{ "data_id": "31723", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5832", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5832", "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: CHEMBL5832 (TID: 102988), and it has 88 rows and 60 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": "2016-07-15 08:20:09", "update_comment": null, "last_update": "2016-07-15 08:20:09", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3457853\/data_52054.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5832", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5832 (TID: 102988), and it has 88 rows and 60 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": 88, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.48380242433138293, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7065907758452183, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 1.8258756685401116, "MinMeansOfNumericAtts": 0.5795454545454544, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.8776119599918317, "MaxMeansOfNumericAtts": 81.86927272727272, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 11.60028409090909, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1601630885146166, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9094234754009131, "MaxSkewnessOfNumericAtts": 1.44365543467783, "MinStdDevOfNumericAtts": 0.07939305994611306, "Quartile1KurtosisOfNumericAtts": -1.6622433578791138, "Quartile3StdDevOfNumericAtts": 0.7022417461877489, "MaxStdDevOfNumericAtts": 31.86630031893751, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 2.0141193181818187, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": -1.1495640055584389, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": -0.5335219271789295, "MeanMeansOfNumericAtts": 10.260928464977644, "Quartile1StdDevOfNumericAtts": 0.17762913790305895, "AutoCorrelation": 0.5441609195402298, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": -1.2366165693206048, "Dimensionality": 0.7045454545454546, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.729125, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.3584918868513684, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.7858090396738444, "Quartile2SkewnessOfNumericAtts": 0.5399623549675473, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "48", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "88", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_02_AA", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "2", "type": "numeric", "distinct": "43", "missing": "0", "min": "8", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "3", "type": "numeric", "distinct": "60", "missing": "0", "min": "10", "max": "10", "mean": "10", "stdev": "0" }, { "name": "SM07_EA.bo.", "index": "4", "type": "numeric", "distinct": "54", "missing": "0", "min": "11", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "5", "type": "numeric", "distinct": "54", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "6", "type": "numeric", "distinct": "48", "missing": "0", "min": "14", "max": "15", "mean": "14", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "7", "type": "numeric", "distinct": "47", "missing": "0", "min": "15", "max": "16", "mean": "16", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "8", "type": "numeric", "distinct": "45", "missing": "0", "min": "17", "max": "18", "mean": "17", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "9", "type": "numeric", "distinct": "46", "missing": "0", "min": "18", "max": "20", "mean": "19", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "10", "type": "numeric", "distinct": "44", "missing": "0", "min": "20", "max": "21", "mean": "20", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "11", "type": "numeric", "distinct": "47", "missing": "0", "min": "21", "max": "23", "mean": "22", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "12", "type": "numeric", "distinct": "43", "missing": "0", "min": "23", "max": "24", "mean": "23", "stdev": "1" }, { "name": "C.034", "index": "13", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig02_EA.bo.", "index": "14", "type": "numeric", "distinct": "33", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "15", "type": "numeric", "distinct": "33", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "16", "type": "numeric", "distinct": "34", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "C.029", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.031", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.042", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "CATS2D_05_LL", "index": "21", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "5" }, { "name": "CATS2D_06_LL", "index": "22", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "6" }, { "name": "CATS2D_07_LL", "index": "23", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "6" }, { "name": "Eig01_AEA.bo.", "index": "24", "type": "numeric", "distinct": "18", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "25", "type": "numeric", "distinct": "19", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA", "index": "26", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "27", "type": "numeric", "distinct": "11", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "28", "type": "numeric", "distinct": "20", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "GATS3s", "index": "29", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.", "index": "30", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "17", "mean": "11", "stdev": "4" }, { "name": "N.074", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nArCN", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCsp", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nImidazoles", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nN", "index": "35", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "nPyrimidines", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nTB", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NtN", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NtsC", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "40", "type": "numeric", "distinct": "15", "missing": "0", "min": "18", "max": "147", "mean": "82", "stdev": "32" }, { "name": "P_VSA_i_4", "index": "41", "type": "numeric", "distinct": "16", "missing": "0", "min": "18", "max": "146", "mean": "82", "stdev": "32" }, { "name": "SM09_AEA.bo.", "index": "42", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "43", "type": "numeric", "distinct": "20", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM11_AEA.ri.", "index": "44", "type": "numeric", "distinct": "11", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM13_EA.ed.", "index": "45", "type": "numeric", "distinct": "45", "missing": "0", "min": "31", "max": "33", "mean": "32", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "46", "type": "numeric", "distinct": "43", "missing": "0", "min": "34", "max": "36", "mean": "34", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "47", "type": "numeric", "distinct": "37", "missing": "0", "min": "36", "max": "38", "mean": "37", "stdev": "1" }, { "name": "SpDiam_AEA.ri.", "index": "48", "type": "numeric", "distinct": "33", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA", "index": "49", "type": "numeric", "distinct": "19", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "50", "type": "numeric", "distinct": "11", "missing": "0", "min": "8", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "51", "type": "numeric", "distinct": "25", "missing": "0", "min": "18", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "52", "type": "numeric", "distinct": "37", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "53", "type": "numeric", "distinct": "36", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "54", "type": "numeric", "distinct": "18", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "55", "type": "numeric", "distinct": "19", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA", "index": "56", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "57", "type": "numeric", "distinct": "11", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "58", "type": "numeric", "distinct": "20", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SpMin1_Bh.e.", "index": "59", "type": "numeric", "distinct": "33", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "60", "type": "numeric", "distinct": "29", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" } ], "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 }