{ "data_id": "33836", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3403", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3403", "version": 10, "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: CHEMBL3403 (TID: 11924), and it has 233 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 13:48:48", "update_comment": null, "last_update": "2016-07-15 13:48:48", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3515178\/data_52488.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-CHEMBL3403", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3403 (TID: 11924), and it has 233 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": 233, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.6835162313247554, "MinStdDevOfNumericAtts": 0.003875704999195287, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.4656289202350472, "MaxStdDevOfNumericAtts": 30.305537743132053, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.30250189056253607, "Quartile3StdDevOfNumericAtts": 1.1403311743582503, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.33905579399141617, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.3079917928935236, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4.984396007902446, "Quartile1SkewnessOfNumericAtts": -0.09413573484039968, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1131306541852517, "AutoCorrelation": 0.22080172413793114, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.5783800322795365, "Dimensionality": 0.27467811158798283, "MeanSkewnessOfNumericAtts": 0.567209261225736, "Quartile2MeansOfNumericAtts": 1.3563390557939914, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.3823322211075788, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5982869449896288, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3146145468526085, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4320477497947518, "MaxKurtosisOfNumericAtts": 6.4942949598392445, "MinMeansOfNumericAtts": -0.05272532188841202, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 51.119978540772536, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.0783249443456024, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 4.972935622317596, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0511233252797845, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "187", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "233", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MATS4i", "index": "1", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GGI5", "index": "2", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GATS4e", "index": "3", "type": "numeric", "distinct": "175", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "JGI5", "index": "4", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SaaaC", "index": "5", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS4p", "index": "6", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "7", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_betaP", "index": "8", "type": "numeric", "distinct": "25", "missing": "0", "min": "7", "max": "29", "mean": "16", "stdev": "3" }, { "name": "JGI7", "index": "9", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.028", "index": "10", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "JGI1", "index": "11", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS2s", "index": "12", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.070", "index": "13", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nArNHR", "index": "14", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "15", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "H.047", "index": "16", "type": "numeric", "distinct": "24", "missing": "0", "min": "4", "max": "31", "mean": "18", "stdev": "5" }, { "name": "PCD", "index": "17", "type": "numeric", "distinct": "175", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SaaN", "index": "18", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "3" }, { "name": "Eig03_AEA.ri.", "index": "19", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA", "index": "20", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "21", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS7s", "index": "22", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "GATS4i", "index": "23", "type": "numeric", "distinct": "153", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "O.", "index": "24", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "MATS5s", "index": "25", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.075", "index": "26", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NaaN", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nPyridines", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "GATS1e", "index": "29", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMAD_AEA.ed.", "index": "30", "type": "numeric", "distinct": "116", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_05_AL", "index": "31", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "5" }, { "name": "IVDE", "index": "32", "type": "numeric", "distinct": "114", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "33", "type": "numeric", "distinct": "117", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "34", "type": "numeric", "distinct": "109", "missing": "0", "min": "15", "max": "18", "mean": "16", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "35", "type": "numeric", "distinct": "111", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "36", "type": "numeric", "distinct": "106", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "37", "type": "numeric", "distinct": "104", "missing": "0", "min": "19", "max": "22", "mean": "21", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "38", "type": "numeric", "distinct": "104", "missing": "0", "min": "20", "max": "24", "mean": "22", "stdev": "1" }, { "name": "Eta_B_A", "index": "39", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaaC", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_AL", "index": "41", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "4" }, { "name": "GGI1", "index": "42", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "14", "mean": "6", "stdev": "2" }, { "name": "Eig01_EA.bo.", "index": "43", "type": "numeric", "distinct": "40", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "44", "type": "numeric", "distinct": "40", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "45", "type": "numeric", "distinct": "41", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "46", "type": "numeric", "distinct": "40", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NdsCH", "index": "47", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "SdsCH", "index": "48", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "SpDiam_EA.ed.", "index": "49", "type": "numeric", "distinct": "44", "missing": "0", "min": "16", "max": "28", "mean": "20", "stdev": "3" }, { "name": "SpMAD_EA.dm.", "index": "50", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS2p", "index": "51", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "52", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nCconj", "index": "53", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "3" }, { "name": "JGI6", "index": "54", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Me", "index": "55", "type": "numeric", "distinct": "39", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "56", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "MATS2v", "index": "57", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "58", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "140", "mean": "51", "stdev": "30" }, { "name": "Eig04_EA.dm.", "index": "59", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.s.", "index": "60", "type": "numeric", "distinct": "33", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "CATS2D_09_AL", "index": "61", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "3" }, { "name": "GATS2p", "index": "62", "type": "numeric", "distinct": "149", "missing": "0", "min": "1", "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 }