{ "data_id": "33760", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3818", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3818", "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: CHEMBL3818 (TID: 10669), and it has 36 rows and 58 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 13:37:05", "update_comment": null, "last_update": "2016-07-15 13:37:05", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3513298\/data_51813.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3818", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3818 (TID: 10669), and it has 36 rows and 58 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": 36, "NumberOfFeatures": 60, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 59, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 1.6666666666666667, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -1.2444042236176438, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.13587218808467624, "Quartile2MeansOfNumericAtts": 1.50275, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.0097466648197795, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.14295246840836787, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9865108733019483, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7409802195162067, "MaxKurtosisOfNumericAtts": 7.883744968920691, "MinMeansOfNumericAtts": 0.11038888888888888, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 76.8013888888889, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.13894855348334145, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.33333333333333, "Quartile3MeansOfNumericAtts": 3.8796666666666666, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8788585444240389, "PercentageOfSymbolicFeatures": 1.6666666666666667, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.9968643266591688, "MinStdDevOfNumericAtts": 0.011367839626673908, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.542381264811593, "MaxStdDevOfNumericAtts": 36.70159177729628, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.5941427013252856, "Quartile3StdDevOfNumericAtts": 1.3121037884204516, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.75, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.5534001834122073, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.565137005649718, "Quartile1SkewnessOfNumericAtts": -0.4048365441392337, "AutoCorrelation": -0.20588571428571417, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.25386153424933944 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "59", "type": "numeric", "distinct": "31", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "36", "missing": "0", "identifier": "1", "distr": [] }, { "name": "DLS_05", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaaN", "index": "2", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "4" }, { "name": "Eig05_EA.bo.", "index": "3", "type": "numeric", "distinct": "27", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM15_AEA.ri.", "index": "4", "type": "numeric", "distinct": "27", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Mp", "index": "5", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "6", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "7", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "LOC", "index": "8", "type": "numeric", "distinct": "21", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "9", "type": "numeric", "distinct": "27", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "10", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eta_alpha_A", "index": "11", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nPyrrolidines", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "H.053", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GATS4m", "index": "14", "type": "numeric", "distinct": "32", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ARR", "index": "15", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS7s", "index": "16", "type": "numeric", "distinct": "32", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_AEA.ri.", "index": "17", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "1" }, { "name": "Eig04_EA.ri.", "index": "18", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Mi", "index": "19", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "20", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "21", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS1p", "index": "22", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1v", "index": "23", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2m", "index": "24", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "25", "type": "numeric", "distinct": "28", "missing": "0", "min": "45", "max": "169", "mean": "77", "stdev": "37" }, { "name": "P_VSA_v_3", "index": "26", "type": "numeric", "distinct": "28", "missing": "0", "min": "45", "max": "169", "mean": "77", "stdev": "37" }, { "name": "SaaCH", "index": "27", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "4" }, { "name": "C.027", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AA", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CIC3", "index": "30", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.dm.", "index": "31", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "H.049", "index": "32", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "JGT", "index": "33", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "N.075", "index": "34", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "35", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nDB", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NdO", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NdssC", "index": "38", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nPyridines", "index": "39", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NRS", "index": "40", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "O.058", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_5", "index": "42", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "69", "mean": "28", "stdev": "17" }, { "name": "P_VSA_LogP_1", "index": "43", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "43", "mean": "20", "stdev": "14" }, { "name": "P_VSA_MR_7", "index": "44", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "34", "mean": "12", "stdev": "15" }, { "name": "SdO", "index": "45", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "12", "mean": "7", "stdev": "6" }, { "name": "SM02_EA.dm.", "index": "46", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM04_EA.dm.", "index": "47", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "48", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "49", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "3" }, { "name": "SM10_EA.dm.", "index": "50", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "4" }, { "name": "SM12_EA.dm.", "index": "51", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "11", "mean": "6", "stdev": "4" }, { "name": "SM14_EA.dm.", "index": "52", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "13", "mean": "7", "stdev": "5" }, { "name": "SpDiam_EA.dm.", "index": "53", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMAD_EA.dm.", "index": "54", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax_EA.dm.", "index": "55", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM02_AEA.bo.", "index": "56", "type": "numeric", "distinct": "23", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM03_AEA.bo.", "index": "57", "type": "numeric", "distinct": "23", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "58", "type": "numeric", "distinct": "13", "missing": "0", "min": "3", "max": "5", "mean": "4", "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 }