{ "data_id": "32673", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5800", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5800", "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: CHEMBL5800 (TID: 101563), and it has 172 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 10:49:26", "update_comment": null, "last_update": "2016-07-15 10:49:26", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3486957\/data_36112.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-CHEMBL5800", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5800 (TID: 101563), and it has 172 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": 172, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 13.1148770486042, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.291768592647959, "MaxStdDevOfNumericAtts": 178.23135559647767, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.9167591823539474, "Quartile3StdDevOfNumericAtts": 10.656236431996955, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.7029156976744186, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 29.554381537505343, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 23.909627378435516, "Quartile1SkewnessOfNumericAtts": 0.7262296805349883, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.317116411665054, "AutoCorrelation": 0.4398654970760233, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 15.027308918103389, "Dimensionality": 0.2616279069767442, "MeanSkewnessOfNumericAtts": 3.2723796621778614, "Quartile2MeansOfNumericAtts": 5.6656133720930235, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.89289816150867, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 2.6042768792371183, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6662293063652185, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.0074657215367586, "MaxKurtosisOfNumericAtts": 171.99999999999983, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 431.7314534883721, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 34.40510590640491, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 31.353197674418603, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.33898924120552343, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "108", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "172", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "160", "missing": "0", "min": "6", "max": "15", "mean": "9", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "85", "missing": "0", "min": "29", "max": "52", "mean": "42", "stdev": "5" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "89", "missing": "0", "min": "22", "max": "55", "mean": "40", "stdev": "5" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "51", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "162", "missing": "0", "min": "192", "max": "1885", "mean": "432", "stdev": "178" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "76", "missing": "0", "min": "2", "max": "23", "mean": "7", "stdev": "4" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "30", "mean": "14", "stdev": "5" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "55", "missing": "0", "min": "18", "max": "257", "mean": "50", "stdev": "23" }, { "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": "26", "missing": "0", "min": "4", "max": "43", "mean": "17", "stdev": "6" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "47", "missing": "0", "min": "13", "max": "135", "mean": "32", "stdev": "13" }, { "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": "59", "missing": "0", "min": "19", "max": "260", "mean": "52", "stdev": "24" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "34", "missing": "0", "min": "8", "max": "86", "mean": "21", "stdev": "9" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "27", "missing": "0", "min": "4", "max": "41", "mean": "16", "stdev": "6" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "45", "mean": "5", "stdev": "5" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "125", "mean": "20", "stdev": "11" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "15", "missing": "0", "min": "3", "max": "46", "mean": "9", "stdev": "4" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "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": "10", "missing": "0", "min": "1", "max": "21", "mean": "3", "stdev": "2" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "23", "mean": "4", "stdev": "3" }, { "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": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "42", "missing": "0", "min": "13", "max": "132", "mean": "30", "stdev": "13" }, { "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": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "22", "mean": "7", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "61", "mean": "6", "stdev": "6" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "68", "missing": "0", "min": "18", "max": "167", "mean": "42", "stdev": "17" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "162", "missing": "0", "min": "19", "max": "261", "mean": "51", "stdev": "24" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "163", "missing": "0", "min": "20", "max": "294", "mean": "56", "stdev": "27" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "162", "missing": "0", "min": "13", "max": "160", "mean": "35", "stdev": "15" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "162", "missing": "0", "min": "13", "max": "154", "mean": "33", "stdev": "14" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "8", "mean": "2", "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 }