{ "data_id": "23636", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4329", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4329", "version": 7, "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: CHEMBL4329 (TID: 10008), and it has 189 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": "2016-07-14 12:53:46", "update_comment": null, "last_update": "2016-07-14 12:53:46", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3229837\/data_52721.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4329", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4329 (TID: 10008), and it has 189 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": 189, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "REPTreeDepth3Kappa": null, "DecisionStumpKappa": null, "MaxMeansOfNumericAtts": 54402.88888888889, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 2.024290727117906, "RandomTreeDepth1AUC": null, "Dimensionality": 0.3492063492063492, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.9309829778147058, "RandomTreeDepth1ErrRate": null, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0782128376283782, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1Kappa": null, "J48.00001.AUC": null, "MaxSkewnessOfNumericAtts": 3.9527974120949394, "MinStdDevOfNumericAtts": 0.04753496434997808, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 6.692460435416149, "AutoCorrelation": -0.16489893617021217, "RandomTreeDepth2AUC": null, "J48.00001.ErrRate": null, "MaxStdDevOfNumericAtts": 94863.13701441837, "MinorityClassPercentage": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 84.36738359788359, "CfsSubsetEval_DecisionStumpAUC": null, "RandomTreeDepth2ErrRate": null, "J48.00001.Kappa": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": null, "RandomTreeDepth2Kappa": null, "J48.0001.AUC": null, "MeanKurtosisOfNumericAtts": 4.340631268517174, "NaiveBayesAUC": null, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.5684696314127873, "CfsSubsetEval_DecisionStumpKappa": null, "RandomTreeDepth3AUC": null, "J48.0001.ErrRate": null, "MeanMeansOfNumericAtts": 934.7251617419619, "NaiveBayesErrRate": null, "Quartile1KurtosisOfNumericAtts": 0.44150920437680785, "Quartile3StdDevOfNumericAtts": 41.27670450721337, "CfsSubsetEval_NaiveBayesAUC": null, "RandomTreeDepth3ErrRate": null, "J48.0001.Kappa": null, "MeanMutualInformation": null, "NaiveBayesKappa": null, "Quartile1MeansOfNumericAtts": 1.5613624338624343, "REPTreeDepth1AUC": null, "CfsSubsetEval_NaiveBayesErrRate": null, "RandomTreeDepth3Kappa": null, "J48.001.AUC": null, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": null, "CfsSubsetEval_NaiveBayesKappa": null, "CfsSubsetEval_kNN1NAUC": null, "StdvNominalAttDistinctValues": null, "J48.001.ErrRate": null, "MeanNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 1.0360275593667085, "REPTreeDepth1Kappa": null, "CfsSubsetEval_kNN1NErrRate": null, "kNN1NAUC": null, "J48.001.Kappa": null, "MeanSkewnessOfNumericAtts": 1.7277155536465894, "Quartile1StdDevOfNumericAtts": 0.5859601007725477, "REPTreeDepth2AUC": null, "CfsSubsetEval_kNN1NKappa": null, "kNN1NErrRate": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1569.8043047037008, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": null, "ClassEntropy": null, "kNN1NKappa": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 3.5836974280606744, "REPTreeDepth2Kappa": null, "REPTreeDepth3AUC": null, "DecisionStumpAUC": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3215531558210574, "Quartile2MeansOfNumericAtts": 5.70010052910053, "REPTreeDepth3ErrRate": null, "DecisionStumpErrRate": null, "MaxKurtosisOfNumericAtts": 19.705030961862686, "MinMeansOfNumericAtts": 0.047756613756613754, "Quartile2MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "160", "missing": "0", "target": "1", "min": "5", "max": "11", "mean": "8", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "189", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr11", "index": "1", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "564", "mean": "126", "stdev": "144" }, { "name": "D.Dtr08", "index": "2", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "370", "mean": "39", "stdev": "42" }, { "name": "SpMax7_Bh.s.", "index": "3", "type": "numeric", "distinct": "138", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "1" }, { "name": "P_VSA_MR_7", "index": "4", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "107", "mean": "16", "stdev": "29" }, { "name": "ATSC7s", "index": "5", "type": "numeric", "distinct": "176", "missing": "0", "min": "22", "max": "462", "mean": "108", "stdev": "87" }, { "name": "MSD", "index": "6", "type": "numeric", "distinct": "145", "missing": "0", "min": "4", "max": "17", "mean": "7", "stdev": "2" }, { "name": "ATSC8s", "index": "7", "type": "numeric", "distinct": "176", "missing": "0", "min": "8", "max": "604", "mean": "101", "stdev": "121" }, { "name": "TIC1", "index": "8", "type": "numeric", "distinct": "160", "missing": "0", "min": "112", "max": "579", "mean": "228", "stdev": "95" }, { "name": "nHet", "index": "9", "type": "numeric", "distinct": "18", "missing": "0", "min": "2", "max": "27", "mean": "7", "stdev": "5" }, { "name": "AECC", "index": "10", "type": "numeric", "distinct": "132", "missing": "0", "min": "6", "max": "30", "mean": "11", "stdev": "4" }, { "name": "IDE", "index": "11", "type": "numeric", "distinct": "135", "missing": "0", "min": "3", "max": "5", "mean": "3", "stdev": "0" }, { "name": "D.Dtr03", "index": "12", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "82", "mean": "12", "stdev": "19" }, { "name": "DECC", "index": "13", "type": "numeric", "distinct": "128", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "HVcpx", "index": "14", "type": "numeric", "distinct": "133", "missing": "0", "min": "3", "max": "5", "mean": "3", "stdev": "0" }, { "name": "ICR", "index": "15", "type": "numeric", "distinct": "119", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IC2", "index": "16", "type": "numeric", "distinct": "150", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MATS2v", "index": "17", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IC3", "index": "18", "type": "numeric", "distinct": "150", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Psi_i_s", "index": "19", "type": "numeric", "distinct": "153", "missing": "0", "min": "35", "max": "206", "mean": "73", "stdev": "35" }, { "name": "CATS2D_05_AA", "index": "20", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "RBN", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "34", "mean": "6", "stdev": "6" }, { "name": "Eig04_EA.dm.", "index": "22", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nCconj", "index": "23", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "ZM1Kup", "index": "24", "type": "numeric", "distinct": "150", "missing": "0", "min": "200", "max": "1240", "mean": "469", "stdev": "228" }, { "name": "Eig02_AEA.bo.", "index": "25", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nHAcc", "index": "26", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "26", "mean": "6", "stdev": "5" }, { "name": "SpMax6_Bh.s.", "index": "27", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "C.016", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NdsCH", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "nR.Cs", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SdsCH", "index": "31", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ON0", "index": "32", "type": "numeric", "distinct": "89", "missing": "0", "min": "9", "max": "46", "mean": "17", "stdev": "7" }, { "name": "SaasC", "index": "33", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "2" }, { "name": "CENT", "index": "34", "type": "numeric", "distinct": "147", "missing": "0", "min": "269", "max": "22947", "mean": "2697", "stdev": "4278" }, { "name": "TIE", "index": "35", "type": "numeric", "distinct": "176", "missing": "0", "min": "25", "max": "851", "mean": "100", "stdev": "141" }, { "name": "P_VSA_LogP_2", "index": "36", "type": "numeric", "distinct": "79", "missing": "0", "min": "7", "max": "352", "mean": "46", "stdev": "65" }, { "name": "CATS2D_08_DA", "index": "37", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "3" }, { "name": "GMTIV", "index": "38", "type": "numeric", "distinct": "171", "missing": "0", "min": "4253", "max": "535013", "mean": "54403", "stdev": "94863" }, { "name": "SpMin1_Bh.s.", "index": "39", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ECC", "index": "40", "type": "numeric", "distinct": "122", "missing": "0", "min": "101", "max": "2095", "mean": "415", "stdev": "382" }, { "name": "CATS2D_07_DA", "index": "41", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "IAC", "index": "42", "type": "numeric", "distinct": "138", "missing": "0", "min": "50", "max": "255", "mean": "95", "stdev": "41" }, { "name": "TIC0", "index": "43", "type": "numeric", "distinct": "138", "missing": "0", "min": "50", "max": "255", "mean": "95", "stdev": "41" }, { "name": "IC4", "index": "44", "type": "numeric", "distinct": "139", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax4_Bh.s.", "index": "45", "type": "numeric", "distinct": "119", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig09_EA.ri.", "index": "46", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CSI", "index": "47", "type": "numeric", "distinct": "133", "missing": "0", "min": "217", "max": "4547", "mean": "905", "stdev": "789" }, { "name": "PJI2", "index": "48", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "49", "type": "numeric", "distinct": "128", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax8_Bh.s.", "index": "50", "type": "numeric", "distinct": "131", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SpMax3_Bh.s.", "index": "51", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "S1K", "index": "52", "type": "numeric", "distinct": "145", "missing": "0", "min": "11", "max": "67", "mean": "23", "stdev": "11" }, { "name": "GGI10", "index": "53", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.p.", "index": "54", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC7e", "index": "55", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MDDD", "index": "56", "type": "numeric", "distinct": "147", "missing": "0", "min": "9", "max": "168", "mean": "37", "stdev": "32" }, { "name": "D.Dtr10", "index": "57", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "818", "mean": "182", "stdev": "154" }, { "name": "Chi1_EA.dm.", "index": "58", "type": "numeric", "distinct": "139", "missing": "0", "min": "10", "max": "68", "mean": "34", "stdev": "9" }, { "name": "SpMAD_EA", "index": "59", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_p_2", "index": "60", "type": "numeric", "distinct": "61", "missing": "0", "min": "25", "max": "642", "mean": "135", "stdev": "123" }, { "name": "P_VSA_v_2", "index": "61", "type": "numeric", "distinct": "68", "missing": "0", "min": "25", "max": "642", "mean": "137", "stdev": "123" }, { "name": "SAacc", "index": "62", "type": "numeric", "distinct": "64", "missing": "0", "min": "25", "max": "637", "mean": "135", "stdev": "124" }, { "name": "GGI9", "index": "63", "type": "numeric", "distinct": "117", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "S2K", "index": "64", "type": "numeric", "distinct": "147", "missing": "0", "min": "4", "max": "36", "mean": "9", "stdev": "6" } ], "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 }