevOfNumericAtts": 1.6710459999445177 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "72", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "95", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MPC05", "index": "1", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC06", "index": "2", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MPC07", "index": "3", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "N.", "index": "4", "type": "numeric", "distinct": "45", "missing": "0", "min": "1", "max": "14", "mean": "4", "stdev": "2" }, { "name": "Eig01_AEA.ri.", "index": "5", "type": "numeric", "distinct": "29", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GATS1s", "index": "6", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "7", "type": "numeric", "distinct": "29", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC04", "index": "8", "type": "numeric", "distinct": "52", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X5", "index": "9", "type": "numeric", "distinct": "87", "missing": "0", "min": "4", "max": "12", "mean": "7", "stdev": "2" }, { "name": "LOC", "index": "10", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "piPC06", "index": "11", "type": "numeric", "distinct": "84", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "12", "type": "numeric", "distinct": "33", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "13", "type": "numeric", "distinct": "61", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "14", "type": "numeric", "distinct": "33", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "15", "type": "numeric", "distinct": "33", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X4A", "index": "16", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BAC", "index": "17", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "170", "mean": "61", "stdev": "51" }, { "name": "CATS2D_03_AL", "index": "18", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "6", "stdev": "4" }, { "name": "ZM2Kup", "index": "19", "type": "numeric", "distinct": "85", "missing": "0", "min": "211", "max": "672", "mean": "424", "stdev": "125" }, { "name": "TPC", "index": "20", "type": "numeric", "distinct": "79", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Wap", "index": "21", "type": "numeric", "distinct": "85", "missing": "0", "min": "2796", "max": "106155", "mean": "26112", "stdev": "22121" }, { "name": "Eig02_AEA.dm.", "index": "22", "type": "numeric", "distinct": "50", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "23", "type": "numeric", "distinct": "43", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_AEA.ed.", "index": "24", "type": "numeric", "distinct": "32", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "Eig03_EA.ed.", "index": "25", "type": "numeric", "distinct": "34", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "2" }, { "name": "GGI4", "index": "26", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "GGI5", "index": "27", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "MWC06", "index": "28", "type": "numeric", "distinct": "81", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "MWC07", "index": "29", "type": "numeric", "distinct": "85", "missing": "0", "min": "9", "max": "10", "mean": "9", "stdev": "0" }, { "name": "MWC08", "index": "30", "type": "numeric", "distinct": "83", "missing": "0", "min": "10", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MWC09", "index": "31", "type": "numeric", "distinct": "82", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "MWC10", "index": "32", "type": "numeric", "distinct": "80", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM02_EA.dm.", "index": "33", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM02_EA.ed.", "index": "34", "type": "numeric", "distinct": "73", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SM04_EA.dm.", "index": "35", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SM12_AEA.dm.", "index": "36", "type": "numeric", "distinct": "34", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "2" }, { "name": "SpAD_EA.dm.", "index": "37", "type": "numeric", "distinct": "49", "missing": "0", "min": "1", "max": "22", "mean": "13", "stdev": "6" }, { "name": "SRW10", "index": "38", "type": "numeric", "distinct": "86", "missing": "0", "min": "10", "max": "11", "mean": "10", "stdev": "0" }, { "name": "TWC", "index": "39", "type": "numeric", "distinct": "80", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM06_EA.ed.", "index": "40", "type": "numeric", "distinct": "71", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "1" }, { "name": "SM07_EA.ed.", "index": "41", "type": "numeric", "distinct": "64", "missing": "0", "min": "16", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM08_EA.ed.", "index": "42", "type": "numeric", "distinct": "65", "missing": "0", "min": "19", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM09_EA.ed.", "index": "43", "type": "numeric", "distinct": "64", "missing": "0", "min": "21", "max": "25", "mean": "23", "stdev": "1" }, { "name": "SM10_EA.ed.", "index": "44", "type": "numeric", "distinct": "64", "missing": "0", "min": "23", "max": "28", "mean": "25", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "45", "type": "numeric", "distinct": "61", "missing": "0", "min": "26", "max": "31", "mean": "28", "stdev": "1" }, { "name": "SM12_EA.ed.", "index": "46", "type": "numeric", "distinct": "57", "missing": "0", "min": "28", "max": "34", "mean": "30", "stdev": "1" }, { "name": "SM13_AEA.ed.", "index": "47", "type": "numeric", "distinct": "66", "missing": "0", "min": "24", "max": "28", "mean": "26", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "48", "type": "numeric", "distinct": "54", "missing": "0", "min": "30", "max": "36", "mean": "33", "stdev": "2" }, { "name": "SM14_EA.ed.", "index": "49", "type": "numeric", "distinct": "54", "missing": "0", "min": "32", "max": "39", "mean": "35", "stdev": "2" }, { "name": "SM15_AEA.ed.", "index": "50", "type": "numeric", "distinct": "65", "missing": "0", "min": "28", "max": "32", "mean": "30", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "51", "type": "numeric", "distinct": "56", "missing": "0", "min": "35", "max": "42", "mean": "38", "stdev": "2" }, { "name": "SpMAD_AEA.ed.", "index": "52", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X5A", "index": "53", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "54", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "55", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "SM08_EA.dm.", "index": "56", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "12", "mean": "8", "stdev": "4" }, { "name": "SM10_EA.dm.", "index": "57", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "15", "mean": "9", "stdev": "5" }, { "name": "SM12_EA.dm.", "index": "58", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "17", "mean": "11", "stdev": "6" }, { "name": "SM14_EA.dm.", "index": "59", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "20", "mean": "13", "stdev": "6" }, { "name": "SpDiam_EA.dm.", "index": "60", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "8", "mean": "5", "stdev": "2" }, { "name": "SpMax_EA.dm.", "index": "61", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "piPC07", "index": "62", "type": "numeric", "distinct": "86", "missing": "0", "min": "5", "max": "8", "mean": "6", "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 }