{ "data_id": "40199", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1901", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1901", "version": 12, "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: CHEMBL1901 (TID: 10472), and it has 455 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": "2016-07-16 10:37:41", "update_comment": null, "last_update": "2016-07-16 10:37:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3690928\/data_33922.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-CHEMBL1901", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1901 (TID: 10472), and it has 455 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": 455, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 7.9010713778316815, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.2442098803858777, "MaxStdDevOfNumericAtts": 281.59180254052, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.3292423781418691, "Quartile3StdDevOfNumericAtts": 18.608658750110624, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6318159340659341, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 5.135667364360154, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 35.042432867132874, "Quartile1SkewnessOfNumericAtts": 0.901098915615363, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3685802072248856, "AutoCorrelation": 0.13963215859030806, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 4.319581552160188, "Dimensionality": 0.0989010989010989, "MeanSkewnessOfNumericAtts": 1.774507473114159, "Quartile2MeansOfNumericAtts": 6.768056043956044, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 15.472381911704911, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.9126890321337218, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8835549058112853, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.455191001106046, "MaxKurtosisOfNumericAtts": 60.6936976205826, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 636.6575824175825, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.762916342708581, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 42.40406593406593, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8191625431850956, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "259", "missing": "0", "target": "1", "min": "5", "max": "11", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "455", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "307", "missing": "0", "min": "7", "max": "14", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "109", "missing": "0", "min": "33", "max": "49", "mean": "42", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "124", "missing": "0", "min": "28", "max": "52", "mean": "42", "stdev": "5" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "43", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "137", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "130", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "332", "missing": "0", "min": "336", "max": "2049", "mean": "637", "stdev": "282" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "11", "mean": "7", "stdev": "2" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "6", "max": "44", "mean": "22", "stdev": "7" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "103", "missing": "0", "min": "37", "max": "271", "mean": "80", "stdev": "40" }, { "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": "34", "missing": "0", "min": "9", "max": "57", "mean": "26", "stdev": "8" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "73", "missing": "0", "min": "26", "max": "148", "mean": "49", "stdev": "21" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "105", "missing": "0", "min": "39", "max": "275", "mean": "84", "stdev": "41" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "59", "missing": "0", "min": "16", "max": "89", "mean": "33", "stdev": "14" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "36", "missing": "0", "min": "9", "max": "52", "mean": "23", "stdev": "8" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "37", "missing": "0", "min": "1", "max": "51", "mean": "10", "stdev": "8" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "24", "mean": "4", "stdev": "4" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "71", "missing": "0", "min": "12", "max": "127", "mean": "35", "stdev": "20" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "36", "missing": "0", "min": "5", "max": "55", "mean": "12", "stdev": "8" }, { "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": "20", "missing": "0", "min": "1", "max": "25", "mean": "6", "stdev": "3" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "35", "mean": "5", "stdev": "5" }, { "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": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "65", "missing": "0", "min": "24", "max": "144", "mean": "45", "stdev": "20" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "13", "mean": "6", "stdev": "2" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "70", "mean": "11", "stdev": "11" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "112", "missing": "0", "min": "36", "max": "183", "mean": "64", "stdev": "26" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "335", "missing": "0", "min": "39", "max": "277", "mean": "81", "stdev": "41" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "338", "missing": "0", "min": "42", "max": "311", "mean": "90", "stdev": "46" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "334", "missing": "0", "min": "26", "max": "168", "mean": "54", "stdev": "24" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "338", "missing": "0", "min": "26", "max": "163", "mean": "51", "stdev": "24" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "8", "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 }