{ "data_id": "35716", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3437", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3437", "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: CHEMBL3437 (TID: 20143), and it has 138 rows and 62 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 18:47:41", "update_comment": null, "last_update": "2016-07-15 18:47:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3565885\/data_52390.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3437", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3437 (TID: 20143), and it has 138 rows and 62 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": 138, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.559904194963734, "MinStdDevOfNumericAtts": 0.007072055134189015, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.163541906344566, "MaxStdDevOfNumericAtts": 33.12580207287644, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6680851442412816, "Quartile3StdDevOfNumericAtts": 1.9089444312597406, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.33641304347826084, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.854283512158186, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.328561306648263, "Quartile1SkewnessOfNumericAtts": 0.04063714689291828, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1488417391856617, "AutoCorrelation": 0.21825547445255492, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.014971164593485575, "Dimensionality": 0.463768115942029, "MeanSkewnessOfNumericAtts": 0.6823769355359645, "Quartile2MeansOfNumericAtts": 1.0583478260869565, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.5652015791064917, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5090720005246353, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9980197115883414, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4733855536086696, "MaxKurtosisOfNumericAtts": 24.13929244811075, "MinMeansOfNumericAtts": -0.049768115942028984, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 73.13126811594202, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.353387030941928, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 4.420710144927536, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.622976790175294, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "103", "missing": "0", "target": "1", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "138", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_01_AP", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_DA", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NsssN", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssN", "index": "4", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.068", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "6", "type": "numeric", "distinct": "73", "missing": "0", "min": "3", "max": "117", "mean": "40", "stdev": "31" }, { "name": "LOC", "index": "7", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nN.N", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "9", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "88", "mean": "27", "stdev": "23" }, { "name": "GATS2i", "index": "10", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS3v", "index": "11", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS1e", "index": "12", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2v", "index": "13", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1e", "index": "14", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_1", "index": "15", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "53", "mean": "12", "stdev": "12" }, { "name": "GATS3p", "index": "16", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SsCH3", "index": "17", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "ATSC2e", "index": "18", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NsCH3", "index": "19", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "GATS3s", "index": "20", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS2p", "index": "21", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.005", "index": "22", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "H.047", "index": "23", "type": "numeric", "distinct": "18", "missing": "0", "min": "2", "max": "20", "mean": "10", "stdev": "4" }, { "name": "GATS2p", "index": "24", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PDI", "index": "25", "type": "numeric", "distinct": "81", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.069", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS3i", "index": "27", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1s", "index": "28", "type": "numeric", "distinct": "119", "missing": "0", "min": "5", "max": "50", "mean": "11", "stdev": "6" }, { "name": "JGI6", "index": "29", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GNar", "index": "30", "type": "numeric", "distinct": "49", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "HNar", "index": "31", "type": "numeric", "distinct": "43", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0A", "index": "32", "type": "numeric", "distinct": "41", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "33", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "BAC", "index": "34", "type": "numeric", "distinct": "37", "missing": "0", "min": "3", "max": "64", "mean": "19", "stdev": "12" }, { "name": "MATS2i", "index": "35", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1v", "index": "36", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "37", "type": "numeric", "distinct": "20", "missing": "0", "min": "33", "max": "132", "mean": "51", "stdev": "24" }, { "name": "P_VSA_MR_6", "index": "38", "type": "numeric", "distinct": "66", "missing": "0", "min": "6", "max": "149", "mean": "73", "stdev": "33" }, { "name": "SaasC", "index": "39", "type": "numeric", "distinct": "125", "missing": "0", "min": "-2", "max": "4", "mean": "2", "stdev": "1" }, { "name": "ATSC3e", "index": "40", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SssNH", "index": "41", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "Eta_B", "index": "42", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "IVDE", "index": "43", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC6v", "index": "44", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "20", "mean": "6", "stdev": "3" }, { "name": "nN", "index": "45", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "ATS5i", "index": "46", "type": "numeric", "distinct": "122", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_sh_p", "index": "47", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.075", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NaaN", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaN", "index": "50", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "ATSC5e", "index": "51", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS6s", "index": "52", "type": "numeric", "distinct": "125", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "nROR", "index": "53", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.059", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax6_Bh.s.", "index": "55", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IAC", "index": "56", "type": "numeric", "distinct": "87", "missing": "0", "min": "21", "max": "76", "mean": "48", "stdev": "13" }, { "name": "TIC0", "index": "57", "type": "numeric", "distinct": "87", "missing": "0", "min": "21", "max": "76", "mean": "48", "stdev": "13" }, { "name": "SPI", "index": "58", "type": "numeric", "distinct": "106", "missing": "0", "min": "3", "max": "15", "mean": "8", "stdev": "3" }, { "name": "CATS2D_02_PL", "index": "59", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SAdon", "index": "60", "type": "numeric", "distinct": "15", "missing": "0", "min": "33", "max": "118", "mean": "54", "stdev": "24" }, { "name": "JGI7", "index": "61", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_C_A", "index": "62", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "1", "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 }