{ "data_id": "35535", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4234", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4234", "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: CHEMBL4234 (TID: 11488), and it has 177 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 18:18:21", "update_comment": null, "last_update": "2016-07-15 18:18:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3560890\/data_52612.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4234", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4234 (TID: 11488), and it has 177 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": 177, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3672316384180791, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.3143860833100494, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.42726014707561816, "Quartile2MeansOfNumericAtts": 3.2402429378531075, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 98.35004109914972, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.6238832743926495, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.25444808003832176, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6422795144094631, "MaxKurtosisOfNumericAtts": 14.757809444898609, "MinMeansOfNumericAtts": -0.43735028248587593, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 6587.288135593222, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.1751743376446075, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 5.0254406779661025, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.225507761592635, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.164395807918767, "MinStdDevOfNumericAtts": 0.01651381112535577, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.022123109713956323, "MaxStdDevOfNumericAtts": 5405.685838827211, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.6197704969752803, "Quartile3StdDevOfNumericAtts": 0.7521521702897136, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9501624293785312, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.929396849893955, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 126.37330526129945, "Quartile1SkewnessOfNumericAtts": -1.17682721769876, "AutoCorrelation": 0.06783522727272642, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3908282164670963 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "129", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "177", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GGI9", "index": "1", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "2", "type": "numeric", "distinct": "116", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "Eig06_EA", "index": "3", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig12_EA", "index": "4", "type": "numeric", "distinct": "90", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig12_EA.ed.", "index": "5", "type": "numeric", "distinct": "98", "missing": "0", "min": "-6", "max": "4", "mean": "0", "stdev": "2" }, { "name": "SM06_AEA.dm.", "index": "6", "type": "numeric", "distinct": "90", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM07_AEA.ri.", "index": "7", "type": "numeric", "distinct": "98", "missing": "0", "min": "-6", "max": "4", "mean": "0", "stdev": "2" }, { "name": "SM14_AEA.bo.", "index": "8", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piPC04", "index": "9", "type": "numeric", "distinct": "105", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "10", "type": "numeric", "distinct": "105", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "X4", "index": "11", "type": "numeric", "distinct": "107", "missing": "0", "min": "3", "max": "15", "mean": "7", "stdev": "2" }, { "name": "Eig06_AEA.ed.", "index": "12", "type": "numeric", "distinct": "95", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC03", "index": "13", "type": "numeric", "distinct": "94", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig12_AEA.bo.", "index": "14", "type": "numeric", "distinct": "111", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "15", "type": "numeric", "distinct": "71", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "16", "type": "numeric", "distinct": "71", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "17", "type": "numeric", "distinct": "71", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "18", "type": "numeric", "distinct": "106", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "19", "type": "numeric", "distinct": "111", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "20", "type": "numeric", "distinct": "115", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "MAXDP", "index": "21", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "PW2", "index": "22", "type": "numeric", "distinct": "57", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig12_EA.ri.", "index": "23", "type": "numeric", "distinct": "134", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "24", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GMTI", "index": "25", "type": "numeric", "distinct": "107", "missing": "0", "min": "746", "max": "37150", "mean": "6587", "stdev": "5406" }, { "name": "Eig08_EA", "index": "26", "type": "numeric", "distinct": "86", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "27", "type": "numeric", "distinct": "86", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig09_AEA.ri.", "index": "28", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig09_EA.ri.", "index": "29", "type": "numeric", "distinct": "113", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "30", "type": "numeric", "distinct": "94", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "31", "type": "numeric", "distinct": "148", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig12_EA.bo.", "index": "32", "type": "numeric", "distinct": "107", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM03_AEA.bo.", "index": "33", "type": "numeric", "distinct": "97", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "34", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "35", "type": "numeric", "distinct": "97", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "36", "type": "numeric", "distinct": "107", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "37", "type": "numeric", "distinct": "93", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X4sol", "index": "38", "type": "numeric", "distinct": "127", "missing": "0", "min": "3", "max": "16", "mean": "8", "stdev": "2" }, { "name": "Eig08_AEA.bo.", "index": "39", "type": "numeric", "distinct": "94", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "CSI", "index": "40", "type": "numeric", "distinct": "102", "missing": "0", "min": "134", "max": "1540", "mean": "495", "stdev": "235" }, { "name": "ATS7m", "index": "41", "type": "numeric", "distinct": "164", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig07_AEA.ed.", "index": "42", "type": "numeric", "distinct": "94", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig06_EA.ed.", "index": "43", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "SM15_AEA.dm.", "index": "44", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "Eig04_AEA.dm.", "index": "45", "type": "numeric", "distinct": "123", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig12_AEA.ri.", "index": "46", "type": "numeric", "distinct": "141", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig05_AEA.bo.", "index": "47", "type": "numeric", "distinct": "110", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig13_AEA.ed.", "index": "48", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig08_EA.ri.", "index": "49", "type": "numeric", "distinct": "113", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "GGI3", "index": "50", "type": "numeric", "distinct": "47", "missing": "0", "min": "1", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig03_EA.bo.", "index": "51", "type": "numeric", "distinct": "115", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "52", "type": "numeric", "distinct": "115", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.ed.", "index": "53", "type": "numeric", "distinct": "93", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "piPC02", "index": "54", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "55", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS6m", "index": "56", "type": "numeric", "distinct": "168", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig09_EA", "index": "57", "type": "numeric", "distinct": "75", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "58", "type": "numeric", "distinct": "75", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CENT", "index": "59", "type": "numeric", "distinct": "104", "missing": "0", "min": "109", "max": "4192", "mean": "806", "stdev": "611" }, { "name": "Eig14_AEA.bo.", "index": "60", "type": "numeric", "distinct": "100", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig07_EA.ed.", "index": "61", "type": "numeric", "distinct": "99", "missing": "0", "min": "-1", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM02_AEA.ri.", "index": "62", "type": "numeric", "distinct": "99", "missing": "0", "min": "-1", "max": "9", "mean": "3", "stdev": "2" }, { "name": "Eig14_AEA.ri.", "index": "63", "type": "numeric", "distinct": "132", "missing": "0", "min": "-1", "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 }