{ "data_id": "32008", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4633", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4633", "version": 9, "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: CHEMBL4633 (TID: 10553), and it has 378 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 09:04:54", "update_comment": null, "last_update": "2016-07-15 09:04:54", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3467342\/data_53087.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4633", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4633 (TID: 10553), and it has 378 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": 378, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 15.179499999999999, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3702093220275162, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.603753892935044, "MaxSkewnessOfNumericAtts": 2.339385334128759, "MinStdDevOfNumericAtts": 0.1094151336904501, "Quartile1KurtosisOfNumericAtts": 0.6975252757939443, "Quartile3StdDevOfNumericAtts": 3.656654239844503, "MaxStdDevOfNumericAtts": 182.4270266425418, "MinorityClassPercentage": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.9036296296296296, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.451678674188536, "Quartile1SkewnessOfNumericAtts": 0.4348066705078575, "MeanMeansOfNumericAtts": 24.40893919292427, "Quartile1StdDevOfNumericAtts": 0.49779724095745204, "AutoCorrelation": 0.21418832891246736, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 1.2818339467679944, "Dimensionality": 0.17989417989417988, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 5.344777777777778, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.9392828027279139, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 10.806562425509998, "Quartile2SkewnessOfNumericAtts": 1.0111646817934927, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.0088536185343653, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2238251030225258, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 6.122198358821638, "MinMeansOfNumericAtts": 0.31027513227513226, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.021807893121805, "MaxMeansOfNumericAtts": 586.1901058201058, "MinMutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "253", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "378", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig03_AEA.dm.", "index": "1", "type": "numeric", "distinct": "191", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "2", "type": "numeric", "distinct": "52", "missing": "0", "min": "94", "max": "694", "mean": "308", "stdev": "128" }, { "name": "ATSC6v", "index": "3", "type": "numeric", "distinct": "353", "missing": "0", "min": "5", "max": "78", "mean": "23", "stdev": "17" }, { "name": "ATSC7v", "index": "4", "type": "numeric", "distinct": "351", "missing": "0", "min": "4", "max": "80", "mean": "23", "stdev": "18" }, { "name": "PCR", "index": "5", "type": "numeric", "distinct": "204", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1m", "index": "6", "type": "numeric", "distinct": "299", "missing": "0", "min": "2", "max": "27", "mean": "13", "stdev": "5" }, { "name": "ATSC3v", "index": "7", "type": "numeric", "distinct": "341", "missing": "0", "min": "4", "max": "40", "mean": "17", "stdev": "8" }, { "name": "LOC", "index": "8", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS6i", "index": "9", "type": "numeric", "distinct": "307", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATSC5m", "index": "10", "type": "numeric", "distinct": "356", "missing": "0", "min": "13", "max": "149", "mean": "45", "stdev": "32" }, { "name": "SAtot", "index": "11", "type": "numeric", "distinct": "316", "missing": "0", "min": "266", "max": "1124", "mean": "586", "stdev": "182" }, { "name": "ATS6p", "index": "12", "type": "numeric", "distinct": "302", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS7p", "index": "13", "type": "numeric", "distinct": "308", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "MAXDP", "index": "14", "type": "numeric", "distinct": "312", "missing": "0", "min": "1", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATSC8p", "index": "15", "type": "numeric", "distinct": "348", "missing": "0", "min": "0", "max": "56", "mean": "16", "stdev": "12" }, { "name": "ATS1p", "index": "16", "type": "numeric", "distinct": "253", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "17", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS5v", "index": "18", "type": "numeric", "distinct": "297", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATSC6i", "index": "19", "type": "numeric", "distinct": "330", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "ATSC7p", "index": "20", "type": "numeric", "distinct": "348", "missing": "0", "min": "2", "max": "59", "mean": "17", "stdev": "13" }, { "name": "Eig13_AEA.ri.", "index": "21", "type": "numeric", "distinct": "243", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "22", "type": "numeric", "distinct": "248", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eta_alpha", "index": "23", "type": "numeric", "distinct": "205", "missing": "0", "min": "7", "max": "25", "mean": "15", "stdev": "4" }, { "name": "X1Mad", "index": "24", "type": "numeric", "distinct": "324", "missing": "0", "min": "7", "max": "24", "mean": "14", "stdev": "4" }, { "name": "GGI5", "index": "25", "type": "numeric", "distinct": "182", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "GGI8", "index": "26", "type": "numeric", "distinct": "184", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GGI9", "index": "27", "type": "numeric", "distinct": "183", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM04_EA.ri.", "index": "28", "type": "numeric", "distinct": "287", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM05_EA.ri.", "index": "29", "type": "numeric", "distinct": "267", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "X4sol", "index": "30", "type": "numeric", "distinct": "259", "missing": "0", "min": "4", "max": "20", "mean": "10", "stdev": "3" }, { "name": "X5sol", "index": "31", "type": "numeric", "distinct": "262", "missing": "0", "min": "3", "max": "18", "mean": "8", "stdev": "3" }, { "name": "ATSC3m", "index": "32", "type": "numeric", "distinct": "342", "missing": "0", "min": "9", "max": "77", "mean": "34", "stdev": "15" }, { "name": "SpMAD_EA.bo.", "index": "33", "type": "numeric", "distinct": "195", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCrs", "index": "34", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "TIE", "index": "35", "type": "numeric", "distinct": "356", "missing": "0", "min": "21", "max": "268", "mean": "83", "stdev": "55" }, { "name": "ATS5i", "index": "36", "type": "numeric", "distinct": "305", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "37", "type": "numeric", "distinct": "202", "missing": "0", "min": "-5", "max": "5", "mean": "1", "stdev": "2" }, { "name": "Eig15_AEA.dm.", "index": "38", "type": "numeric", "distinct": "225", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "S1K", "index": "39", "type": "numeric", "distinct": "261", "missing": "0", "min": "10", "max": "42", "mean": "23", "stdev": "7" }, { "name": "SM08_AEA.ri.", "index": "40", "type": "numeric", "distinct": "202", "missing": "0", "min": "-5", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SPI", "index": "41", "type": "numeric", "distinct": "266", "missing": "0", "min": "0", "max": "44", "mean": "17", "stdev": "9" }, { "name": "ATSC8e", "index": "42", "type": "numeric", "distinct": "316", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "ATSC8s", "index": "43", "type": "numeric", "distinct": "350", "missing": "0", "min": "3", "max": "832", "mean": "133", "stdev": "151" }, { "name": "ATSC2i", "index": "44", "type": "numeric", "distinct": "283", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "nCs", "index": "45", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "3" }, { "name": "ATS4v", "index": "46", "type": "numeric", "distinct": "298", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC7i", "index": "47", "type": "numeric", "distinct": "331", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "48", "type": "numeric", "distinct": "269", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Psi_i_1", "index": "49", "type": "numeric", "distinct": "328", "missing": "0", "min": "8", "max": "35", "mean": "19", "stdev": "5" }, { "name": "X1sol", "index": "50", "type": "numeric", "distinct": "226", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "X3sol", "index": "51", "type": "numeric", "distinct": "253", "missing": "0", "min": "5", "max": "22", "mean": "12", "stdev": "3" }, { "name": "ATS2p", "index": "52", "type": "numeric", "distinct": "266", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC6p", "index": "53", "type": "numeric", "distinct": "350", "missing": "0", "min": "4", "max": "57", "mean": "17", "stdev": "12" }, { "name": "SpMin6_Bh.s.", "index": "54", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS6v", "index": "55", "type": "numeric", "distinct": "302", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eta_beta_A", "index": "56", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X4v", "index": "57", "type": "numeric", "distinct": "330", "missing": "0", "min": "2", "max": "13", "mean": "5", "stdev": "2" }, { "name": "SM06_EA.ri.", "index": "58", "type": "numeric", "distinct": "298", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SM07_EA.ri.", "index": "59", "type": "numeric", "distinct": "286", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "1" }, { "name": "SM08_EA.ri.", "index": "60", "type": "numeric", "distinct": "299", "missing": "0", "min": "8", "max": "12", "mean": "10", "stdev": "1" }, { "name": "SM09_EA.ri.", "index": "61", "type": "numeric", "distinct": "286", "missing": "0", "min": "8", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SM10_EA.ri.", "index": "62", "type": "numeric", "distinct": "300", "missing": "0", "min": "10", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM11_EA.ri.", "index": "63", "type": "numeric", "distinct": "296", "missing": "0", "min": "10", "max": "16", "mean": "14", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "64", "type": "numeric", "distinct": "302", "missing": "0", "min": "11", "max": "18", "mean": "15", "stdev": "1" }, { "name": "DBI", "index": "65", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "ATS1e", "index": "66", "type": "numeric", "distinct": "241", "missing": "0", "min": "3", "max": "5", "mean": "4", "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 }