{ "data_id": "28761", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1820", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1820", "version": 8, "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: CHEMBL1820 (TID: 213), and it has 114 rows and 63 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 00:48:52", "update_comment": null, "last_update": "2016-07-15 00:48:52", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3371843\/data_52552.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1820", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1820 (TID: 213), and it has 114 rows and 63 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": 114, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.292046052631579, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.10133890062185985, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.638832922149122, "Quartile1SkewnessOfNumericAtts": 0.029465214903917437, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3771972560641485, "AutoCorrelation": -0.08493805309734499, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.564553570212472, "Dimensionality": 0.5701754385964912, "MeanSkewnessOfNumericAtts": 0.47490919538184995, "Quartile2MeansOfNumericAtts": 2.969877192982456, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 3.953531675916947, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.2598864182021897, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.5136371541454863, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5456533015398646, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 33.58833794796617, "MinMeansOfNumericAtts": 0.025956140350877187, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 213.00788596491228, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.05702824343317048, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 5.016603070175439, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7601330479847344, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.452412147996433, "MinStdDevOfNumericAtts": 0.0060486628274098305, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6434001611747119, "MaxStdDevOfNumericAtts": 111.1622774163986, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.0508567468571384, "Quartile3StdDevOfNumericAtts": 1.3243835138141762 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "88", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "114", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GGI4", "index": "1", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig06_EA.ed.", "index": "2", "type": "numeric", "distinct": "72", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "2" }, { "name": "SM15_AEA.dm.", "index": "3", "type": "numeric", "distinct": "72", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "2" }, { "name": "Eig07_AEA.dm.", "index": "4", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig08_AEA.dm.", "index": "5", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig07_EA.dm.", "index": "6", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig08_EA.dm.", "index": "7", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "8", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SdO", "index": "9", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "64", "mean": "16", "stdev": "18" }, { "name": "GGI2", "index": "10", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "8", "mean": "3", "stdev": "1" }, { "name": "TIC2", "index": "11", "type": "numeric", "distinct": "92", "missing": "0", "min": "98", "max": "343", "mean": "213", "stdev": "72" }, { "name": "Eig05_AEA.ed.", "index": "12", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig05_EA.ed.", "index": "13", "type": "numeric", "distinct": "67", "missing": "0", "min": "3", "max": "9", "mean": "6", "stdev": "2" }, { "name": "SM14_AEA.dm.", "index": "14", "type": "numeric", "distinct": "67", "missing": "0", "min": "3", "max": "9", "mean": "6", "stdev": "2" }, { "name": "MPC05", "index": "15", "type": "numeric", "distinct": "58", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC07", "index": "16", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "X3A", "index": "17", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA", "index": "18", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eta_B", "index": "19", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "20", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "21", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_AEA.ed.", "index": "22", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig10_AEA.ed.", "index": "23", "type": "numeric", "distinct": "69", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin7_Bh.p.", "index": "24", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "25", "type": "numeric", "distinct": "73", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig02_AEA.dm.", "index": "26", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nRCONHR", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS4m", "index": "28", "type": "numeric", "distinct": "104", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "29", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS4s", "index": "30", "type": "numeric", "distinct": "104", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig04_EA.ed.", "index": "31", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "32", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ON0", "index": "33", "type": "numeric", "distinct": "55", "missing": "0", "min": "8", "max": "24", "mean": "14", "stdev": "4" }, { "name": "SM13_AEA.dm.", "index": "34", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SPI", "index": "35", "type": "numeric", "distinct": "78", "missing": "0", "min": "5", "max": "31", "mean": "13", "stdev": "6" }, { "name": "Eig03_EA.ed.", "index": "36", "type": "numeric", "distinct": "60", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "37", "type": "numeric", "distinct": "60", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "38", "type": "numeric", "distinct": "94", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA", "index": "39", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "nCb.", "index": "40", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "SM14_AEA.bo.", "index": "41", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "42", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "GGI8", "index": "43", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.003", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax6_Bh.e.", "index": "45", "type": "numeric", "distinct": "84", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "46", "type": "numeric", "distinct": "79", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "47", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig12_AEA.ri.", "index": "48", "type": "numeric", "distinct": "80", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig12_EA", "index": "49", "type": "numeric", "distinct": "61", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "50", "type": "numeric", "distinct": "95", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "MPC04", "index": "51", "type": "numeric", "distinct": "52", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC06", "index": "52", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC08", "index": "53", "type": "numeric", "distinct": "65", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC09", "index": "54", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "nCIR", "index": "55", "type": "numeric", "distinct": "8", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "2" }, { "name": "PW4", "index": "56", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW5", "index": "57", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM06_AEA.dm.", "index": "58", "type": "numeric", "distinct": "61", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SpMax6_Bh.p.", "index": "59", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "X4sol", "index": "60", "type": "numeric", "distinct": "89", "missing": "0", "min": "4", "max": "15", "mean": "8", "stdev": "2" }, { "name": "X5sol", "index": "61", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "12", "mean": "6", "stdev": "2" }, { "name": "D.Dtr10", "index": "62", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "344", "mean": "54", "stdev": "111" }, { "name": "nR10", "index": "63", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "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 }