{ "data_id": "34443", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2336", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2336", "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: CHEMBL2336 (TID: 12536), and it has 202 rows and 64 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 15:23:00", "update_comment": null, "last_update": "2016-07-15 15:23:00", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3529271\/data_52628.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2336", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2336 (TID: 12536), and it has 202 rows and 64 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": 202, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.8975425444752205, "Dimensionality": 0.32673267326732675, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 7.084049504950495, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.8087071610414797, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 313.09703731969586, "Quartile2SkewnessOfNumericAtts": -0.670522131533476, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.41374412324792126, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5146907030417114, "MinMeansOfNumericAtts": 0.1100049504950495, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 12.276072066118028, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.4019971854676294, "MaxMeansOfNumericAtts": 39118.22772277228, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 23.958908415841584, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.940645754766201, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.020484309618456764, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.20632241594531747, "MaxSkewnessOfNumericAtts": 0.9913618163567106, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.2043699993949628, "Quartile3StdDevOfNumericAtts": 0.9880296173333294, "MaxStdDevOfNumericAtts": 20144.502511367013, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.022121287128713, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.5484438617041367, "Quartile1SkewnessOfNumericAtts": -1.43532460943194, "MeanMeansOfNumericAtts": 625.9574477532369, "Quartile1StdDevOfNumericAtts": 0.22519928891906116, "AutoCorrelation": -0.207452736318408, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "145", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "202", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig11_AEA.ed.", "index": "1", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig11_EA.ed.", "index": "2", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM06_AEA.ri.", "index": "3", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "MPC06", "index": "4", "type": "numeric", "distinct": "69", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig10_AEA.ri.", "index": "5", "type": "numeric", "distinct": "118", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_EA.ri.", "index": "6", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MPC10", "index": "7", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMaxA_AEA.dm.", "index": "8", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC6i", "index": "9", "type": "numeric", "distinct": "188", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig11_EA", "index": "10", "type": "numeric", "distinct": "90", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM05_AEA.dm.", "index": "11", "type": "numeric", "distinct": "90", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "TPC", "index": "12", "type": "numeric", "distinct": "112", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Eig10_EA.bo.", "index": "13", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig10_EA", "index": "14", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM04_AEA.dm.", "index": "15", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "16", "type": "numeric", "distinct": "105", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Wap", "index": "17", "type": "numeric", "distinct": "118", "missing": "0", "min": "4482", "max": "93850", "mean": "39118", "stdev": "20145" }, { "name": "Eig13_AEA.bo.", "index": "18", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.ed.", "index": "19", "type": "numeric", "distinct": "94", "missing": "0", "min": "17", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM02_EA.ri.", "index": "20", "type": "numeric", "distinct": "149", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SRW08", "index": "21", "type": "numeric", "distinct": "109", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "MWC04", "index": "22", "type": "numeric", "distinct": "101", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SRW06", "index": "23", "type": "numeric", "distinct": "98", "missing": "0", "min": "7", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SpAD_EA.ri.", "index": "24", "type": "numeric", "distinct": "178", "missing": "0", "min": "28", "max": "68", "mean": "50", "stdev": "8" }, { "name": "ATSC5i", "index": "25", "type": "numeric", "distinct": "184", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "MWC07", "index": "26", "type": "numeric", "distinct": "110", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "MPC04", "index": "27", "type": "numeric", "distinct": "50", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "X5", "index": "28", "type": "numeric", "distinct": "124", "missing": "0", "min": "4", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SpAD_AEA.dm.", "index": "29", "type": "numeric", "distinct": "164", "missing": "0", "min": "30", "max": "72", "mean": "55", "stdev": "8" }, { "name": "RDSQ", "index": "30", "type": "numeric", "distinct": "124", "missing": "0", "min": "131", "max": "437", "mean": "301", "stdev": "60" }, { "name": "SpAD_AEA.ri.", "index": "31", "type": "numeric", "distinct": "178", "missing": "0", "min": "30", "max": "70", "mean": "53", "stdev": "8" }, { "name": "SpAD_EA", "index": "32", "type": "numeric", "distinct": "124", "missing": "0", "min": "30", "max": "70", "mean": "53", "stdev": "8" }, { "name": "SpAD_AEA.bo.", "index": "33", "type": "numeric", "distinct": "138", "missing": "0", "min": "30", "max": "71", "mean": "54", "stdev": "8" }, { "name": "ATS5m", "index": "34", "type": "numeric", "distinct": "179", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "35", "type": "numeric", "distinct": "124", "missing": "0", "min": "82", "max": "210", "mean": "158", "stdev": "24" }, { "name": "MWC05", "index": "36", "type": "numeric", "distinct": "103", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Eig15_AEA.ri.", "index": "37", "type": "numeric", "distinct": "129", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig15_EA.ri.", "index": "38", "type": "numeric", "distinct": "137", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Chi0_EA.ed.", "index": "39", "type": "numeric", "distinct": "124", "missing": "0", "min": "7", "max": "17", "mean": "12", "stdev": "2" }, { "name": "Chi1_EA.ed.", "index": "40", "type": "numeric", "distinct": "122", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "MPC07", "index": "41", "type": "numeric", "distinct": "81", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM02_AEA.ed.", "index": "42", "type": "numeric", "distinct": "81", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eig11_AEA.bo.", "index": "43", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "44", "type": "numeric", "distinct": "123", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MWC03", "index": "45", "type": "numeric", "distinct": "81", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ZM2", "index": "46", "type": "numeric", "distinct": "81", "missing": "0", "min": "110", "max": "268", "mean": "204", "stdev": "30" }, { "name": "Eig01_AEA.ed.", "index": "47", "type": "numeric", "distinct": "67", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "48", "type": "numeric", "distinct": "80", "missing": "0", "min": "10", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SM09_EA.ed.", "index": "49", "type": "numeric", "distinct": "118", "missing": "0", "min": "21", "max": "24", "mean": "23", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "50", "type": "numeric", "distinct": "80", "missing": "0", "min": "10", "max": "14", "mean": "12", "stdev": "1" }, { "name": "SM10_EA.ed.", "index": "51", "type": "numeric", "distinct": "115", "missing": "0", "min": "24", "max": "27", "mean": "25", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "52", "type": "numeric", "distinct": "114", "missing": "0", "min": "26", "max": "29", "mean": "28", "stdev": "1" }, { "name": "SM12_EA.ed.", "index": "53", "type": "numeric", "distinct": "113", "missing": "0", "min": "28", "max": "32", "mean": "30", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "54", "type": "numeric", "distinct": "113", "missing": "0", "min": "30", "max": "35", "mean": "33", "stdev": "1" }, { "name": "SM14_EA.ed.", "index": "55", "type": "numeric", "distinct": "110", "missing": "0", "min": "33", "max": "37", "mean": "35", "stdev": "1" }, { "name": "SM15_EA.ed.", "index": "56", "type": "numeric", "distinct": "105", "missing": "0", "min": "35", "max": "40", "mean": "37", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "57", "type": "numeric", "distinct": "67", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "58", "type": "numeric", "distinct": "80", "missing": "0", "min": "10", "max": "14", "mean": "12", "stdev": "1" }, { "name": "MWC02", "index": "59", "type": "numeric", "distinct": "49", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ZM1", "index": "60", "type": "numeric", "distinct": "49", "missing": "0", "min": "94", "max": "228", "mean": "171", "stdev": "26" }, { "name": "SM04_EA.ed.", "index": "61", "type": "numeric", "distinct": "116", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "0" }, { "name": "ATS6m", "index": "62", "type": "numeric", "distinct": "178", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MPC03", "index": "63", "type": "numeric", "distinct": "42", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA", "index": "64", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "4", "mean": "3", "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 }