{ "data_id": "31346", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5555", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5555", "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: CHEMBL5555 (TID: 101234), and it has 334 rows and 65 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 07:20:08", "update_comment": null, "last_update": "2016-07-15 07:20:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3446040\/data_52801.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5555", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5555 (TID: 101234), and it has 334 rows and 65 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": 334, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 24.56866165065492, "MinMeansOfNumericAtts": -0.532820359281437, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.029753972349154, "MaxMeansOfNumericAtts": 212.32914371257485, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 6.681690119760479, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.129928400337095, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 2.150932241947166, "MaxSkewnessOfNumericAtts": 4.673631386598602, "MinStdDevOfNumericAtts": 0.03340880717565197, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.2981549498276492, "MaxStdDevOfNumericAtts": 68.10910242830882, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.12696497126792095, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.12574850299401208, "MeanKurtosisOfNumericAtts": 3.13832865753652, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 12.642071175830159, "Quartile1SkewnessOfNumericAtts": -0.2642593618530744, "AutoCorrelation": 0.046906906906906576, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.15538730655787708, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.20059880239520958, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.6313310171523838, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.7470904524637771, "Quartile2MeansOfNumericAtts": 1.7937784431137729, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.019536176426471, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.27194522064054044, "Quartile2StdDevOfNumericAtts": 0.3401611048091704, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9014728463074566, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "230", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "334", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_03_AN", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_AN", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_DN", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.057", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_AN", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_NL", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "7", "type": "numeric", "distinct": "110", "missing": "0", "min": "17", "max": "192", "mean": "97", "stdev": "33" }, { "name": "P_VSA_LogP_2", "index": "8", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "68", "mean": "25", "stdev": "12" }, { "name": "CATS2D_01_AA", "index": "9", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "10", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "11", "type": "numeric", "distinct": "77", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "12", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_02_AN", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "14", "type": "numeric", "distinct": "247", "missing": "0", "min": "-4", "max": "0", "mean": "-1", "stdev": "0" }, { "name": "CATS2D_04_AN", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS5s", "index": "16", "type": "numeric", "distinct": "273", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_AA", "index": "17", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "P_VSA_MR_5", "index": "18", "type": "numeric", "distinct": "212", "missing": "0", "min": "6", "max": "107", "mean": "47", "stdev": "16" }, { "name": "nRCOOH", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpDiam_AEA.ed.", "index": "21", "type": "numeric", "distinct": "128", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "GATS6v", "index": "22", "type": "numeric", "distinct": "216", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.075", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "NaaN", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMax1_Bh.m.", "index": "25", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "26", "type": "numeric", "distinct": "145", "missing": "0", "min": "29", "max": "153", "mean": "97", "stdev": "19" }, { "name": "CATS2D_02_AA", "index": "27", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GATS6p", "index": "28", "type": "numeric", "distinct": "235", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS6v", "index": "29", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS6p", "index": "30", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AMW", "index": "31", "type": "numeric", "distinct": "244", "missing": "0", "min": "7", "max": "18", "mean": "9", "stdev": "1" }, { "name": "SpMin2_Bh.p.", "index": "32", "type": "numeric", "distinct": "97", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "33", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SpMin1_Bh.m.", "index": "34", "type": "numeric", "distinct": "107", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "35", "type": "numeric", "distinct": "101", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.v.", "index": "36", "type": "numeric", "distinct": "98", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_AN", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "NaasN", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SaasN", "index": "39", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "C.031", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "41", "type": "numeric", "distinct": "184", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "AAC", "index": "42", "type": "numeric", "distinct": "195", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "43", "type": "numeric", "distinct": "195", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_AN", "index": "44", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "45", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "46", "type": "numeric", "distinct": "235", "missing": "0", "min": "2", "max": "60", "mean": "35", "stdev": "11" }, { "name": "GATS4s", "index": "47", "type": "numeric", "distinct": "269", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "48", "type": "numeric", "distinct": "144", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "D.Dtr05", "index": "49", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "322", "mean": "53", "stdev": "68" }, { "name": "P_VSA_s_4", "index": "50", "type": "numeric", "distinct": "160", "missing": "0", "min": "30", "max": "152", "mean": "86", "stdev": "27" }, { "name": "ATSC1m", "index": "51", "type": "numeric", "distinct": "271", "missing": "0", "min": "1", "max": "16", "mean": "8", "stdev": "3" }, { "name": "GATS5e", "index": "52", "type": "numeric", "distinct": "244", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8s", "index": "53", "type": "numeric", "distinct": "281", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "MATS4e", "index": "54", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nHet", "index": "55", "type": "numeric", "distinct": "13", "missing": "0", "min": "3", "max": "15", "mean": "10", "stdev": "2" }, { "name": "ATSC8m", "index": "56", "type": "numeric", "distinct": "325", "missing": "0", "min": "7", "max": "39", "mean": "24", "stdev": "6" }, { "name": "H.051", "index": "57", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SpMin2_Bh.e.", "index": "58", "type": "numeric", "distinct": "137", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ZM1Mad", "index": "59", "type": "numeric", "distinct": "302", "missing": "0", "min": "126", "max": "377", "mean": "212", "stdev": "29" }, { "name": "N.", "index": "60", "type": "numeric", "distinct": "88", "missing": "0", "min": "2", "max": "21", "mean": "8", "stdev": "3" }, { "name": "ATSC2m", "index": "61", "type": "numeric", "distinct": "304", "missing": "0", "min": "4", "max": "30", "mean": "18", "stdev": "5" }, { "name": "MATS3s", "index": "62", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8i", "index": "63", "type": "numeric", "distinct": "275", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS1m", "index": "64", "type": "numeric", "distinct": "182", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "65", "type": "numeric", "distinct": "219", "missing": "0", "min": "3", "max": "41", "mean": "25", "stdev": "7" } ], "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 }