{ "data_id": "34885", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1878", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1878", "version": 11, "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: CHEMBL1878 (TID: 282), and it has 479 rows and 64 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 16:32:53", "update_comment": null, "last_update": "2016-07-15 16:32:53", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3541513\/data_52668.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1878", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1878 (TID: 282), and it has 479 rows and 64 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": 479, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.19357111885185097, "Dimensionality": 0.13778705636743216, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.7315219206680585, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.039633155123091485, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.4390273419661563, "Quartile2SkewnessOfNumericAtts": -0.013939706102459388, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3359643522870164, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9008708964925276, "MinMeansOfNumericAtts": 0.26308350730688934, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 8.612711692348455, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.5142104906350482, "MaxMeansOfNumericAtts": 48.79958246346556, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 7.2891962421711884, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -0.9795355023956511, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.0346168384430957, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.4772270817229699, "MaxSkewnessOfNumericAtts": 1.70716049959653, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.2935866959658602, "Quartile3StdDevOfNumericAtts": 1.2861674837508734, "MaxStdDevOfNumericAtts": 20.549915305207367, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.244111691022964, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 0.41473891728046913, "Quartile1SkewnessOfNumericAtts": -0.45681802225625084, "MeanMeansOfNumericAtts": 5.98399649911675, "Quartile1StdDevOfNumericAtts": 0.244213810549699, "AutoCorrelation": 0.17601255230125573, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "228", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "479", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_09_LL", "index": "1", "type": "numeric", "distinct": "33", "missing": "0", "min": "2", "max": "51", "mean": "12", "stdev": "7" }, { "name": "GGI7", "index": "2", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA", "index": "3", "type": "numeric", "distinct": "246", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "4", "type": "numeric", "distinct": "246", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_AL", "index": "5", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "5" }, { "name": "Eig06_AEA.dm.", "index": "6", "type": "numeric", "distinct": "290", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "7", "type": "numeric", "distinct": "241", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI4", "index": "8", "type": "numeric", "distinct": "246", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ATS4p", "index": "9", "type": "numeric", "distinct": "348", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_07_AL", "index": "10", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "20", "mean": "6", "stdev": "5" }, { "name": "Eig05_EA.ri.", "index": "11", "type": "numeric", "distinct": "267", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "C.011", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS4v", "index": "13", "type": "numeric", "distinct": "340", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "14", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "15", "type": "numeric", "distinct": "257", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "16", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "H.046", "index": "17", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "4" }, { "name": "Eig04_EA.ed.", "index": "18", "type": "numeric", "distinct": "280", "missing": "0", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "SM13_AEA.dm.", "index": "19", "type": "numeric", "distinct": "280", "missing": "0", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "GGI2", "index": "20", "type": "numeric", "distinct": "35", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "21", "type": "numeric", "distinct": "151", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS5p", "index": "22", "type": "numeric", "distinct": "373", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig02_AEA.ri.", "index": "23", "type": "numeric", "distinct": "234", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "24", "type": "numeric", "distinct": "189", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SsCH3", "index": "25", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "Eig05_AEA.ri.", "index": "26", "type": "numeric", "distinct": "296", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "27", "type": "numeric", "distinct": "183", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "28", "type": "numeric", "distinct": "183", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SRW09", "index": "29", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "4" }, { "name": "SpMax1_Bh.e.", "index": "30", "type": "numeric", "distinct": "159", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MPC04", "index": "31", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SssNH", "index": "32", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "C.001", "index": "33", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "Eig04_EA.ri.", "index": "34", "type": "numeric", "distinct": "283", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "TPC", "index": "35", "type": "numeric", "distinct": "243", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "1" }, { "name": "GGI9", "index": "36", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "37", "type": "numeric", "distinct": "109", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "38", "type": "numeric", "distinct": "205", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax5_Bh.p.", "index": "39", "type": "numeric", "distinct": "246", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig02_AEA.ed.", "index": "40", "type": "numeric", "distinct": "198", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig13_EA.bo.", "index": "41", "type": "numeric", "distinct": "239", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM03_EA", "index": "42", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "43", "type": "numeric", "distinct": "269", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "44", "type": "numeric", "distinct": "269", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "BAC", "index": "45", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "110", "mean": "31", "stdev": "21" }, { "name": "GGI5", "index": "46", "type": "numeric", "distinct": "213", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Ram", "index": "47", "type": "numeric", "distinct": "14", "missing": "0", "min": "4", "max": "17", "mean": "10", "stdev": "2" }, { "name": "Eig08_AEA.bo.", "index": "48", "type": "numeric", "distinct": "214", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig02_EA.ed.", "index": "49", "type": "numeric", "distinct": "236", "missing": "0", "min": "7", "max": "13", "mean": "10", "stdev": "1" }, { "name": "SM11_AEA.dm.", "index": "50", "type": "numeric", "distinct": "236", "missing": "0", "min": "7", "max": "13", "mean": "10", "stdev": "1" }, { "name": "MWC10", "index": "51", "type": "numeric", "distinct": "299", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "ATS4m", "index": "52", "type": "numeric", "distinct": "350", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM04_AEA.ed.", "index": "53", "type": "numeric", "distinct": "276", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "nCp", "index": "54", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "Eta_B", "index": "55", "type": "numeric", "distinct": "200", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Pol", "index": "56", "type": "numeric", "distinct": "50", "missing": "0", "min": "23", "max": "79", "mean": "49", "stdev": "10" }, { "name": "TWC", "index": "57", "type": "numeric", "distinct": "297", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "ATSC8p", "index": "58", "type": "numeric", "distinct": "442", "missing": "0", "min": "4", "max": "25", "mean": "12", "stdev": "4" }, { "name": "X5v", "index": "59", "type": "numeric", "distinct": "420", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM07_AEA.bo.", "index": "60", "type": "numeric", "distinct": "289", "missing": "0", "min": "11", "max": "12", "mean": "12", "stdev": "0" }, { "name": "Eta_C_A", "index": "61", "type": "numeric", "distinct": "313", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MWC09", "index": "62", "type": "numeric", "distinct": "311", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM12_AEA.ed.", "index": "63", "type": "numeric", "distinct": "311", "missing": "0", "min": "21", "max": "26", "mean": "24", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "64", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" } ], "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 }