{ "data_id": "32646", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3590", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3590", "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: CHEMBL3590 (TID: 11214), and it has 187 rows and 62 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 10:45:24", "update_comment": null, "last_update": "2016-07-15 10:45:24", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3486334\/data_52414.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3590", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3590 (TID: 11214), and it has 187 rows and 62 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": 187, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.4051945166727728, "MinStdDevOfNumericAtts": 0.01739490486313495, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6439814616027983, "MaxStdDevOfNumericAtts": 43.32012995854411, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.1099216133834708, "Quartile3StdDevOfNumericAtts": 1.3329838264605567, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.674, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.2068150294075043, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.007194465665052, "Quartile1SkewnessOfNumericAtts": -0.17540924616958317, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.20870533333753802, "AutoCorrelation": 0.041198924731182855, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.6518057014792387, "Dimensionality": 0.3422459893048128, "MeanSkewnessOfNumericAtts": 0.21546962039517858, "Quartile2MeansOfNumericAtts": 4.384005347593583, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.2601848109604554, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.2627656407946045, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8315688696559378, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.503445905791924, "MaxKurtosisOfNumericAtts": 3.006207793244108, "MinMeansOfNumericAtts": -0.13416042780748663, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 117.47620320855614, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.46438792675424967, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 6.734652406417112, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2691087147636884, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "125", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "187", "missing": "0", "identifier": "1", "distr": [] }, { "name": "piPC05", "index": "1", "type": "numeric", "distinct": "131", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piPC09", "index": "2", "type": "numeric", "distinct": "141", "missing": "0", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "piPC08", "index": "3", "type": "numeric", "distinct": "136", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "4", "type": "numeric", "distinct": "140", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "piPC06", "index": "5", "type": "numeric", "distinct": "128", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "6", "type": "numeric", "distinct": "136", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "piPC10", "index": "7", "type": "numeric", "distinct": "139", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "piID", "index": "8", "type": "numeric", "distinct": "133", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "nBM", "index": "9", "type": "numeric", "distinct": "17", "missing": "0", "min": "3", "max": "21", "mean": "11", "stdev": "6" }, { "name": "Uc", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "P_VSA_p_3", "index": "11", "type": "numeric", "distinct": "158", "missing": "0", "min": "47", "max": "222", "mean": "117", "stdev": "43" }, { "name": "P_VSA_v_3", "index": "12", "type": "numeric", "distinct": "158", "missing": "0", "min": "47", "max": "222", "mean": "117", "stdev": "43" }, { "name": "Eta_betaP", "index": "13", "type": "numeric", "distinct": "29", "missing": "0", "min": "5", "max": "24", "mean": "12", "stdev": "6" }, { "name": "Ui", "index": "14", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nAB", "index": "15", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "18", "mean": "9", "stdev": "6" }, { "name": "piPC04", "index": "16", "type": "numeric", "distinct": "131", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nCar", "index": "17", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "6" }, { "name": "Eta_beta", "index": "18", "type": "numeric", "distinct": "84", "missing": "0", "min": "15", "max": "51", "mean": "28", "stdev": "8" }, { "name": "PCD", "index": "19", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "20", "type": "numeric", "distinct": "51", "missing": "0", "min": "36", "max": "154", "mean": "88", "stdev": "29" }, { "name": "NaasC", "index": "21", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "JGI3", "index": "22", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "23", "type": "numeric", "distinct": "144", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "C.019", "index": "24", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nRNHO", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig01_AEA.dm.", "index": "26", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "27", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_sh_y", "index": "28", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ARR", "index": "29", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.017", "index": "30", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nR.Ct", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "32", "type": "numeric", "distinct": "150", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "33", "type": "numeric", "distinct": "141", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SdssC", "index": "34", "type": "numeric", "distinct": "174", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MATS4p", "index": "35", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS5e", "index": "36", "type": "numeric", "distinct": "177", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "nCconj", "index": "37", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NdssC", "index": "38", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "MATS5m", "index": "39", "type": "numeric", "distinct": "162", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS5m", "index": "40", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2s", "index": "41", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "AAC", "index": "42", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AECC", "index": "43", "type": "numeric", "distinct": "128", "missing": "0", "min": "6", "max": "16", "mean": "10", "stdev": "2" }, { "name": "ALOGP", "index": "44", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "ALOGP2", "index": "45", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "49", "mean": "14", "stdev": "11" }, { "name": "AMR", "index": "46", "type": "numeric", "distinct": "172", "missing": "0", "min": "59", "max": "158", "mean": "91", "stdev": "18" }, { "name": "AMW", "index": "47", "type": "numeric", "distinct": "139", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "ATS1e", "index": "48", "type": "numeric", "distinct": "136", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "49", "type": "numeric", "distinct": "127", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "50", "type": "numeric", "distinct": "136", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1p", "index": "51", "type": "numeric", "distinct": "136", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1s", "index": "52", "type": "numeric", "distinct": "158", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS1v", "index": "53", "type": "numeric", "distinct": "140", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS2e", "index": "54", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2i", "index": "55", "type": "numeric", "distinct": "143", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS2m", "index": "56", "type": "numeric", "distinct": "152", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2p", "index": "57", "type": "numeric", "distinct": "155", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2s", "index": "58", "type": "numeric", "distinct": "162", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS2v", "index": "59", "type": "numeric", "distinct": "155", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS3e", "index": "60", "type": "numeric", "distinct": "163", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS3i", "index": "61", "type": "numeric", "distinct": "160", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3m", "index": "62", "type": "numeric", "distinct": "164", "missing": "0", "min": "3", "max": "4", "mean": "4", "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 }