{ "data_id": "35379", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2543", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2543", "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: CHEMBL2543 (TID: 11629), and it has 688 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 17:53:18", "update_comment": null, "last_update": "2016-07-15 17:53:18", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3556424\/data_53467.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2543", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2543 (TID: 11629), and it has 688 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": 688, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.4637453245166665, "Dimensionality": 0.10319767441860465, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.962089389534883, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.1002233059986573, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 21.50599773381561, "Quartile2SkewnessOfNumericAtts": 0.3231001460865929, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.5254968577296482, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.3043582557222133, "MinMeansOfNumericAtts": 0.14389534883720956, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 14.776777696736715, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.4435533531678695, "MaxMeansOfNumericAtts": 1294.1206395348834, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 18.389704941860465, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.204691877896347, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.032801222085035574, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5905074525121877, "MaxSkewnessOfNumericAtts": 3.5295732918153426, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.15594492339308774, "Quartile3StdDevOfNumericAtts": 5.258407113402606, "MaxStdDevOfNumericAtts": 830.7882097571544, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.134204941860465, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.421384570686072, "Quartile1SkewnessOfNumericAtts": -0.49587485401642306, "MeanMeansOfNumericAtts": 52.64007794850499, "Quartile1StdDevOfNumericAtts": 0.3791984548582693, "AutoCorrelation": 0.5265967976710323, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "77", "missing": "0", "target": "1", "min": "5", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "688", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Chi0_EA.dm.", "index": "1", "type": "numeric", "distinct": "591", "missing": "0", "min": "0", "max": "46", "mean": "18", "stdev": "8" }, { "name": "ATSC3m", "index": "2", "type": "numeric", "distinct": "665", "missing": "0", "min": "5", "max": "59", "mean": "22", "stdev": "8" }, { "name": "SsssN", "index": "3", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Eta_epsi", "index": "4", "type": "numeric", "distinct": "534", "missing": "0", "min": "11", "max": "51", "mean": "29", "stdev": "7" }, { "name": "ATSC8m", "index": "5", "type": "numeric", "distinct": "674", "missing": "0", "min": "0", "max": "67", "mean": "21", "stdev": "10" }, { "name": "PCR", "index": "6", "type": "numeric", "distinct": "282", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS5i", "index": "7", "type": "numeric", "distinct": "528", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "8", "type": "numeric", "distinct": "472", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS3m", "index": "9", "type": "numeric", "distinct": "478", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_i_3", "index": "10", "type": "numeric", "distinct": "387", "missing": "0", "min": "24", "max": "550", "mean": "239", "stdev": "81" }, { "name": "CATS2D_02_AL", "index": "11", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "5", "stdev": "3" }, { "name": "Eig11_AEA.dm.", "index": "12", "type": "numeric", "distinct": "436", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS8m", "index": "13", "type": "numeric", "distinct": "550", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "IAC", "index": "14", "type": "numeric", "distinct": "589", "missing": "0", "min": "26", "max": "137", "mean": "75", "stdev": "19" }, { "name": "TIC0", "index": "15", "type": "numeric", "distinct": "589", "missing": "0", "min": "26", "max": "137", "mean": "75", "stdev": "19" }, { "name": "CENT", "index": "16", "type": "numeric", "distinct": "542", "missing": "0", "min": "49", "max": "5486", "mean": "1294", "stdev": "831" }, { "name": "S1K", "index": "17", "type": "numeric", "distinct": "544", "missing": "0", "min": "7", "max": "32", "mean": "18", "stdev": "4" }, { "name": "Eig12_AEA.dm.", "index": "18", "type": "numeric", "distinct": "452", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS5e", "index": "19", "type": "numeric", "distinct": "520", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "IDM", "index": "20", "type": "numeric", "distinct": "525", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "ATSC5m", "index": "21", "type": "numeric", "distinct": "676", "missing": "0", "min": "4", "max": "63", "mean": "25", "stdev": "10" }, { "name": "H.047", "index": "22", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "29", "mean": "11", "stdev": "5" }, { "name": "Chi1_EA.bo.", "index": "23", "type": "numeric", "distinct": "607", "missing": "0", "min": "4", "max": "21", "mean": "11", "stdev": "3" }, { "name": "ATS1e", "index": "24", "type": "numeric", "distinct": "458", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SAtot", "index": "25", "type": "numeric", "distinct": "649", "missing": "0", "min": "182", "max": "780", "mean": "451", "stdev": "102" }, { "name": "ATSC2m", "index": "26", "type": "numeric", "distinct": "639", "missing": "0", "min": "0", "max": "39", "mean": "16", "stdev": "6" }, { "name": "SpMax6_Bh.i.", "index": "27", "type": "numeric", "distinct": "395", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "28", "type": "numeric", "distinct": "624", "missing": "0", "min": "52", "max": "274", "mean": "132", "stdev": "32" }, { "name": "Eig07_AEA.dm.", "index": "29", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "TIC5", "index": "30", "type": "numeric", "distinct": "518", "missing": "0", "min": "41", "max": "485", "mean": "234", "stdev": "72" }, { "name": "PHI", "index": "31", "type": "numeric", "distinct": "589", "missing": "0", "min": "1", "max": "11", "mean": "5", "stdev": "2" }, { "name": "Se", "index": "32", "type": "numeric", "distinct": "602", "missing": "0", "min": "15", "max": "83", "mean": "46", "stdev": "11" }, { "name": "X0v", "index": "33", "type": "numeric", "distinct": "623", "missing": "0", "min": "7", "max": "27", "mean": "15", "stdev": "3" }, { "name": "Eta_betaS", "index": "34", "type": "numeric", "distinct": "86", "missing": "0", "min": "7", "max": "31", "mean": "18", "stdev": "4" }, { "name": "Psi_i_0", "index": "35", "type": "numeric", "distinct": "635", "missing": "0", "min": "7", "max": "33", "mean": "19", "stdev": "4" }, { "name": "ATSC4i", "index": "36", "type": "numeric", "distinct": "546", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATSC5v", "index": "37", "type": "numeric", "distinct": "662", "missing": "0", "min": "1", "max": "29", "mean": "11", "stdev": "5" }, { "name": "Eig07_EA", "index": "38", "type": "numeric", "distinct": "435", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "39", "type": "numeric", "distinct": "435", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SRW06", "index": "40", "type": "numeric", "distinct": "347", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ATS7p", "index": "41", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS8e", "index": "42", "type": "numeric", "distinct": "570", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SRW07", "index": "43", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SRW09", "index": "44", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "X0", "index": "45", "type": "numeric", "distinct": "308", "missing": "0", "min": "8", "max": "32", "mean": "19", "stdev": "4" }, { "name": "ATS3e", "index": "46", "type": "numeric", "distinct": "488", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS3p", "index": "47", "type": "numeric", "distinct": "473", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SRW04", "index": "48", "type": "numeric", "distinct": "121", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig13_AEA.dm.", "index": "49", "type": "numeric", "distinct": "477", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "HDcpx", "index": "50", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMaxA_AEA.ri.", "index": "51", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS2e", "index": "52", "type": "numeric", "distinct": "482", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "53", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "ON0V", "index": "54", "type": "numeric", "distinct": "496", "missing": "0", "min": "3", "max": "16", "mean": "9", "stdev": "2" }, { "name": "CATS2D_08_DP", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "56", "type": "numeric", "distinct": "456", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS3v", "index": "57", "type": "numeric", "distinct": "476", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "BID", "index": "58", "type": "numeric", "distinct": "120", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIC4", "index": "59", "type": "numeric", "distinct": "518", "missing": "0", "min": "41", "max": "479", "mean": "233", "stdev": "71" }, { "name": "ATS2i", "index": "60", "type": "numeric", "distinct": "483", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Chi0_EA.bo.", "index": "61", "type": "numeric", "distinct": "584", "missing": "0", "min": "6", "max": "29", "mean": "16", "stdev": "4" }, { "name": "Psi_i_1", "index": "62", "type": "numeric", "distinct": "642", "missing": "0", "min": "6", "max": "29", "mean": "16", "stdev": "4" }, { "name": "SpMax6_Bh.p.", "index": "63", "type": "numeric", "distinct": "394", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "RDSQ", "index": "64", "type": "numeric", "distinct": "625", "missing": "0", "min": "63", "max": "598", "mean": "240", "stdev": "76" }, { "name": "Eig10_EA.ed.", "index": "65", "type": "numeric", "distinct": "502", "missing": "0", "min": "-5", "max": "6", "mean": "2", "stdev": "2" }, { "name": "SM05_AEA.ri.", "index": "66", "type": "numeric", "distinct": "502", "missing": "0", "min": "-5", "max": "6", "mean": "2", "stdev": "2" }, { "name": "ATSC4p", "index": "67", "type": "numeric", "distinct": "661", "missing": "0", "min": "1", "max": "21", "mean": "9", "stdev": "3" }, { "name": "TIC3", "index": "68", "type": "numeric", "distinct": "547", "missing": "0", "min": "41", "max": "477", "mean": "229", "stdev": "70" }, { "name": "Eig08_EA.ed.", "index": "69", "type": "numeric", "distinct": "531", "missing": "0", "min": "-3", "max": "8", "mean": "4", "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 }