{ "data_id": "26615", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3921", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3921", "version": 9, "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: CHEMBL3921 (TID: 11653), and it has 218 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 19:39:33", "update_comment": null, "last_update": "2016-07-14 19:39:33", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3307718\/data_52700.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3921", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3921 (TID: 11653), and it has 218 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": 218, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.372830275229357, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.164082554052566, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 41.12186175017642, "Quartile1SkewnessOfNumericAtts": 0.9551520207346405, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.570402271319506, "AutoCorrelation": 0.3599170506912448, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9127039858284554, "Dimensionality": 0.30275229357798167, "MeanSkewnessOfNumericAtts": 1.0403032417872915, "Quartile2MeansOfNumericAtts": 5.039454128440367, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 32.006078579936464, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.2350181659110733, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.9213607586175723, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9233389480715261, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 32.96688588982433, "MinMeansOfNumericAtts": 0.08727064220183486, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 299.10855963302754, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.147572356682639, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 12.908529816513761, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.071387585551897, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.3273879149728485, "MinStdDevOfNumericAtts": 0.0163882941406094, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.7970565649815606, "MaxStdDevOfNumericAtts": 445.5978066411925, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.21673232160847045, "Quartile3StdDevOfNumericAtts": 9.519925361047907 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "112", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "218", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_e_1", "index": "1", "type": "numeric", "distinct": "51", "missing": "0", "min": "71", "max": "1071", "mean": "292", "stdev": "207" }, { "name": "P_VSA_m_1", "index": "2", "type": "numeric", "distinct": "50", "missing": "0", "min": "71", "max": "1071", "mean": "292", "stdev": "207" }, { "name": "P_VSA_MR_1", "index": "3", "type": "numeric", "distinct": "63", "missing": "0", "min": "71", "max": "1001", "mean": "286", "stdev": "192" }, { "name": "P_VSA_p_1", "index": "4", "type": "numeric", "distinct": "68", "missing": "0", "min": "94", "max": "1071", "mean": "299", "stdev": "204" }, { "name": "P_VSA_s_2", "index": "5", "type": "numeric", "distinct": "68", "missing": "0", "min": "78", "max": "1073", "mean": "293", "stdev": "207" }, { "name": "P_VSA_v_1", "index": "6", "type": "numeric", "distinct": "50", "missing": "0", "min": "71", "max": "1071", "mean": "292", "stdev": "207" }, { "name": "SpMin4_Bh.m.", "index": "7", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC3v", "index": "8", "type": "numeric", "distinct": "192", "missing": "0", "min": "5", "max": "73", "mean": "17", "stdev": "15" }, { "name": "P_VSA_LogP_7", "index": "9", "type": "numeric", "distinct": "50", "missing": "0", "min": "59", "max": "1001", "mean": "282", "stdev": "190" }, { "name": "SpMin5_Bh.m.", "index": "10", "type": "numeric", "distinct": "116", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "11", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1v", "index": "12", "type": "numeric", "distinct": "155", "missing": "0", "min": "2", "max": "25", "mean": "7", "stdev": "5" }, { "name": "ATSC2v", "index": "13", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "48", "mean": "13", "stdev": "9" }, { "name": "SpMin3_Bh.v.", "index": "14", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin8_Bh.m.", "index": "15", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_LL", "index": "16", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "25", "mean": "11", "stdev": "6" }, { "name": "SpMin2_Bh.m.", "index": "17", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.s.", "index": "18", "type": "numeric", "distinct": "89", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "19", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS5s", "index": "20", "type": "numeric", "distinct": "189", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DECC", "index": "21", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SpMin4_Bh.v.", "index": "22", "type": "numeric", "distinct": "119", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS4p", "index": "23", "type": "numeric", "distinct": "182", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS5i", "index": "24", "type": "numeric", "distinct": "186", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS5p", "index": "25", "type": "numeric", "distinct": "187", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATSC3p", "index": "26", "type": "numeric", "distinct": "190", "missing": "0", "min": "4", "max": "67", "mean": "17", "stdev": "14" }, { "name": "ATSC4i", "index": "27", "type": "numeric", "distinct": "191", "missing": "0", "min": "1", "max": "9", "mean": "2", "stdev": "2" }, { "name": "ATSC4p", "index": "28", "type": "numeric", "distinct": "209", "missing": "0", "min": "4", "max": "84", "mean": "19", "stdev": "18" }, { "name": "ATSC5i", "index": "29", "type": "numeric", "distinct": "199", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "ATSC5p", "index": "30", "type": "numeric", "distinct": "210", "missing": "0", "min": "3", "max": "97", "mean": "20", "stdev": "22" }, { "name": "ATSC6i", "index": "31", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" }, { "name": "X4v", "index": "32", "type": "numeric", "distinct": "211", "missing": "0", "min": "2", "max": "28", "mean": "7", "stdev": "6" }, { "name": "X5v", "index": "33", "type": "numeric", "distinct": "207", "missing": "0", "min": "1", "max": "22", "mean": "5", "stdev": "5" }, { "name": "SM10_EA.bo.", "index": "34", "type": "numeric", "distinct": "151", "missing": "0", "min": "12", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SpDiam_AEA.dm.", "index": "35", "type": "numeric", "distinct": "47", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "X3Av", "index": "36", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.002", "index": "37", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "17", "mean": "2", "stdev": "4" }, { "name": "H.046", "index": "38", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "42", "mean": "5", "stdev": "12" }, { "name": "SpMin6_Bh.m.", "index": "39", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_LL", "index": "40", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "31", "mean": "13", "stdev": "7" }, { "name": "ATS2p", "index": "41", "type": "numeric", "distinct": "149", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3p", "index": "42", "type": "numeric", "distinct": "163", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS3v", "index": "43", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATSC2i", "index": "44", "type": "numeric", "distinct": "152", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "ATSC2p", "index": "45", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "46", "mean": "12", "stdev": "10" }, { "name": "ATSC3i", "index": "46", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "7", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_5", "index": "47", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "116", "mean": "39", "stdev": "26" }, { "name": "ATS4v", "index": "48", "type": "numeric", "distinct": "176", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS5e", "index": "49", "type": "numeric", "distinct": "184", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS5v", "index": "50", "type": "numeric", "distinct": "193", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS6e", "index": "51", "type": "numeric", "distinct": "189", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS6i", "index": "52", "type": "numeric", "distinct": "192", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS6p", "index": "53", "type": "numeric", "distinct": "190", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS6v", "index": "54", "type": "numeric", "distinct": "190", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS7e", "index": "55", "type": "numeric", "distinct": "198", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS7i", "index": "56", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS7p", "index": "57", "type": "numeric", "distinct": "193", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS7v", "index": "58", "type": "numeric", "distinct": "189", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS8e", "index": "59", "type": "numeric", "distinct": "194", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS8i", "index": "60", "type": "numeric", "distinct": "181", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS8p", "index": "61", "type": "numeric", "distinct": "197", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATSC1p", "index": "62", "type": "numeric", "distinct": "155", "missing": "0", "min": "2", "max": "31", "mean": "8", "stdev": "7" }, { "name": "ATSC2s", "index": "63", "type": "numeric", "distinct": "204", "missing": "0", "min": "13", "max": "1657", "mean": "267", "stdev": "446" }, { "name": "ATSC6p", "index": "64", "type": "numeric", "distinct": "210", "missing": "0", "min": "3", "max": "107", "mean": "21", "stdev": "26" } ], "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 }