{ "data_id": "34339", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1929", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1929", "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: CHEMBL1929 (TID: 149), and it has 152 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 15:06:18", "update_comment": null, "last_update": "2016-07-15 15:06:18", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3526474\/data_52748.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1929", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1929 (TID: 149), and it has 152 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": 152, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "MaxMeansOfNumericAtts": 18953.855263157904, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.0926238286085885, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 4.3067549342105265, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0571435613448261, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 4.341125001910057, "MinStdDevOfNumericAtts": 0.05545925648941761, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.174858013409021, "MaxStdDevOfNumericAtts": 35452.23741552841, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.256307990116727, "Quartile3StdDevOfNumericAtts": 2.6488036326776814, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": -0.6241069078947368, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.9234412185672083, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 504.3091723484851, "Quartile1SkewnessOfNumericAtts": 0.4060173820878267, "AutoCorrelation": 0.21136423841059582, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.6027521877262604, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.4407894736842105, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.12189441564731784, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.8693153534302576, "Quartile2MeansOfNumericAtts": 1.2039440789473685, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 852.086525962507, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6568583366282874, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.866951043354343, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.0304291187170012, "MaxKurtosisOfNumericAtts": 20.387077784597487, "MinMeansOfNumericAtts": -2.252578947368421, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "112", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "152", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NssCH2", "index": "1", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "2" }, { "name": "SpMin1_Bh.i.", "index": "2", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig15_AEA.dm.", "index": "3", "type": "numeric", "distinct": "115", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig14_EA.ed.", "index": "4", "type": "numeric", "distinct": "99", "missing": "0", "min": "-7", "max": "6", "mean": "-2", "stdev": "3" }, { "name": "SM09_AEA.ri.", "index": "5", "type": "numeric", "distinct": "99", "missing": "0", "min": "-7", "max": "6", "mean": "-2", "stdev": "3" }, { "name": "Eig14_EA", "index": "6", "type": "numeric", "distinct": "88", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "7", "type": "numeric", "distinct": "96", "missing": "0", "min": "-3", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "8", "type": "numeric", "distinct": "105", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SM08_AEA.dm.", "index": "9", "type": "numeric", "distinct": "88", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig15_EA.ed.", "index": "10", "type": "numeric", "distinct": "102", "missing": "0", "min": "-7", "max": "5", "mean": "-2", "stdev": "3" }, { "name": "SM10_AEA.ri.", "index": "11", "type": "numeric", "distinct": "102", "missing": "0", "min": "-7", "max": "5", "mean": "-2", "stdev": "3" }, { "name": "Eig15_EA", "index": "12", "type": "numeric", "distinct": "87", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig15_EA.bo.", "index": "13", "type": "numeric", "distinct": "97", "missing": "0", "min": "-3", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig15_EA.ri.", "index": "14", "type": "numeric", "distinct": "109", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SM09_AEA.dm.", "index": "15", "type": "numeric", "distinct": "87", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SssCH2", "index": "16", "type": "numeric", "distinct": "89", "missing": "0", "min": "-2", "max": "17", "mean": "1", "stdev": "3" }, { "name": "SpMin1_Bh.e.", "index": "17", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig14_AEA.dm.", "index": "18", "type": "numeric", "distinct": "115", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Hy", "index": "19", "type": "numeric", "distinct": "111", "missing": "0", "min": "-1", "max": "8", "mean": "1", "stdev": "2" }, { "name": "Inflammat.50", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig13_EA", "index": "21", "type": "numeric", "distinct": "91", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig13_EA.bo.", "index": "22", "type": "numeric", "distinct": "106", "missing": "0", "min": "-3", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "23", "type": "numeric", "distinct": "99", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "3" }, { "name": "Eig13_EA.ri.", "index": "24", "type": "numeric", "distinct": "116", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SM07_AEA.dm.", "index": "25", "type": "numeric", "distinct": "91", "missing": "0", "min": "-2", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "SM08_AEA.ri.", "index": "26", "type": "numeric", "distinct": "99", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "3" }, { "name": "SpMax1_Bh.p.", "index": "27", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig13_AEA.dm.", "index": "28", "type": "numeric", "distinct": "126", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMin7_Bh.i.", "index": "29", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "30", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS5e", "index": "31", "type": "numeric", "distinct": "145", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "nR10", "index": "32", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "LOC", "index": "33", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax8_Bh.i.", "index": "34", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "35", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "46", "mean": "17", "stdev": "11" }, { "name": "ATS3e", "index": "36", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig12_EA.bo.", "index": "37", "type": "numeric", "distinct": "119", "missing": "0", "min": "-3", "max": "3", "mean": "-1", "stdev": "1" }, { "name": "Eig12_EA.ed.", "index": "38", "type": "numeric", "distinct": "112", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "3" }, { "name": "SM07_AEA.ri.", "index": "39", "type": "numeric", "distinct": "112", "missing": "0", "min": "-7", "max": "6", "mean": "-1", "stdev": "3" }, { "name": "Chi0_EA.dm.", "index": "40", "type": "numeric", "distinct": "120", "missing": "0", "min": "2", "max": "36", "mean": "15", "stdev": "8" }, { "name": "TPC", "index": "41", "type": "numeric", "distinct": "115", "missing": "0", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "Wap", "index": "42", "type": "numeric", "distinct": "122", "missing": "0", "min": "397", "max": "224113", "mean": "18954", "stdev": "35452" }, { "name": "CATS2D_08_LL", "index": "43", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "20", "mean": "2", "stdev": "3" }, { "name": "ATS4e", "index": "44", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig09_AEA.ed.", "index": "45", "type": "numeric", "distinct": "118", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig12_EA", "index": "46", "type": "numeric", "distinct": "105", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "47", "type": "numeric", "distinct": "125", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM06_AEA.dm.", "index": "48", "type": "numeric", "distinct": "105", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC1p", "index": "49", "type": "numeric", "distinct": "131", "missing": "0", "min": "1", "max": "9", "mean": "3", "stdev": "2" }, { "name": "ATSC5v", "index": "50", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "33", "mean": "8", "stdev": "6" }, { "name": "CIC0", "index": "51", "type": "numeric", "distinct": "127", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS1e", "index": "52", "type": "numeric", "distinct": "126", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "53", "type": "numeric", "distinct": "123", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2e", "index": "54", "type": "numeric", "distinct": "131", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nBT", "index": "55", "type": "numeric", "distinct": "52", "missing": "0", "min": "15", "max": "90", "mean": "40", "stdev": "17" }, { "name": "Se", "index": "56", "type": "numeric", "distinct": "130", "missing": "0", "min": "15", "max": "88", "mean": "39", "stdev": "17" }, { "name": "TIC5", "index": "57", "type": "numeric", "distinct": "125", "missing": "0", "min": "53", "max": "493", "mean": "186", "stdev": "104" }, { "name": "ATS5i", "index": "58", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ECC", "index": "59", "type": "numeric", "distinct": "107", "missing": "0", "min": "37", "max": "944", "mean": "219", "stdev": "166" }, { "name": "N.068", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nRNR2", "index": "61", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Chi0_EA.bo.", "index": "62", "type": "numeric", "distinct": "126", "missing": "0", "min": "6", "max": "31", "mean": "13", "stdev": "6" }, { "name": "IDMT", "index": "63", "type": "numeric", "distinct": "125", "missing": "0", "min": "562", "max": "135042", "mean": "13736", "stdev": "20384" }, { "name": "SpMax7_Bh.e.", "index": "64", "type": "numeric", "distinct": "116", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC6p", "index": "65", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "23", "mean": "6", "stdev": "5" } ], "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 }