{ "data_id": "40337", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5480", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5480", "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: CHEMBL5480 (TID: 101208), 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": "2016-07-16 11:06:42", "update_comment": null, "last_update": "2016-07-16 11:06:42", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3693800\/data_52411.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5480", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5480 (TID: 101208), 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, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.463768115942029, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.7949688005469189, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.38553029334911787, "Quartile2MeansOfNumericAtts": 1.3591884057971015, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.7449977166866408, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.2296026978980964, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5280501250772054, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.18819732911866952, "MaxKurtosisOfNumericAtts": 35.363831038014546, "MinMeansOfNumericAtts": -0.10523913043478261, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 97.5580652173913, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.22116601577307815, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 4.6394927536231885, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.7518386919484279, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.237489278079737, "MinStdDevOfNumericAtts": 0.006727910795080508, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6994334582540097, "MaxStdDevOfNumericAtts": 48.53599922056597, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.1193266546996994, "Quartile3StdDevOfNumericAtts": 0.8248750903199086, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6894057971014492, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.04269948649040582, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4.761550494593973, "Quartile1SkewnessOfNumericAtts": -0.11372929942865895, "AutoCorrelation": 0.5993138686131385, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11912031956900526 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "81", "missing": "0", "target": "1", "min": "5", "max": "6", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "138", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_LogP_2", "index": "1", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "63", "mean": "19", "stdev": "17" }, { "name": "GATS1v", "index": "2", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DD", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCONN", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nN.CO.2", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS1p", "index": "6", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.041", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CIC4", "index": "8", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC4", "index": "9", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "10", "type": "numeric", "distinct": "53", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "NssNH", "index": "11", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SssNH", "index": "12", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "BIC4", "index": "13", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC5", "index": "14", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SIC5", "index": "15", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.072", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "BIC5", "index": "17", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NdS", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "S.108", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SdS", "index": "20", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "P_VSA_LogP_8", "index": "21", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "46", "mean": "10", "stdev": "19" }, { "name": "CATS2D_09_DL", "index": "22", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig03_AEA.ed.", "index": "23", "type": "numeric", "distinct": "58", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "GATS1m", "index": "24", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_08_DL", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "JGI4", "index": "26", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS2v", "index": "27", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "D.Dtr05", "index": "28", "type": "numeric", "distinct": "79", "missing": "0", "min": "36", "max": "258", "mean": "98", "stdev": "49" }, { "name": "GATS3v", "index": "29", "type": "numeric", "distinct": "112", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS3v", "index": "30", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "31", "type": "numeric", "distinct": "36", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "32", "type": "numeric", "distinct": "36", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "33", "type": "numeric", "distinct": "36", "missing": "0", "min": "10", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SpMax2_Bh.s.", "index": "34", "type": "numeric", "distinct": "52", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "35", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA", "index": "36", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "37", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS7s", "index": "38", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "39", "type": "numeric", "distinct": "27", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "40", "type": "numeric", "distinct": "44", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "41", "type": "numeric", "distinct": "27", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig03_AEA.bo.", "index": "42", "type": "numeric", "distinct": "76", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "43", "type": "numeric", "distinct": "120", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA", "index": "44", "type": "numeric", "distinct": "39", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "45", "type": "numeric", "distinct": "39", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "46", "type": "numeric", "distinct": "39", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "47", "type": "numeric", "distinct": "39", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS5s", "index": "48", "type": "numeric", "distinct": "128", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS3p", "index": "49", "type": "numeric", "distinct": "121", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "50", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "51", "type": "numeric", "distinct": "61", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "52", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "53", "type": "numeric", "distinct": "61", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "54", "type": "numeric", "distinct": "69", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nDB", "index": "55", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "MATS3m", "index": "56", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SssCH2", "index": "57", "type": "numeric", "distinct": "73", "missing": "0", "min": "-1", "max": "7", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.bo.", "index": "58", "type": "numeric", "distinct": "47", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "59", "type": "numeric", "distinct": "47", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS3e", "index": "60", "type": "numeric", "distinct": "119", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS5e", "index": "61", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "62", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" } ], "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 }