{ "data_id": "38130", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3201", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3201", "version": 12, "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: CHEMBL3201 (TID: 10694), and it has 212 rows and 65 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": "2016-07-16 03:03:45", "update_comment": null, "last_update": "2016-07-16 03:03:45", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3630261\/data_53016.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3201", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3201 (TID: 10694), and it has 212 rows and 65 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": 212, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 1.9646644884267, "MinMeansOfNumericAtts": 0.02790566037735849, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.5595378263569184, "MaxMeansOfNumericAtts": 162.9637641509434, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 5.582549528301887, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.6298810461950092, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 0.5190311118385832, "MaxSkewnessOfNumericAtts": 1.443339109263025, "MinStdDevOfNumericAtts": 0.006551333284781077, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 3.3521348742341672, "MaxStdDevOfNumericAtts": 62.988316170473276, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.2676828262419209, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.776245283018868, "MeanKurtosisOfNumericAtts": -0.8256657623863284, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 20.116790666094914, "Quartile1SkewnessOfNumericAtts": -0.21578590674844006, "AutoCorrelation": 0.0429052132701419, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.28968485159129487, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3160377358490566, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.9174528391657517, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.16371451684449417, "Quartile2MeansOfNumericAtts": 2.802672169811321, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.664877217067257, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.22059452063336515, "Quartile2StdDevOfNumericAtts": 0.4525721642144741, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4980365205533777, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "185", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "212", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATS5i", "index": "1", "type": "numeric", "distinct": "168", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS4i", "index": "2", "type": "numeric", "distinct": "158", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.s.", "index": "3", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC6p", "index": "4", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "ATSC5i", "index": "5", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC6i", "index": "6", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS6i", "index": "7", "type": "numeric", "distinct": "178", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS6e", "index": "8", "type": "numeric", "distinct": "182", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "9", "type": "numeric", "distinct": "160", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "10", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "11", "type": "numeric", "distinct": "170", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "12", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "13", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "14", "type": "numeric", "distinct": "139", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "15", "type": "numeric", "distinct": "171", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "16", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS5e", "index": "17", "type": "numeric", "distinct": "185", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "18", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "AMW", "index": "19", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "11", "stdev": "4" }, { "name": "SpMin8_Bh.m.", "index": "20", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5v", "index": "21", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "4" }, { "name": "SpMin5_Bh.e.", "index": "22", "type": "numeric", "distinct": "156", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.i.", "index": "23", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.p.", "index": "24", "type": "numeric", "distinct": "174", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "25", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "26", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "51", "mean": "32", "stdev": "11" }, { "name": "SpMin7_Bh.v.", "index": "27", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.v.", "index": "28", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.", "index": "29", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "19", "mean": "6", "stdev": "5" }, { "name": "nN", "index": "30", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "RBF", "index": "31", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "32", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "ATS8i", "index": "33", "type": "numeric", "distinct": "170", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax7_Bh.i.", "index": "34", "type": "numeric", "distinct": "146", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.e.", "index": "35", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS1i", "index": "36", "type": "numeric", "distinct": "148", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2i", "index": "37", "type": "numeric", "distinct": "156", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS7i", "index": "38", "type": "numeric", "distinct": "182", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATSC1i", "index": "39", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2i", "index": "40", "type": "numeric", "distinct": "154", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Si", "index": "41", "type": "numeric", "distinct": "162", "missing": "0", "min": "23", "max": "65", "mean": "35", "stdev": "11" }, { "name": "TIC4", "index": "42", "type": "numeric", "distinct": "139", "missing": "0", "min": "56", "max": "293", "mean": "147", "stdev": "55" }, { "name": "TIC5", "index": "43", "type": "numeric", "distinct": "136", "missing": "0", "min": "56", "max": "293", "mean": "148", "stdev": "55" }, { "name": "SpMin4_Bh.m.", "index": "44", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "45", "type": "numeric", "distinct": "165", "missing": "0", "min": "49", "max": "235", "mean": "124", "stdev": "44" }, { "name": "Eta_B_A", "index": "46", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "TIC2", "index": "47", "type": "numeric", "distinct": "176", "missing": "0", "min": "48", "max": "268", "mean": "126", "stdev": "51" }, { "name": "ATSC6v", "index": "48", "type": "numeric", "distinct": "199", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "P_VSA_p_3", "index": "49", "type": "numeric", "distinct": "165", "missing": "0", "min": "68", "max": "362", "mean": "163", "stdev": "63" }, { "name": "P_VSA_v_3", "index": "50", "type": "numeric", "distinct": "165", "missing": "0", "min": "68", "max": "362", "mean": "163", "stdev": "63" }, { "name": "P_VSA_i_4", "index": "51", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "129", "mean": "33", "stdev": "31" }, { "name": "ATSC4i", "index": "52", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1v", "index": "53", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "54", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "55", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC4v", "index": "56", "type": "numeric", "distinct": "201", "missing": "0", "min": "0", "max": "18", "mean": "6", "stdev": "4" }, { "name": "ATSC3i", "index": "57", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS8e", "index": "58", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATSC7i", "index": "59", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC8i", "index": "60", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ISIZ", "index": "61", "type": "numeric", "distinct": "35", "missing": "0", "min": "92", "max": "332", "mean": "161", "stdev": "61" }, { "name": "nAT", "index": "62", "type": "numeric", "distinct": "35", "missing": "0", "min": "21", "max": "57", "mean": "32", "stdev": "9" }, { "name": "nBT", "index": "63", "type": "numeric", "distinct": "34", "missing": "0", "min": "23", "max": "60", "mean": "34", "stdev": "10" }, { "name": "SpMax3_Bh.e.", "index": "64", "type": "numeric", "distinct": "163", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "65", "type": "numeric", "distinct": "153", "missing": "0", "min": "2", "max": "3", "mean": "2", "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 }