{ "data_id": "39749", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3886", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3886", "version": 13, "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: CHEMBL3886 (TID: 20007), and it has 694 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": "2016-07-16 09:04:14", "update_comment": null, "last_update": "2016-07-16 09:04:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3682690\/data_53469.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3886", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3886 (TID: 20007), and it has 694 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": 694, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.10230547550432277, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.120138032053673, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.19284569955413464, "Quartile2MeansOfNumericAtts": 4.659842219020173, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.00356831431136, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.32931309215117116, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6892459605088597, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.418320912916503, "MaxKurtosisOfNumericAtts": 11.297494068500814, "MinMeansOfNumericAtts": 0.04135590778097982, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 666.9844092219021, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.1987999783219525, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 8.142159582132566, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9693686097681085, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.0272274907433423, "MinStdDevOfNumericAtts": 0.044705596054443957, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.4183366102350079, "MaxStdDevOfNumericAtts": 152.90180439851892, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.27282169005006196, "Quartile3StdDevOfNumericAtts": 2.0697084115900353, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.006445244956772, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.4362673277266453, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 35.46609042815974, "Quartile1SkewnessOfNumericAtts": -0.766917811799838, "AutoCorrelation": 0.6559841269841271, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.26295650674539217 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "62", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "694", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin6_Bh.p.", "index": "1", "type": "numeric", "distinct": "396", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "2", "type": "numeric", "distinct": "489", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS7p", "index": "3", "type": "numeric", "distinct": "563", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS6p", "index": "4", "type": "numeric", "distinct": "537", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3e", "index": "5", "type": "numeric", "distinct": "488", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATSC3m", "index": "6", "type": "numeric", "distinct": "670", "missing": "0", "min": "3", "max": "59", "mean": "22", "stdev": "8" }, { "name": "ATS7v", "index": "7", "type": "numeric", "distinct": "552", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ZM2Per", "index": "8", "type": "numeric", "distinct": "673", "missing": "0", "min": "292", "max": "1169", "mean": "667", "stdev": "153" }, { "name": "Eig06_AEA.bo.", "index": "9", "type": "numeric", "distinct": "456", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC7p", "index": "10", "type": "numeric", "distinct": "665", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "3" }, { "name": "ATS7i", "index": "11", "type": "numeric", "distinct": "567", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ZM2Kup", "index": "12", "type": "numeric", "distinct": "668", "missing": "0", "min": "202", "max": "780", "mean": "443", "stdev": "103" }, { "name": "ZM2MulPer", "index": "13", "type": "numeric", "distinct": "675", "missing": "0", "min": "205", "max": "789", "mean": "455", "stdev": "102" }, { "name": "ATS8e", "index": "14", "type": "numeric", "distinct": "576", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS3i", "index": "15", "type": "numeric", "distinct": "500", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM2V", "index": "16", "type": "numeric", "distinct": "308", "missing": "0", "min": "193", "max": "746", "mean": "427", "stdev": "96" }, { "name": "ATS8p", "index": "17", "type": "numeric", "distinct": "576", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "18", "type": "numeric", "distinct": "506", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC6v", "index": "19", "type": "numeric", "distinct": "668", "missing": "0", "min": "0", "max": "35", "mean": "10", "stdev": "5" }, { "name": "CATS2D_03_AL", "index": "20", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "6", "stdev": "3" }, { "name": "Eig06_EA", "index": "21", "type": "numeric", "distinct": "449", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "22", "type": "numeric", "distinct": "449", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS7e", "index": "23", "type": "numeric", "distinct": "552", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS2e", "index": "24", "type": "numeric", "distinct": "484", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS8i", "index": "25", "type": "numeric", "distinct": "586", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SpMin6_Bh.s.", "index": "26", "type": "numeric", "distinct": "379", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "27", "type": "numeric", "distinct": "473", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "ATS5p", "index": "28", "type": "numeric", "distinct": "531", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "29", "type": "numeric", "distinct": "518", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC6p", "index": "30", "type": "numeric", "distinct": "663", "missing": "0", "min": "0", "max": "27", "mean": "8", "stdev": "3" }, { "name": "piPC02", "index": "31", "type": "numeric", "distinct": "241", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "32", "type": "numeric", "distinct": "241", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "33", "type": "numeric", "distinct": "455", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "34", "type": "numeric", "distinct": "460", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "35", "type": "numeric", "distinct": "325", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC7v", "index": "36", "type": "numeric", "distinct": "666", "missing": "0", "min": "0", "max": "37", "mean": "10", "stdev": "5" }, { "name": "SaasN", "index": "37", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "ATS5e", "index": "38", "type": "numeric", "distinct": "530", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eta_betaP", "index": "39", "type": "numeric", "distinct": "49", "missing": "0", "min": "8", "max": "35", "mean": "20", "stdev": "5" }, { "name": "MWC04", "index": "40", "type": "numeric", "distinct": "328", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "41", "type": "numeric", "distinct": "471", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SpMin6_Bh.e.", "index": "42", "type": "numeric", "distinct": "373", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.i.", "index": "43", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GGI6", "index": "44", "type": "numeric", "distinct": "429", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "MWC05", "index": "45", "type": "numeric", "distinct": "448", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "ATS6i", "index": "46", "type": "numeric", "distinct": "551", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS8v", "index": "47", "type": "numeric", "distinct": "560", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATS6e", "index": "48", "type": "numeric", "distinct": "548", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC8p", "index": "49", "type": "numeric", "distinct": "666", "missing": "0", "min": "0", "max": "25", "mean": "7", "stdev": "3" }, { "name": "X1MulPer", "index": "50", "type": "numeric", "distinct": "636", "missing": "0", "min": "3", "max": "15", "mean": "8", "stdev": "2" }, { "name": "SpMin6_Bh.v.", "index": "51", "type": "numeric", "distinct": "374", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "52", "type": "numeric", "distinct": "251", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS2i", "index": "53", "type": "numeric", "distinct": "489", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "54", "type": "numeric", "distinct": "448", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "X5sol", "index": "55", "type": "numeric", "distinct": "606", "missing": "0", "min": "3", "max": "17", "mean": "7", "stdev": "2" }, { "name": "MATS1m", "index": "56", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "57", "type": "numeric", "distinct": "635", "missing": "0", "min": "52", "max": "274", "mean": "133", "stdev": "32" }, { "name": "SpMax2_Bh.m.", "index": "58", "type": "numeric", "distinct": "310", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig12_AEA.ed.", "index": "59", "type": "numeric", "distinct": "435", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig06_AEA.ed.", "index": "60", "type": "numeric", "distinct": "502", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ON0V", "index": "61", "type": "numeric", "distinct": "509", "missing": "0", "min": "3", "max": "16", "mean": "9", "stdev": "2" }, { "name": "SRW09", "index": "62", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "SM05_AEA.bo.", "index": "63", "type": "numeric", "distinct": "439", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "ATSC3i", "index": "64", "type": "numeric", "distinct": "554", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "65", "type": "numeric", "distinct": "594", "missing": "0", "min": "0", "max": "46", "mean": "18", "stdev": "8" }, { "name": "X4sol", "index": "66", "type": "numeric", "distinct": "605", "missing": "0", "min": "4", "max": "19", "mean": "9", "stdev": "2" }, { "name": "X1Per", "index": "67", "type": "numeric", "distinct": "641", "missing": "0", "min": "2", "max": "12", "mean": "7", "stdev": "2" }, { "name": "SpMin3_Bh.v.", "index": "68", "type": "numeric", "distinct": "325", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM02_AEA.ed.", "index": "69", "type": "numeric", "distinct": "171", "missing": "0", "min": "5", "max": "7", "mean": "6", "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 }