{ "data_id": "35550", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4106", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4106", "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: CHEMBL4106 (TID: 17107), and it has 290 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": "2016-07-15 18:20:57", "update_comment": null, "last_update": "2016-07-15 18:20:57", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3561447\/data_52709.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4106", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4106 (TID: 17107), and it has 290 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": 290, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.22758620689655173, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.3010654338089398, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.3874015907947423, "Quartile2MeansOfNumericAtts": 1.203448275862069, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.6797567838564995, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.36533518611739546, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0596109686384836, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.47242736018890036, "MaxKurtosisOfNumericAtts": 7.975868932676059, "MinMeansOfNumericAtts": -0.04527586206896552, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 78.67939310344828, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.024488412294108, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 5.527558620689655, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2545049540518218, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.7969770922283144, "MinStdDevOfNumericAtts": 0.012351058003854607, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.214843576975528, "MaxStdDevOfNumericAtts": 36.533419089998795, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.457400735132411, "Quartile3StdDevOfNumericAtts": 1.0883621536812014, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.49317758620689656, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.7014037740736359, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4.386293368700265, "Quartile1SkewnessOfNumericAtts": -0.38409274231399476, "AutoCorrelation": 0.010598615916954582, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.07447281795556923 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "169", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "290", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SsNH2", "index": "1", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "ARR", "index": "2", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "3", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsNH2", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "BIC5", "index": "8", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PCR", "index": "9", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BIC4", "index": "10", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_PL", "index": "11", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS7i", "index": "12", "type": "numeric", "distinct": "188", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC5", "index": "13", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_08_PL", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_AP", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "N.066", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRNH2", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_DA", "index": "18", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "NssNH", "index": "19", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "9", "mean": "4", "stdev": "1" }, { "name": "SssNH", "index": "20", "type": "numeric", "distinct": "262", "missing": "0", "min": "3", "max": "27", "mean": "10", "stdev": "3" }, { "name": "X2A", "index": "21", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DBI", "index": "22", "type": "numeric", "distinct": "68", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax1_Bh.v.", "index": "23", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC2", "index": "24", "type": "numeric", "distinct": "230", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "25", "type": "numeric", "distinct": "16", "missing": "0", "min": "3", "max": "19", "mean": "10", "stdev": "3" }, { "name": "SIC1", "index": "26", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AP", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SIC3", "index": "28", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI3", "index": "29", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "BIC1", "index": "30", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "31", "type": "numeric", "distinct": "122", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "BIC3", "index": "32", "type": "numeric", "distinct": "112", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC1", "index": "33", "type": "numeric", "distinct": "231", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_beta_A", "index": "34", "type": "numeric", "distinct": "150", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "35", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nAB", "index": "36", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "28", "mean": "8", "stdev": "5" }, { "name": "piID", "index": "37", "type": "numeric", "distinct": "187", "missing": "0", "min": "6", "max": "13", "mean": "8", "stdev": "1" }, { "name": "piPC05", "index": "38", "type": "numeric", "distinct": "188", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "piPC08", "index": "39", "type": "numeric", "distinct": "205", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC09", "index": "40", "type": "numeric", "distinct": "203", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "IC1", "index": "41", "type": "numeric", "distinct": "229", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nBnz", "index": "42", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nCar", "index": "43", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "26", "mean": "7", "stdev": "5" }, { "name": "nCb.", "index": "44", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "45", "type": "numeric", "distinct": "149", "missing": "0", "min": "16", "max": "221", "mean": "79", "stdev": "37" }, { "name": "SpMax1_Bh.p.", "index": "46", "type": "numeric", "distinct": "115", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "47", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "50", "mean": "12", "stdev": "13" }, { "name": "H.053", "index": "48", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "X0A", "index": "49", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC2", "index": "50", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS4e", "index": "51", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4v", "index": "52", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IC3", "index": "53", "type": "numeric", "distinct": "213", "missing": "0", "min": "4", "max": "6", "mean": "6", "stdev": "0" }, { "name": "GATS4v", "index": "54", "type": "numeric", "distinct": "168", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_B", "index": "55", "type": "numeric", "distinct": "154", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piPC10", "index": "56", "type": "numeric", "distinct": "204", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "57", "type": "numeric", "distinct": "211", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "HNar", "index": "58", "type": "numeric", "distinct": "144", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nBM", "index": "59", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "33", "mean": "12", "stdev": "6" }, { "name": "nCsp2", "index": "60", "type": "numeric", "distinct": "22", "missing": "0", "min": "3", "max": "30", "mean": "11", "stdev": "5" }, { "name": "piPC06", "index": "61", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Uc", "index": "62", "type": "numeric", "distinct": "25", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "JGI1", "index": "63", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_betaP", "index": "64", "type": "numeric", "distinct": "42", "missing": "0", "min": "5", "max": "34", "mean": "14", "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 }