{ "data_id": "34803", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL229", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL229", "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: CHEMBL229 (TID: 125), and it has 1425 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median).", "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 16:20:03", "update_comment": null, "last_update": "2016-07-15 16:20:03", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3539573\/data_34281.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL229", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL229 (TID: 125), and it has 1425 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1425, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 16.8106610727971, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.5617223645269582, "MaxStdDevOfNumericAtts": 119.15694995341593, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.49368939949320945, "Quartile3StdDevOfNumericAtts": 7.922099155327211, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6225035087719297, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 12.527268747256956, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 24.887610813397124, "Quartile1SkewnessOfNumericAtts": -0.047841766786872325, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3253518847771076, "AutoCorrelation": -0.22141292134831422, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.26263997368501935, "Dimensionality": 0.031578947368421054, "MeanSkewnessOfNumericAtts": 1.3441176361520268, "Quartile2MeansOfNumericAtts": 6.4013684210526325, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.841894574864133, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.2780442976234099, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7962702639417967, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.324600653080198, "MaxKurtosisOfNumericAtts": 280.99269984102375, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 426.7930877192982, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.9893126696562895, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 32.83438596491228, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7954562467682034, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "695", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "8", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1425", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "746", "missing": "0", "min": "6", "max": "13", "mean": "7", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "134", "missing": "0", "min": "30", "max": "57", "mean": "40", "stdev": "3" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "153", "missing": "0", "min": "19", "max": "60", "mean": "47", "stdev": "4" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "128", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "934", "missing": "0", "min": "147", "max": "795", "mean": "427", "stdev": "119" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "22", "mean": "6", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "27", "mean": "13", "stdev": "4" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "80", "missing": "0", "min": "21", "max": "115", "mean": "58", "stdev": "16" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "28", "mean": "15", "stdev": "4" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "45", "missing": "0", "min": "12", "max": "65", "mean": "34", "stdev": "9" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "85", "missing": "0", "min": "22", "max": "123", "mean": "61", "stdev": "17" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "36", "missing": "0", "min": "7", "max": "44", "mean": "23", "stdev": "7" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "28", "mean": "14", "stdev": "4" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "32", "mean": "9", "stdev": "4" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "58", "mean": "27", "stdev": "8" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "15", "mean": "7", "stdev": "3" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "1" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "42", "missing": "0", "min": "11", "max": "57", "mean": "31", "stdev": "9" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "13", "mean": "5", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "16", "mean": "7", "stdev": "3" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "95", "missing": "0", "min": "13", "max": "72", "mean": "42", "stdev": "12" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "935", "missing": "0", "min": "22", "max": "116", "mean": "58", "stdev": "17" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "941", "missing": "0", "min": "23", "max": "130", "mean": "66", "stdev": "19" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "905", "missing": "0", "min": "14", "max": "72", "mean": "38", "stdev": "10" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "941", "missing": "0", "min": "13", "max": "69", "mean": "36", "stdev": "10" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "11", "mean": "1", "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 }