{ "data_id": "35649", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4899", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4899", "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: CHEMBL4899 (TID: 100414), and it has 266 rows and 66 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 18:36:55", "update_comment": null, "last_update": "2016-07-15 18:36:55", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3564002\/data_53051.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4899", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4899 (TID: 100414), and it has 266 rows and 66 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": 266, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.2556390977443609, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.059706600891866, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.1328666225694246, "Quartile2MeansOfNumericAtts": 4.005875939849624, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 11.959455336842053, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.08646581787746575, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9230067424863313, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7537468778012609, "MaxKurtosisOfNumericAtts": 51.56606459440607, "MinMeansOfNumericAtts": -0.01845112781954889, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 524.570597744361, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.147390893373183, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 11.984184210526315, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.787349312909499, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 6.9031810194139505, "MinStdDevOfNumericAtts": 0.006950168168153353, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8876894449144906, "MaxStdDevOfNumericAtts": 132.71035380443362, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.3687265807402187, "Quartile3StdDevOfNumericAtts": 4.810414825461554, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.571428571428572, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.360949514550758, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 35.91738912579957, "Quartile1SkewnessOfNumericAtts": -1.0325973883868058, "AutoCorrelation": -0.08315094339622651, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2910847736784634 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "148", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "266", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nN", "index": "1", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "2" }, { "name": "nTriazoles", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArX", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpMin1_Bh.e.", "index": "4", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "5", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "CATS2D_01_AA", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eta_betaP", "index": "7", "type": "numeric", "distinct": "37", "missing": "0", "min": "8", "max": "48", "mean": "22", "stdev": "5" }, { "name": "nArNHR", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "9", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "10", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig07_AEA.bo.", "index": "11", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X.", "index": "12", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "17", "mean": "3", "stdev": "3" }, { "name": "P_VSA_LogP_8", "index": "13", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "276", "mean": "37", "stdev": "41" }, { "name": "P_VSA_p_3", "index": "14", "type": "numeric", "distinct": "235", "missing": "0", "min": "57", "max": "516", "mean": "178", "stdev": "50" }, { "name": "P_VSA_v_3", "index": "15", "type": "numeric", "distinct": "235", "missing": "0", "min": "57", "max": "516", "mean": "178", "stdev": "50" }, { "name": "nX", "index": "16", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "C.026", "index": "17", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "3" }, { "name": "P_VSA_LogP_6", "index": "18", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "49", "mean": "14", "stdev": "11" }, { "name": "nAB", "index": "19", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "36", "mean": "21", "stdev": "5" }, { "name": "nBM", "index": "20", "type": "numeric", "distinct": "22", "missing": "0", "min": "6", "max": "42", "mean": "22", "stdev": "5" }, { "name": "Uc", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Ui", "index": "22", "type": "numeric", "distinct": "21", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "PCD", "index": "23", "type": "numeric", "distinct": "172", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "piPC09", "index": "24", "type": "numeric", "distinct": "168", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "0" }, { "name": "SssNH", "index": "25", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "MATS7m", "index": "26", "type": "numeric", "distinct": "196", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.070", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "28", "type": "numeric", "distinct": "235", "missing": "0", "min": "57", "max": "334", "mean": "219", "stdev": "55" }, { "name": "P_VSA_LogP_5", "index": "29", "type": "numeric", "distinct": "175", "missing": "0", "min": "6", "max": "233", "mean": "81", "stdev": "35" }, { "name": "SsCl", "index": "30", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "13", "mean": "5", "stdev": "5" }, { "name": "Eig07_EA.bo.", "index": "31", "type": "numeric", "distinct": "134", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "piID", "index": "32", "type": "numeric", "distinct": "163", "missing": "0", "min": "7", "max": "17", "mean": "12", "stdev": "1" }, { "name": "MATS4i", "index": "33", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "34", "type": "numeric", "distinct": "185", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "JGI4", "index": "35", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "36", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "369", "mean": "97", "stdev": "45" }, { "name": "CATS2D_04_DA", "index": "37", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "NaasN", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SaasN", "index": "39", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "GGI7", "index": "40", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS8m", "index": "41", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "42", "type": "numeric", "distinct": "180", "missing": "0", "min": "12", "max": "219", "mean": "102", "stdev": "32" }, { "name": "NaasC", "index": "43", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "21", "mean": "7", "stdev": "2" }, { "name": "IC1", "index": "44", "type": "numeric", "distinct": "213", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_F_A", "index": "45", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "46", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "205", "mean": "99", "stdev": "39" }, { "name": "Eig06_AEA.bo.", "index": "47", "type": "numeric", "distinct": "128", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS7m", "index": "48", "type": "numeric", "distinct": "233", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ZM1MulPer", "index": "49", "type": "numeric", "distinct": "240", "missing": "0", "min": "229", "max": "1490", "mean": "525", "stdev": "133" }, { "name": "ZM1V", "index": "50", "type": "numeric", "distinct": "124", "missing": "0", "min": "212", "max": "1364", "mean": "488", "stdev": "121" }, { "name": "CATS2D_05_DD", "index": "51", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eta_FL", "index": "52", "type": "numeric", "distinct": "246", "missing": "0", "min": "3", "max": "18", "mean": "8", "stdev": "2" }, { "name": "Eig04_AEA.ri.", "index": "53", "type": "numeric", "distinct": "200", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "54", "type": "numeric", "distinct": "178", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "StN", "index": "55", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "19", "mean": "5", "stdev": "5" }, { "name": "IC2", "index": "56", "type": "numeric", "distinct": "209", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MATS6e", "index": "57", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "58", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "163", "mean": "75", "stdev": "42" }, { "name": "piPC05", "index": "59", "type": "numeric", "distinct": "147", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "60", "type": "numeric", "distinct": "161", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "61", "type": "numeric", "distinct": "94", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SsF", "index": "62", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "93", "mean": "9", "stdev": "11" }, { "name": "F.084", "index": "63", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "D.Dtr10", "index": "64", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "268", "mean": "80", "stdev": "77" }, { "name": "piPC03", "index": "65", "type": "numeric", "distinct": "147", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GATS7v", "index": "66", "type": "numeric", "distinct": "183", "missing": "0", "min": "1", "max": "2", "mean": "1", "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 }