{ "data_id": "33615", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5469", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5469", "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: CHEMBL5469 (TID: 100995), and it has 785 rows and 69 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 13:14:19", "update_comment": null, "last_update": "2016-07-15 13:14:19", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3509555\/data_53598.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5469", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5469 (TID: 100995), and it has 785 rows and 69 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": 785, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.09044585987261146, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.11255745486393365, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.031688248613104486, "Quartile2MeansOfNumericAtts": 5.352315286624204, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 447.06213604604557, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.1772757523965342, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6760512510021153, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6532031586758056, "MaxKurtosisOfNumericAtts": 5.973934105383872, "MinMeansOfNumericAtts": 0.01710318471337576, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 31380.149044586065, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.5315799597124868, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 18.61442101910828, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.062792297056324, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.8065695671158462, "MinStdDevOfNumericAtts": 0.09487805422849013, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.3246774820181119, "MaxStdDevOfNumericAtts": 19842.735963117382, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.23878644477658872, "Quartile3StdDevOfNumericAtts": 4.691183765949185, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.4904528662420384, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.34043038672058934, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 730.2510752320306, "Quartile1SkewnessOfNumericAtts": -0.5304490983212881, "AutoCorrelation": 0.4737142857142856, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3214121247727168 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "240", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "785", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Psi_e_1", "index": "1", "type": "numeric", "distinct": "685", "missing": "0", "min": "2", "max": "8", "mean": "4", "stdev": "1" }, { "name": "ATSC1i", "index": "2", "type": "numeric", "distinct": "471", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "3", "type": "numeric", "distinct": "694", "missing": "0", "min": "0", "max": "77", "mean": "24", "stdev": "15" }, { "name": "SM03_AEA.ed.", "index": "4", "type": "numeric", "distinct": "456", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "X2", "index": "5", "type": "numeric", "distinct": "691", "missing": "0", "min": "5", "max": "20", "mean": "12", "stdev": "3" }, { "name": "SM04_EA", "index": "6", "type": "numeric", "distinct": "230", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC2i", "index": "7", "type": "numeric", "distinct": "570", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATSC8i", "index": "8", "type": "numeric", "distinct": "634", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM04_AEA.ed.", "index": "9", "type": "numeric", "distinct": "515", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "ATS2s", "index": "10", "type": "numeric", "distinct": "567", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Ram", "index": "11", "type": "numeric", "distinct": "18", "missing": "0", "min": "3", "max": "22", "mean": "10", "stdev": "3" }, { "name": "SM02_EA.ed.", "index": "12", "type": "numeric", "distinct": "334", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "13", "type": "numeric", "distinct": "444", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Psi_e_0", "index": "14", "type": "numeric", "distinct": "707", "missing": "0", "min": "4", "max": "17", "mean": "10", "stdev": "2" }, { "name": "Chi1_EA.bo.", "index": "15", "type": "numeric", "distinct": "705", "missing": "0", "min": "5", "max": "21", "mean": "11", "stdev": "3" }, { "name": "SPI", "index": "16", "type": "numeric", "distinct": "696", "missing": "0", "min": "0", "max": "26", "mean": "13", "stdev": "5" }, { "name": "ATSC4i", "index": "17", "type": "numeric", "distinct": "624", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "GGI2", "index": "18", "type": "numeric", "distinct": "36", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Eig05_EA", "index": "19", "type": "numeric", "distinct": "522", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM13_AEA.bo.", "index": "20", "type": "numeric", "distinct": "522", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS2m", "index": "21", "type": "numeric", "distinct": "505", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_epsi", "index": "22", "type": "numeric", "distinct": "593", "missing": "0", "min": "13", "max": "51", "mean": "29", "stdev": "7" }, { "name": "SM02_AEA.ed.", "index": "23", "type": "numeric", "distinct": "184", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "IAC", "index": "24", "type": "numeric", "distinct": "676", "missing": "0", "min": "31", "max": "137", "mean": "76", "stdev": "20" }, { "name": "TIC0", "index": "25", "type": "numeric", "distinct": "676", "missing": "0", "min": "31", "max": "137", "mean": "76", "stdev": "20" }, { "name": "Eig08_AEA.ed.", "index": "26", "type": "numeric", "distinct": "545", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "GGI10", "index": "27", "type": "numeric", "distinct": "223", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Dz", "index": "28", "type": "numeric", "distinct": "240", "missing": "0", "min": "27", "max": "103", "mean": "60", "stdev": "14" }, { "name": "GGI8", "index": "29", "type": "numeric", "distinct": "363", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X0", "index": "30", "type": "numeric", "distinct": "366", "missing": "0", "min": "9", "max": "32", "mean": "19", "stdev": "4" }, { "name": "XMOD", "index": "31", "type": "numeric", "distinct": "754", "missing": "0", "min": "37", "max": "143", "mean": "87", "stdev": "19" }, { "name": "Eta_C", "index": "32", "type": "numeric", "distinct": "763", "missing": "0", "min": "6", "max": "50", "mean": "21", "stdev": "8" }, { "name": "ATSC7i", "index": "33", "type": "numeric", "distinct": "638", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig04_EA", "index": "34", "type": "numeric", "distinct": "500", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "35", "type": "numeric", "distinct": "500", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax7_Bh.i.", "index": "36", "type": "numeric", "distinct": "430", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "37", "type": "numeric", "distinct": "501", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nArNHR", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "GMTIV", "index": "39", "type": "numeric", "distinct": "761", "missing": "0", "min": "1858", "max": "129162", "mean": "31380", "stdev": "19843" }, { "name": "SpAD_EA.ed.", "index": "40", "type": "numeric", "distinct": "725", "missing": "0", "min": "53", "max": "274", "mean": "133", "stdev": "33" }, { "name": "SMTIV", "index": "41", "type": "numeric", "distinct": "758", "missing": "0", "min": "1450", "max": "71800", "mean": "17548", "stdev": "10910" }, { "name": "Eig06_AEA.dm.", "index": "42", "type": "numeric", "distinct": "565", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Psi_i_s", "index": "43", "type": "numeric", "distinct": "504", "missing": "0", "min": "25", "max": "112", "mean": "65", "stdev": "16" }, { "name": "ON0", "index": "44", "type": "numeric", "distinct": "150", "missing": "0", "min": "6", "max": "23", "mean": "14", "stdev": "3" }, { "name": "ZM2Kup", "index": "45", "type": "numeric", "distinct": "759", "missing": "0", "min": "145", "max": "759", "mean": "443", "stdev": "108" }, { "name": "ZM2Mad", "index": "46", "type": "numeric", "distinct": "761", "missing": "0", "min": "76", "max": "380", "mean": "204", "stdev": "50" }, { "name": "Eig05_AEA.ri.", "index": "47", "type": "numeric", "distinct": "537", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDDM", "index": "48", "type": "numeric", "distinct": "305", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM03_EA", "index": "49", "type": "numeric", "distinct": "22", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig05_AEA.ed.", "index": "50", "type": "numeric", "distinct": "561", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "MW", "index": "51", "type": "numeric", "distinct": "694", "missing": "0", "min": "163", "max": "642", "mean": "385", "stdev": "85" }, { "name": "ATS1e", "index": "52", "type": "numeric", "distinct": "509", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig14_AEA.ed.", "index": "53", "type": "numeric", "distinct": "513", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig06_AEA.ed.", "index": "54", "type": "numeric", "distinct": "556", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATSC5i", "index": "55", "type": "numeric", "distinct": "627", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "TIC1", "index": "56", "type": "numeric", "distinct": "735", "missing": "0", "min": "50", "max": "328", "mean": "169", "stdev": "50" }, { "name": "Eig05_EA.ed.", "index": "57", "type": "numeric", "distinct": "657", "missing": "0", "min": "1", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "58", "type": "numeric", "distinct": "657", "missing": "0", "min": "1", "max": "10", "mean": "6", "stdev": "1" }, { "name": "LPRS", "index": "59", "type": "numeric", "distinct": "725", "missing": "0", "min": "41", "max": "277", "mean": "138", "stdev": "43" }, { "name": "S1K", "index": "60", "type": "numeric", "distinct": "625", "missing": "0", "min": "7", "max": "32", "mean": "18", "stdev": "5" }, { "name": "Eig08_EA.ed.", "index": "61", "type": "numeric", "distinct": "627", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "62", "type": "numeric", "distinct": "627", "missing": "0", "min": "-3", "max": "8", "mean": "4", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "63", "type": "numeric", "distinct": "558", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC3i", "index": "64", "type": "numeric", "distinct": "617", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATS7s", "index": "65", "type": "numeric", "distinct": "625", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS8m", "index": "66", "type": "numeric", "distinct": "633", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATS5e", "index": "67", "type": "numeric", "distinct": "584", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "68", "type": "numeric", "distinct": "472", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eta_betaS", "index": "69", "type": "numeric", "distinct": "87", "missing": "0", "min": "8", "max": "31", "mean": "18", "stdev": "4" } ], "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 }