{ "data_id": "35111", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5543", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5543", "version": 11, "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: CHEMBL5543 (TID: 101014), and it has 448 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": "2016-07-15 17:09:43", "update_comment": null, "last_update": "2016-07-15 17:09:43", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3548473\/data_53414.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5543", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5543 (TID: 101014), and it has 448 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": 448, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 25.811176247889826, "MinMeansOfNumericAtts": 0.11910714285714286, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.4825945730394086, "MaxMeansOfNumericAtts": 9923.962053571431, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 14.845110491071427, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.2679206047076756, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3SkewnessOfNumericAtts": 0.284488428280785, "MaxSkewnessOfNumericAtts": 1.9751996465795567, "MinStdDevOfNumericAtts": 0.04128969128709456, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 4.600627259609038, "MaxStdDevOfNumericAtts": 8175.1988949328415, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.3555503215007494, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.1260926339285717, "MeanKurtosisOfNumericAtts": 1.1242716477292736, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 296.4859719849898, "Quartile1SkewnessOfNumericAtts": -1.0426487996743108, "AutoCorrelation": 0.08899328859060282, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3380382721859018, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.15625, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.0194242247412042, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.24474852295840482, "Quartile2MeansOfNumericAtts": 3.8451183035714287, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 234.8026858152104, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.11250978166827659, "Quartile2StdDevOfNumericAtts": 0.9700519139735622, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6091892860331436, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "109", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "448", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMaxA_AEA.bo.", "index": "1", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "2", "type": "numeric", "distinct": "319", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Psi_i_0", "index": "3", "type": "numeric", "distinct": "418", "missing": "0", "min": "7", "max": "35", "mean": "18", "stdev": "6" }, { "name": "Chi1_EA.bo.", "index": "4", "type": "numeric", "distinct": "393", "missing": "0", "min": "4", "max": "22", "mean": "11", "stdev": "4" }, { "name": "X1v", "index": "5", "type": "numeric", "distinct": "416", "missing": "0", "min": "3", "max": "17", "mean": "9", "stdev": "3" }, { "name": "SpMaxA_AEA.ed.", "index": "6", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X0sol", "index": "7", "type": "numeric", "distinct": "310", "missing": "0", "min": "7", "max": "32", "mean": "18", "stdev": "5" }, { "name": "SpMax3_Bh.p.", "index": "8", "type": "numeric", "distinct": "318", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Psi_i_1", "index": "9", "type": "numeric", "distinct": "423", "missing": "0", "min": "5", "max": "30", "mean": "15", "stdev": "5" }, { "name": "SMTI", "index": "10", "type": "numeric", "distinct": "392", "missing": "0", "min": "505", "max": "53358", "mean": "9421", "stdev": "7624" }, { "name": "SpMaxA_AEA.ri.", "index": "11", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X1sol", "index": "12", "type": "numeric", "distinct": "369", "missing": "0", "min": "5", "max": "23", "mean": "13", "stdev": "4" }, { "name": "ATS8s", "index": "13", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpMaxA_EA", "index": "14", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2sol", "index": "15", "type": "numeric", "distinct": "395", "missing": "0", "min": "5", "max": "22", "mean": "12", "stdev": "3" }, { "name": "Eta_C", "index": "16", "type": "numeric", "distinct": "433", "missing": "0", "min": "5", "max": "50", "mean": "20", "stdev": "9" }, { "name": "Chi1_EA.ri.", "index": "17", "type": "numeric", "distinct": "432", "missing": "0", "min": "6", "max": "30", "mean": "15", "stdev": "4" }, { "name": "ATS6m", "index": "18", "type": "numeric", "distinct": "381", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "GMTI", "index": "19", "type": "numeric", "distinct": "393", "missing": "0", "min": "453", "max": "59334", "mean": "9924", "stdev": "8175" }, { "name": "Eig11_AEA.ed.", "index": "20", "type": "numeric", "distinct": "302", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig12_EA.bo.", "index": "21", "type": "numeric", "distinct": "307", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Sp", "index": "22", "type": "numeric", "distinct": "393", "missing": "0", "min": "10", "max": "57", "mean": "30", "stdev": "10" }, { "name": "Sv", "index": "23", "type": "numeric", "distinct": "403", "missing": "0", "min": "10", "max": "55", "mean": "29", "stdev": "9" }, { "name": "TIC2", "index": "24", "type": "numeric", "distinct": "409", "missing": "0", "min": "46", "max": "437", "mean": "199", "stdev": "80" }, { "name": "SpMax7_Bh.p.", "index": "25", "type": "numeric", "distinct": "311", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig10_EA.ri.", "index": "26", "type": "numeric", "distinct": "352", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Chi0_EA.bo.", "index": "27", "type": "numeric", "distinct": "390", "missing": "0", "min": "5", "max": "30", "mean": "15", "stdev": "5" }, { "name": "SpMax3_Bh.e.", "index": "28", "type": "numeric", "distinct": "309", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "29", "type": "numeric", "distinct": "310", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS2e", "index": "30", "type": "numeric", "distinct": "361", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1e", "index": "31", "type": "numeric", "distinct": "360", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nBT", "index": "32", "type": "numeric", "distinct": "72", "missing": "0", "min": "14", "max": "89", "mean": "47", "stdev": "16" }, { "name": "SpMaxA_EA.ri.", "index": "33", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Se", "index": "34", "type": "numeric", "distinct": "398", "missing": "0", "min": "14", "max": "83", "mean": "44", "stdev": "15" }, { "name": "Eta_L", "index": "35", "type": "numeric", "distinct": "425", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "X2", "index": "36", "type": "numeric", "distinct": "384", "missing": "0", "min": "4", "max": "22", "mean": "11", "stdev": "4" }, { "name": "ATS8p", "index": "37", "type": "numeric", "distinct": "379", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATS2v", "index": "38", "type": "numeric", "distinct": "364", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "39", "type": "numeric", "distinct": "328", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS7p", "index": "40", "type": "numeric", "distinct": "383", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig10_EA", "index": "41", "type": "numeric", "distinct": "317", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig10_EA.ed.", "index": "42", "type": "numeric", "distinct": "355", "missing": "0", "min": "-6", "max": "6", "mean": "2", "stdev": "2" }, { "name": "SM04_AEA.dm.", "index": "43", "type": "numeric", "distinct": "317", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM05_AEA.ri.", "index": "44", "type": "numeric", "distinct": "355", "missing": "0", "min": "-6", "max": "6", "mean": "2", "stdev": "2" }, { "name": "Eig06_AEA.ri.", "index": "45", "type": "numeric", "distinct": "363", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "1" }, { "name": "ATS7v", "index": "46", "type": "numeric", "distinct": "394", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "CID", "index": "47", "type": "numeric", "distinct": "289", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "48", "type": "numeric", "distinct": "312", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS1i", "index": "49", "type": "numeric", "distinct": "359", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "S0K", "index": "50", "type": "numeric", "distinct": "184", "missing": "0", "min": "31", "max": "268", "mean": "119", "stdev": "46" }, { "name": "ATS5m", "index": "51", "type": "numeric", "distinct": "380", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMax3_Bh.i.", "index": "52", "type": "numeric", "distinct": "298", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ISIZ", "index": "53", "type": "numeric", "distinct": "69", "missing": "0", "min": "48", "max": "529", "mean": "243", "stdev": "103" }, { "name": "nAT", "index": "54", "type": "numeric", "distinct": "69", "missing": "0", "min": "13", "max": "83", "mean": "44", "stdev": "15" }, { "name": "SpMax4_Bh.m.", "index": "55", "type": "numeric", "distinct": "345", "missing": "0", "min": "2", "max": "7", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "56", "type": "numeric", "distinct": "326", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Si", "index": "57", "type": "numeric", "distinct": "400", "missing": "0", "min": "15", "max": "94", "mean": "49", "stdev": "17" }, { "name": "ATS1v", "index": "58", "type": "numeric", "distinct": "358", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X1MulPer", "index": "59", "type": "numeric", "distinct": "418", "missing": "0", "min": "2", "max": "16", "mean": "8", "stdev": "3" }, { "name": "SpMaxA_EA.ed.", "index": "60", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Chi0_EA.ri.", "index": "61", "type": "numeric", "distinct": "427", "missing": "0", "min": "7", "max": "35", "mean": "18", "stdev": "5" }, { "name": "Eig10_EA.bo.", "index": "62", "type": "numeric", "distinct": "338", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "IVDM", "index": "63", "type": "numeric", "distinct": "217", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "X1", "index": "64", "type": "numeric", "distinct": "341", "missing": "0", "min": "5", "max": "24", "mean": "13", "stdev": "4" }, { "name": "SpMaxA_EA.bo.", "index": "65", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS2i", "index": "66", "type": "numeric", "distinct": "369", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS8e", "index": "67", "type": "numeric", "distinct": "381", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig11_EA.bo.", "index": "68", "type": "numeric", "distinct": "338", "missing": "0", "min": "-3", "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 }