{ "data_id": "34594", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4093", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4093", "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: CHEMBL4093 (TID: 20113), and it has 728 rows and 66 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 15:47:07", "update_comment": null, "last_update": "2016-07-15 15:47:07", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3533708\/data_53160.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4093", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4093 (TID: 20113), and it has 728 rows and 66 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": 728, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.4317633178909266, "Dimensionality": 0.09340659340659341, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.586745879120879, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.4282984176568188, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 373.56354901186654, "Quartile2SkewnessOfNumericAtts": 0.28253774392849706, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.136540336303196, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8976951722580728, "MinMeansOfNumericAtts": -0.03296840659340659, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 20.29394042123424, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.088842047595066, "MaxMeansOfNumericAtts": 52101.78846153846, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 32.32432142857142, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.202782995889495, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.010415700248915432, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8222435249924976, "MaxSkewnessOfNumericAtts": 4.187069268057332, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.24044132097862558, "Quartile3StdDevOfNumericAtts": 15.776987700119827, "MaxStdDevOfNumericAtts": 23933.862226625955, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.661125, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.540690085798558, "Quartile1SkewnessOfNumericAtts": -0.5768218277706917, "MeanMeansOfNumericAtts": 832.2086749835984, "Quartile1StdDevOfNumericAtts": 0.2502598252428831, "AutoCorrelation": 0.07301650618982114, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "391", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "728", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_i_4", "index": "1", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "199", "mean": "54", "stdev": "36" }, { "name": "SpMAD_EA.dm.", "index": "2", "type": "numeric", "distinct": "318", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X2A", "index": "3", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "4", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS4i", "index": "5", "type": "numeric", "distinct": "343", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC8s", "index": "6", "type": "numeric", "distinct": "712", "missing": "0", "min": "1", "max": "601", "mean": "136", "stdev": "85" }, { "name": "nF", "index": "7", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "NsF", "index": "8", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "P_VSA_e_6", "index": "9", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "194", "mean": "36", "stdev": "33" }, { "name": "SpMax1_Bh.s.", "index": "10", "type": "numeric", "distinct": "75", "missing": "0", "min": "5", "max": "9", "mean": "8", "stdev": "1" }, { "name": "SsF", "index": "11", "type": "numeric", "distinct": "450", "missing": "0", "min": "0", "max": "172", "mean": "32", "stdev": "29" }, { "name": "ATSC2s", "index": "12", "type": "numeric", "distinct": "701", "missing": "0", "min": "8", "max": "636", "mean": "138", "stdev": "101" }, { "name": "ATSC8e", "index": "13", "type": "numeric", "distinct": "581", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ZM2Per", "index": "14", "type": "numeric", "distinct": "694", "missing": "0", "min": "180", "max": "1290", "mean": "837", "stdev": "158" }, { "name": "C.022", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nCsp", "index": "16", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nR.C.", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "NtsC", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "StsC", "index": "19", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "1" }, { "name": "nHet", "index": "20", "type": "numeric", "distinct": "17", "missing": "0", "min": "1", "max": "18", "mean": "8", "stdev": "3" }, { "name": "ATSC3s", "index": "21", "type": "numeric", "distinct": "711", "missing": "0", "min": "10", "max": "844", "mean": "110", "stdev": "94" }, { "name": "ZM2Kup", "index": "22", "type": "numeric", "distinct": "626", "missing": "0", "min": "124", "max": "860", "mean": "546", "stdev": "104" }, { "name": "P_VSA_MR_5", "index": "23", "type": "numeric", "distinct": "364", "missing": "0", "min": "0", "max": "109", "mean": "32", "stdev": "17" }, { "name": "ATSC6s", "index": "24", "type": "numeric", "distinct": "717", "missing": "0", "min": "29", "max": "960", "mean": "137", "stdev": "92" }, { "name": "MATS1i", "index": "25", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS6v", "index": "26", "type": "numeric", "distinct": "315", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_5", "index": "27", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "68", "mean": "8", "stdev": "12" }, { "name": "Eig01_EA.dm.", "index": "28", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "29", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "CATS2D_08_DA", "index": "30", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "IC1", "index": "31", "type": "numeric", "distinct": "452", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS2s", "index": "32", "type": "numeric", "distinct": "491", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "AAC", "index": "33", "type": "numeric", "distinct": "368", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "34", "type": "numeric", "distinct": "368", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GMTIV", "index": "35", "type": "numeric", "distinct": "694", "missing": "0", "min": "2075", "max": "192667", "mean": "52102", "stdev": "23934" }, { "name": "nTB", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SM08_EA.dm.", "index": "37", "type": "numeric", "distinct": "162", "missing": "0", "min": "0", "max": "14", "mean": "8", "stdev": "3" }, { "name": "SM10_EA.dm.", "index": "38", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "18", "mean": "10", "stdev": "4" }, { "name": "SM12_EA.dm.", "index": "39", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "21", "mean": "12", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "40", "type": "numeric", "distinct": "121", "missing": "0", "min": "0", "max": "25", "mean": "14", "stdev": "6" }, { "name": "SpMax1_Bh.v.", "index": "41", "type": "numeric", "distinct": "183", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI6", "index": "42", "type": "numeric", "distinct": "360", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.p.", "index": "43", "type": "numeric", "distinct": "141", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IAC", "index": "44", "type": "numeric", "distinct": "517", "missing": "0", "min": "37", "max": "133", "mean": "91", "stdev": "16" }, { "name": "TIC0", "index": "45", "type": "numeric", "distinct": "517", "missing": "0", "min": "37", "max": "133", "mean": "91", "stdev": "16" }, { "name": "S3K", "index": "46", "type": "numeric", "distinct": "558", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "Eig04_AEA.dm.", "index": "47", "type": "numeric", "distinct": "393", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_EA.dm.", "index": "48", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "11", "mean": "6", "stdev": "2" }, { "name": "Eig03_EA", "index": "49", "type": "numeric", "distinct": "314", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "50", "type": "numeric", "distinct": "314", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "51", "type": "numeric", "distinct": "183", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC6i", "index": "52", "type": "numeric", "distinct": "604", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Psi_i_s", "index": "53", "type": "numeric", "distinct": "449", "missing": "0", "min": "35", "max": "159", "mean": "88", "stdev": "18" }, { "name": "Eig01_EA.ed.", "index": "54", "type": "numeric", "distinct": "185", "missing": "0", "min": "9", "max": "19", "mean": "14", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "55", "type": "numeric", "distinct": "185", "missing": "0", "min": "9", "max": "19", "mean": "14", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "56", "type": "numeric", "distinct": "185", "missing": "0", "min": "9", "max": "19", "mean": "14", "stdev": "2" }, { "name": "ZM2V", "index": "57", "type": "numeric", "distinct": "295", "missing": "0", "min": "114", "max": "790", "mean": "525", "stdev": "97" }, { "name": "ZM2MulPer", "index": "58", "type": "numeric", "distinct": "684", "missing": "0", "min": "121", "max": "851", "mean": "561", "stdev": "104" }, { "name": "SM04_EA.dm.", "index": "59", "type": "numeric", "distinct": "225", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "2" }, { "name": "Eig01_EA", "index": "60", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "61", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA", "index": "62", "type": "numeric", "distinct": "156", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMax_EA", "index": "63", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MAXDN", "index": "64", "type": "numeric", "distinct": "562", "missing": "0", "min": "1", "max": "9", "mean": "5", "stdev": "2" }, { "name": "ATSC1s", "index": "65", "type": "numeric", "distinct": "641", "missing": "0", "min": "5", "max": "277", "mean": "36", "stdev": "30" }, { "name": "MATS4i", "index": "66", "type": "numeric", "distinct": "339", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }