{ "data_id": "33841", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4123", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4123", "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: CHEMBL4123 (TID: 12910), and it has 326 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 13:49:27", "update_comment": null, "last_update": "2016-07-15 13:49:27", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3515183\/data_35269.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-CHEMBL4123", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4123 (TID: 12910), and it has 326 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": 326, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 18.05547008526838, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6882957779240606, "MaxStdDevOfNumericAtts": 370.34416977745957, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.0346640416705587, "Quartile3StdDevOfNumericAtts": 23.699056958007404, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.3466257668711654, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 13.763830494395473, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 35.679383156720576, "Quartile1SkewnessOfNumericAtts": 0.7883101209374594, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.25180254636422345, "AutoCorrelation": -0.019083076923076567, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.3628867914131009, "Dimensionality": 0.13803680981595093, "MeanSkewnessOfNumericAtts": 2.0755421189925745, "Quartile2MeansOfNumericAtts": 6.8547546012269995, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 20.555709485491853, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.2736513413997947, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2264034649293967, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 4.831549357307068, "MaxKurtosisOfNumericAtts": 325.9999999999976, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 637.0844478527608, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.861635733614779, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 44.761503067484625, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.4262991970074014, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "251", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "326", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "254", "missing": "0", "min": "6", "max": "12", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "127", "missing": "0", "min": "29", "max": "56", "mean": "39", "stdev": "7" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "152", "missing": "0", "min": "23", "max": "60", "mean": "46", "stdev": "7" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "125", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "139", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "261", "missing": "0", "min": "206", "max": "1908", "mean": "637", "stdev": "370" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "17", "mean": "7", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "30", "mean": "12", "stdev": "7" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "102", "missing": "0", "min": "27", "max": "266", "mean": "89", "stdev": "57" }, { "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": "31", "missing": "0", "min": "3", "max": "48", "mean": "18", "stdev": "6" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "68", "missing": "0", "min": "15", "max": "149", "mean": "48", "stdev": "27" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "103", "missing": "0", "min": "28", "max": "271", "mean": "91", "stdev": "57" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "51", "missing": "0", "min": "11", "max": "96", "mean": "32", "stdev": "16" }, { "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": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "31", "missing": "0", "min": "3", "max": "52", "mean": "17", "stdev": "5" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "54", "mean": "15", "stdev": "14" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "4" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "69", "missing": "0", "min": "8", "max": "132", "mean": "43", "stdev": "31" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "36", "missing": "0", "min": "1", "max": "50", "mean": "14", "stdev": "10" }, { "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": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "23", "mean": "7", "stdev": "6" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "27", "mean": "6", "stdev": "5" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "61", "missing": "0", "min": "15", "max": "136", "mean": "45", "stdev": "26" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "20", "mean": "7", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "58", "mean": "15", "stdev": "14" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "104", "missing": "0", "min": "21", "max": "182", "mean": "59", "stdev": "30" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "260", "missing": "0", "min": "28", "max": "270", "mean": "89", "stdev": "58" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "262", "missing": "0", "min": "30", "max": "305", "mean": "101", "stdev": "66" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "259", "missing": "0", "min": "18", "max": "165", "mean": "56", "stdev": "33" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "263", "missing": "0", "min": "18", "max": "157", "mean": "53", "stdev": "32" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "33", "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 }