{ "data_id": "25940", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2219", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2219", "version": 8, "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: CHEMBL2219 (TID: 11521), and it has 674 rows and 69 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": "2016-07-14 18:05:47", "update_comment": null, "last_update": "2016-07-14 18:05:47", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3288925\/data_53604.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2219", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2219 (TID: 11521), and it has 674 rows and 69 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": 674, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1805248516320475, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.6373034196618104, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 43.636710915642226, "Quartile1SkewnessOfNumericAtts": -1.0539244316359602, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5367484723040857, "AutoCorrelation": 0.234475482912331, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.2112154561887372, "Dimensionality": 0.10534124629080119, "MeanSkewnessOfNumericAtts": -0.2322364785489601, "Quartile2MeansOfNumericAtts": 3.2505029673590506, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 13.510703155281263, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.2514660042237163, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.1665977896913122, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8105491972656684, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 5.94067700139539, "MinMeansOfNumericAtts": -0.09752225519287838, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 612.0554451038576, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.0481843139906992, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 7.241670623145401, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.749082556505923, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.5504634060626508, "MinStdDevOfNumericAtts": 0.013014342011881053, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.41351056064989966, "MaxStdDevOfNumericAtts": 192.76888491007745, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.20627332450010671, "Quartile3StdDevOfNumericAtts": 1.9632159757817846 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "300", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "674", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nCsp2", "index": "1", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "41", "mean": "14", "stdev": "6" }, { "name": "Ui", "index": "2", "type": "numeric", "distinct": "36", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "3", "type": "numeric", "distinct": "485", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eta_betaP", "index": "4", "type": "numeric", "distinct": "62", "missing": "0", "min": "2", "max": "46", "mean": "16", "stdev": "6" }, { "name": "Eig06_EA.bo.", "index": "5", "type": "numeric", "distinct": "493", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "piID", "index": "6", "type": "numeric", "distinct": "590", "missing": "0", "min": "4", "max": "15", "mean": "10", "stdev": "2" }, { "name": "Eig03_EA.bo.", "index": "7", "type": "numeric", "distinct": "483", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "8", "type": "numeric", "distinct": "483", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_beta", "index": "9", "type": "numeric", "distinct": "164", "missing": "0", "min": "8", "max": "79", "mean": "33", "stdev": "10" }, { "name": "C.", "index": "10", "type": "numeric", "distinct": "151", "missing": "0", "min": "25", "max": "56", "mean": "42", "stdev": "5" }, { "name": "PCD", "index": "11", "type": "numeric", "distinct": "582", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpMaxA_AEA.ed.", "index": "12", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_FL", "index": "13", "type": "numeric", "distinct": "606", "missing": "0", "min": "1", "max": "16", "mean": "6", "stdev": "2" }, { "name": "piPC03", "index": "14", "type": "numeric", "distinct": "420", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC02", "index": "15", "type": "numeric", "distinct": "252", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "16", "type": "numeric", "distinct": "252", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "17", "type": "numeric", "distinct": "522", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM15_AEA.ri.", "index": "18", "type": "numeric", "distinct": "522", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig12_AEA.bo.", "index": "19", "type": "numeric", "distinct": "452", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig09_AEA.bo.", "index": "20", "type": "numeric", "distinct": "454", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig07_AEA.bo.", "index": "21", "type": "numeric", "distinct": "460", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "22", "type": "numeric", "distinct": "497", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMaxA_EA", "index": "23", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "24", "type": "numeric", "distinct": "312", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "piPC05", "index": "25", "type": "numeric", "distinct": "551", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC08", "index": "26", "type": "numeric", "distinct": "581", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "27", "type": "numeric", "distinct": "470", "missing": "0", "min": "-3", "max": "3", "mean": "1", "stdev": "1" }, { "name": "piPC01", "index": "28", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SCBO", "index": "29", "type": "numeric", "distinct": "92", "missing": "0", "min": "10", "max": "82", "mean": "37", "stdev": "10" }, { "name": "Eig08_AEA.bo.", "index": "30", "type": "numeric", "distinct": "463", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig12_AEA.ri.", "index": "31", "type": "numeric", "distinct": "476", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "S0K", "index": "32", "type": "numeric", "distinct": "228", "missing": "0", "min": "24", "max": "292", "mean": "116", "stdev": "39" }, { "name": "SpMaxA_AEA.ri.", "index": "33", "type": "numeric", "distinct": "167", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig15_AEA.bo.", "index": "34", "type": "numeric", "distinct": "458", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "35", "type": "numeric", "distinct": "466", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nBM", "index": "36", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "41", "mean": "15", "stdev": "7" }, { "name": "Uc", "index": "37", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig12_EA", "index": "38", "type": "numeric", "distinct": "424", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM06_AEA.dm.", "index": "39", "type": "numeric", "distinct": "424", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ZM2Kup", "index": "40", "type": "numeric", "distinct": "653", "missing": "0", "min": "86", "max": "936", "mean": "403", "stdev": "126" }, { "name": "piPC04", "index": "41", "type": "numeric", "distinct": "519", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SpMaxA_AEA.bo.", "index": "42", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "piPC06", "index": "43", "type": "numeric", "distinct": "542", "missing": "0", "min": "2", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "44", "type": "numeric", "distinct": "635", "missing": "0", "min": "11", "max": "119", "mean": "54", "stdev": "16" }, { "name": "ZM2Per", "index": "45", "type": "numeric", "distinct": "657", "missing": "0", "min": "116", "max": "1387", "mean": "612", "stdev": "193" }, { "name": "ZM2V", "index": "46", "type": "numeric", "distinct": "345", "missing": "0", "min": "80", "max": "877", "mean": "392", "stdev": "122" }, { "name": "Eig08_EA", "index": "47", "type": "numeric", "distinct": "444", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM02_AEA.dm.", "index": "48", "type": "numeric", "distinct": "444", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Chi1_EA.ed.", "index": "49", "type": "numeric", "distinct": "579", "missing": "0", "min": "2", "max": "10", "mean": "5", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "50", "type": "numeric", "distinct": "435", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig08_AEA.ed.", "index": "51", "type": "numeric", "distinct": "502", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ZM2MulPer", "index": "52", "type": "numeric", "distinct": "659", "missing": "0", "min": "87", "max": "938", "mean": "419", "stdev": "130" }, { "name": "Eig05_AEA.bo.", "index": "53", "type": "numeric", "distinct": "485", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Mi", "index": "54", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nC", "index": "55", "type": "numeric", "distinct": "33", "missing": "0", "min": "5", "max": "43", "mean": "19", "stdev": "5" }, { "name": "Eig12_EA.bo.", "index": "56", "type": "numeric", "distinct": "466", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax6_Bh.m.", "index": "57", "type": "numeric", "distinct": "449", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "piPC07", "index": "58", "type": "numeric", "distinct": "568", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig09_AEA.ri.", "index": "59", "type": "numeric", "distinct": "492", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_AEA.bo.", "index": "60", "type": "numeric", "distinct": "454", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig07_AEA.ed.", "index": "61", "type": "numeric", "distinct": "491", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eta_F", "index": "62", "type": "numeric", "distinct": "663", "missing": "0", "min": "2", "max": "78", "mean": "25", "stdev": "10" }, { "name": "P_VSA_e_2", "index": "63", "type": "numeric", "distinct": "637", "missing": "0", "min": "28", "max": "299", "mean": "130", "stdev": "45" }, { "name": "SM02_AEA.bo.", "index": "64", "type": "numeric", "distinct": "344", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.028", "index": "65", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "ZM1Per", "index": "66", "type": "numeric", "distinct": "654", "missing": "0", "min": "132", "max": "1385", "mean": "583", "stdev": "177" }, { "name": "Eig06_AEA.bo.", "index": "67", "type": "numeric", "distinct": "468", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "68", "type": "numeric", "distinct": "535", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM03_AEA.ri.", "index": "69", "type": "numeric", "distinct": "535", "missing": "0", "min": "-4", "max": "7", "mean": "3", "stdev": "2" } ], "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 }