{ "data_id": "34915", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL291", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL291", "version": 11, "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: CHEMBL291 (TID: 11396), and it has 107 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 16:37:58", "update_comment": null, "last_update": "2016-07-15 16:37:58", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3542593\/data_52663.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL291", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL291 (TID: 11396), and it has 107 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": 107, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -0.030291722938941668, "Dimensionality": 0.616822429906542, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.62288785046729, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.6970295580298637, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.824396051736392, "Quartile2SkewnessOfNumericAtts": -0.5500948855158324, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.683855626501733, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2527557693555709, "MinMeansOfNumericAtts": 0.057682242990654234, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 19.5240815131602, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.661049589989665, "MaxMeansOfNumericAtts": 234.2096168224299, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 10.064495327102804, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -3.0563008731661867, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.21621085137385548, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": -0.050975017337467426, "MaxSkewnessOfNumericAtts": 0.7531555498906324, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5909382921192567, "Quartile3StdDevOfNumericAtts": 3.4678052755819953, "MaxStdDevOfNumericAtts": 75.95525042227351, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.8485327102803737, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.122489238401714, "Quartile1SkewnessOfNumericAtts": -1.3467483356060113, "MeanMeansOfNumericAtts": 13.277356434219985, "Quartile1StdDevOfNumericAtts": 0.4197331212153941, "AutoCorrelation": -0.006981132075472052, "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": "85", "missing": "0", "target": "1", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "107", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax4_Bh.m.", "index": "1", "type": "numeric", "distinct": "93", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS6p", "index": "2", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS6v", "index": "3", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS7p", "index": "4", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.bo.", "index": "5", "type": "numeric", "distinct": "88", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpAD_EA.bo.", "index": "6", "type": "numeric", "distinct": "98", "missing": "0", "min": "26", "max": "109", "mean": "69", "stdev": "18" }, { "name": "ATSC7p", "index": "7", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "26", "mean": "12", "stdev": "6" }, { "name": "ATSC8p", "index": "8", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "27", "mean": "12", "stdev": "6" }, { "name": "X2sol", "index": "9", "type": "numeric", "distinct": "91", "missing": "0", "min": "5", "max": "26", "mean": "15", "stdev": "5" }, { "name": "Eig12_AEA.ri.", "index": "10", "type": "numeric", "distinct": "78", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "11", "type": "numeric", "distinct": "78", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "piPC01", "index": "12", "type": "numeric", "distinct": "58", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SCBO", "index": "13", "type": "numeric", "distinct": "58", "missing": "0", "min": "18", "max": "72", "mean": "46", "stdev": "12" }, { "name": "SpMax5_Bh.m.", "index": "14", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "15", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "16", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "17", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_AEA.bo.", "index": "18", "type": "numeric", "distinct": "70", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM02_AEA.bo.", "index": "19", "type": "numeric", "distinct": "86", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "20", "type": "numeric", "distinct": "94", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "21", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC6p", "index": "22", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "25", "mean": "12", "stdev": "5" }, { "name": "Eta_F", "index": "23", "type": "numeric", "distinct": "103", "missing": "0", "min": "8", "max": "67", "mean": "35", "stdev": "13" }, { "name": "ATS5p", "index": "24", "type": "numeric", "distinct": "100", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "25", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA.bo.", "index": "26", "type": "numeric", "distinct": "84", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "AMR", "index": "27", "type": "numeric", "distinct": "101", "missing": "0", "min": "45", "max": "190", "mean": "119", "stdev": "30" }, { "name": "Eta_beta", "index": "28", "type": "numeric", "distinct": "71", "missing": "0", "min": "17", "max": "65", "mean": "42", "stdev": "11" }, { "name": "Eig11_EA.bo.", "index": "29", "type": "numeric", "distinct": "74", "missing": "0", "min": "-3", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eta_alpha", "index": "30", "type": "numeric", "distinct": "92", "missing": "0", "min": "6", "max": "23", "mean": "15", "stdev": "4" }, { "name": "SpMax4_Bh.p.", "index": "31", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1m", "index": "32", "type": "numeric", "distinct": "95", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig13_AEA.bo.", "index": "33", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig13_EA.bo.", "index": "34", "type": "numeric", "distinct": "80", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_AEA.bo.", "index": "35", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "36", "type": "numeric", "distinct": "77", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC02", "index": "37", "type": "numeric", "distinct": "75", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "38", "type": "numeric", "distinct": "75", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig10_EA.bo.", "index": "39", "type": "numeric", "distinct": "81", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "40", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig10_AEA.bo.", "index": "41", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "1" }, { "name": "SpMin4_Bh.i.", "index": "42", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS5v", "index": "43", "type": "numeric", "distinct": "100", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1v", "index": "44", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS7v", "index": "45", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig09_AEA.bo.", "index": "46", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig12_EA", "index": "47", "type": "numeric", "distinct": "69", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM02_EA.ri.", "index": "48", "type": "numeric", "distinct": "98", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM06_AEA.dm.", "index": "49", "type": "numeric", "distinct": "69", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.ri.", "index": "50", "type": "numeric", "distinct": "103", "missing": "0", "min": "16", "max": "78", "mean": "49", "stdev": "12" }, { "name": "Eig10_AEA.ri.", "index": "51", "type": "numeric", "distinct": "79", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "52", "type": "numeric", "distinct": "83", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "X1v", "index": "53", "type": "numeric", "distinct": "102", "missing": "0", "min": "4", "max": "19", "mean": "11", "stdev": "3" }, { "name": "X2v", "index": "54", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "18", "mean": "9", "stdev": "4" }, { "name": "ZM2Mad", "index": "55", "type": "numeric", "distinct": "102", "missing": "0", "min": "80", "max": "414", "mean": "234", "stdev": "76" }, { "name": "Eig06_EA.bo.", "index": "56", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig15_AEA.bo.", "index": "57", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig15_AEA.ed.", "index": "58", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig15_EA", "index": "59", "type": "numeric", "distinct": "76", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA.bo.", "index": "60", "type": "numeric", "distinct": "75", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eta_betaP", "index": "61", "type": "numeric", "distinct": "42", "missing": "0", "min": "7", "max": "37", "mean": "23", "stdev": "8" }, { "name": "SM09_AEA.dm.", "index": "62", "type": "numeric", "distinct": "76", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "1" }, { "name": "ATSC3p", "index": "63", "type": "numeric", "distinct": "102", "missing": "0", "min": "2", "max": "21", "mean": "11", "stdev": "4" }, { "name": "ATSC5p", "index": "64", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "26", "mean": "12", "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 }