{ "data_id": "37806", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1808", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1808", "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: CHEMBL1808 (TID: 69), and it has 569 rows and 68 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 01:55:23", "update_comment": null, "last_update": "2016-07-16 01:55:23", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3622099\/data_53343.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1808", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1808 (TID: 69), and it has 569 rows and 68 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": 569, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.12302284710017575, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.6682146060752805, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.039412505889359045, "Quartile2MeansOfNumericAtts": 3.0826731107205623, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.151938720517312, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.4172425087044785, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5858580162730773, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6848469333810583, "MaxKurtosisOfNumericAtts": 19.207265949710273, "MinMeansOfNumericAtts": 0.14527065026362038, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 394.345079086116, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.1186324177865, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 13.35387346221441, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.6846332765193526, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.9403805102069263, "MinStdDevOfNumericAtts": 0.04567730351159638, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1095801963779497, "MaxStdDevOfNumericAtts": 117.2096240552136, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.0009977008379147, "Quartile3StdDevOfNumericAtts": 1.8650203126589155, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.238663444639719, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 3.846899322602706, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 20.15016265505209, "Quartile1SkewnessOfNumericAtts": -0.7701786196252056, "AutoCorrelation": -0.5405633802816897, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4966431691683657 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "339", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "569", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_02_AN", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "GGI4", "index": "2", "type": "numeric", "distinct": "289", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig02_EA.dm.", "index": "3", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SM12_EA.dm.", "index": "4", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "19", "mean": "12", "stdev": "3" }, { "name": "SM14_EA.dm.", "index": "5", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "23", "mean": "13", "stdev": "3" }, { "name": "SpDiam_EA.dm.", "index": "6", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "1" }, { "name": "CATS2D_02_AA", "index": "7", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_AN", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_AA", "index": "9", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "SsssN", "index": "10", "type": "numeric", "distinct": "264", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "ATSC6s", "index": "11", "type": "numeric", "distinct": "485", "missing": "0", "min": "23", "max": "637", "mean": "135", "stdev": "70" }, { "name": "SM11_AEA.ed.", "index": "12", "type": "numeric", "distinct": "359", "missing": "0", "min": "18", "max": "23", "mean": "22", "stdev": "1" }, { "name": "SM12_EA", "index": "13", "type": "numeric", "distinct": "371", "missing": "0", "min": "11", "max": "16", "mean": "14", "stdev": "1" }, { "name": "ATS6s", "index": "14", "type": "numeric", "distinct": "411", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "0" }, { "name": "GGI9", "index": "15", "type": "numeric", "distinct": "210", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SdO", "index": "16", "type": "numeric", "distinct": "477", "missing": "0", "min": "0", "max": "151", "mean": "35", "stdev": "15" }, { "name": "SM11_EA", "index": "17", "type": "numeric", "distinct": "360", "missing": "0", "min": "10", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM09_AEA.ed.", "index": "18", "type": "numeric", "distinct": "372", "missing": "0", "min": "15", "max": "19", "mean": "18", "stdev": "1" }, { "name": "CATS2D_01_AN", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_NL", "index": "20", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "O.057", "index": "21", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "22", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM10_AEA.ed.", "index": "23", "type": "numeric", "distinct": "364", "missing": "0", "min": "17", "max": "21", "mean": "20", "stdev": "1" }, { "name": "SM04_EA.ed.", "index": "24", "type": "numeric", "distinct": "364", "missing": "0", "min": "8", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "25", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "P_VSA_e_5", "index": "26", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "395", "mean": "135", "stdev": "47" }, { "name": "SpMax6_Bh.m.", "index": "27", "type": "numeric", "distinct": "313", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM08_EA.dm.", "index": "28", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "13", "mean": "8", "stdev": "2" }, { "name": "SM05_EA.ed.", "index": "29", "type": "numeric", "distinct": "354", "missing": "0", "min": "9", "max": "14", "mean": "12", "stdev": "1" }, { "name": "Eig06_AEA.dm.", "index": "30", "type": "numeric", "distinct": "356", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NsssN", "index": "31", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "X0sol", "index": "32", "type": "numeric", "distinct": "330", "missing": "0", "min": "8", "max": "63", "mean": "20", "stdev": "6" }, { "name": "SM15_EA", "index": "33", "type": "numeric", "distinct": "375", "missing": "0", "min": "13", "max": "20", "mean": "18", "stdev": "1" }, { "name": "Eta_C_A", "index": "34", "type": "numeric", "distinct": "313", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC7e", "index": "35", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "MAXDP", "index": "36", "type": "numeric", "distinct": "437", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "37", "type": "numeric", "distinct": "336", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_EA.ed.", "index": "38", "type": "numeric", "distinct": "366", "missing": "0", "min": "11", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM10_EA", "index": "39", "type": "numeric", "distinct": "371", "missing": "0", "min": "9", "max": "13", "mean": "12", "stdev": "1" }, { "name": "ATSC6m", "index": "40", "type": "numeric", "distinct": "485", "missing": "0", "min": "1", "max": "156", "mean": "38", "stdev": "16" }, { "name": "X1sol", "index": "41", "type": "numeric", "distinct": "396", "missing": "0", "min": "5", "max": "39", "mean": "13", "stdev": "4" }, { "name": "SpMin5_Bh.i.", "index": "42", "type": "numeric", "distinct": "333", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "43", "type": "numeric", "distinct": "352", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "P_VSA_m_3", "index": "44", "type": "numeric", "distinct": "89", "missing": "0", "min": "25", "max": "395", "mean": "137", "stdev": "46" }, { "name": "SM09_EA", "index": "45", "type": "numeric", "distinct": "364", "missing": "0", "min": "8", "max": "12", "mean": "11", "stdev": "1" }, { "name": "Eig12_AEA.dm.", "index": "46", "type": "numeric", "distinct": "309", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "47", "type": "numeric", "distinct": "346", "missing": "0", "min": "-2", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "48", "type": "numeric", "distinct": "321", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig10_AEA.bo.", "index": "49", "type": "numeric", "distinct": "306", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_AEA.ri.", "index": "50", "type": "numeric", "distinct": "338", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig10_EA.ed.", "index": "51", "type": "numeric", "distinct": "321", "missing": "0", "min": "-6", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SM05_AEA.ri.", "index": "52", "type": "numeric", "distinct": "321", "missing": "0", "min": "-6", "max": "8", "mean": "1", "stdev": "2" }, { "name": "Eig04_EA", "index": "53", "type": "numeric", "distinct": "305", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "54", "type": "numeric", "distinct": "305", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eta_alpha", "index": "55", "type": "numeric", "distinct": "237", "missing": "0", "min": "5", "max": "38", "mean": "13", "stdev": "4" }, { "name": "IAC", "index": "56", "type": "numeric", "distinct": "386", "missing": "0", "min": "33", "max": "274", "mean": "84", "stdev": "26" }, { "name": "TIC0", "index": "57", "type": "numeric", "distinct": "386", "missing": "0", "min": "33", "max": "274", "mean": "84", "stdev": "26" }, { "name": "Eig10_AEA.ed.", "index": "58", "type": "numeric", "distinct": "309", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM07_EA.dm.", "index": "59", "type": "numeric", "distinct": "141", "missing": "0", "min": "0", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SM07_AEA.ed.", "index": "60", "type": "numeric", "distinct": "350", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "0" }, { "name": "SpMin5_Bh.p.", "index": "61", "type": "numeric", "distinct": "317", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig11_EA.ed.", "index": "62", "type": "numeric", "distinct": "299", "missing": "0", "min": "-6", "max": "7", "mean": "1", "stdev": "2" }, { "name": "SM06_AEA.ri.", "index": "63", "type": "numeric", "distinct": "299", "missing": "0", "min": "-6", "max": "7", "mean": "1", "stdev": "2" }, { "name": "MW", "index": "64", "type": "numeric", "distinct": "387", "missing": "0", "min": "162", "max": "1175", "mean": "394", "stdev": "117" }, { "name": "Eig04_EA.ri.", "index": "65", "type": "numeric", "distinct": "358", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "IC4", "index": "66", "type": "numeric", "distinct": "342", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMaxA_EA.bo.", "index": "67", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig10_EA.bo.", "index": "68", "type": "numeric", "distinct": "309", "missing": "0", "min": "-2", "max": "3", "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 }