DEVELOPMENT... { "data_id": "27281", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5604", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5604", "version": 10, "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: CHEMBL5604 (TID: 101030), and it has 103 rows and 65 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": "unknown", "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 21:12:31", "update_comment": null, "last_update": "2016-07-14 21:12:31", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3325868\/data_52907.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5604", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5604 (TID: 101030), and it has 103 rows and 65 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": 103, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.50746268656717, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": -0.6869644936897502, "Quartile1MeansOfNumericAtts": 0.4422791262135922, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.16618575205760683, "Quartile1StdDevOfNumericAtts": 0.13467085831330283, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": -0.13859027804971613, "Quartile2MeansOfNumericAtts": 1.830126213592233, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.5384850912916295, "Quartile2StdDevOfNumericAtts": 0.6160881904914075, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 1.1970188740567629, "Quartile3MeansOfNumericAtts": 5.230740291262135, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.9823311764168584, "Quartile3StdDevOfNumericAtts": 2.024234183257578, "AutoCorrelation": 0.598627450980392, "MeanMeansOfNumericAtts": 11.730334657252133, "ClassEntropy": null, "Dimensionality": 0.6504854368932039, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 50.89475967440575, "MaxMeansOfNumericAtts": 100.16473786407767, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 6.638195780450078, "MaxStdDevOfNumericAtts": 44.77489372000485, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 1.3584727404060397, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 0.6807277134278584, "MeanStdDevOfNumericAtts": 5.611365797173624, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6252236598658572, "MinMeansOfNumericAtts": -0.08545631067961165, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2271103753274293, "MinStdDevOfNumericAtts": 0.002935923349922316, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "24", "missing": "0", "target": "1", "min": "5", "max": "7", "mean": "5", "stdev": "1" }, { "name": "N.073", "index": "49", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_3", "index": "34", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "164", "mean": "51", "stdev": "32" }, { "name": "CATS2D_03_AA", "index": "48", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Rbrid", "index": "47", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "NNRS", "index": "46", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "45", "type": "numeric", "distinct": "89", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "JGI2", "index": "44", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RFD", "index": "43", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "RCI", "index": "42", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MAXDP", "index": "41", "type": "numeric", "distinct": "102", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "MAXDN", "index": "40", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM14_AEA.ri.", "index": "39", "type": "numeric", "distinct": "91", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "38", "type": "numeric", "distinct": "91", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "JGI7", "index": "37", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "36", "type": "numeric", "distinct": "67", "missing": "0", "min": "3", "max": "133", "mean": "81", "stdev": "27" }, { "name": "Eig03_EA.ri.", "index": "35", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "GATS3p", "index": "33", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SAdon", "index": "50", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "151", "mean": "42", "stdev": "27" }, { "name": "P_VSA_MR_6", "index": "51", "type": "numeric", "distinct": "93", "missing": "0", "min": "10", "max": "182", "mean": "94", "stdev": "37" }, { "name": "CATS2D_04_AA", "index": "52", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "JGI4", "index": "53", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nAB", "index": "54", "type": "numeric", "distinct": "18", "missing": "0", "min": "10", "max": "30", "mean": "20", "stdev": "4" }, { "name": "MATS8p", "index": "55", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "56", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "H.050", "index": "57", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Hy", "index": "58", "type": "numeric", "distinct": "89", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nHDon", "index": "59", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "nS", "index": "60", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "61", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "62", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "MATS4i", "index": "63", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "64", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "54", "mean": "13", "stdev": "12" }, { "name": "P_VSA_s_3", "index": "65", "type": "numeric", "distinct": "100", "missing": "0", "min": "12", "max": "89", "mean": "49", "stdev": "17" }, { "name": "P_VSA_MR_7", "index": "8", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "180", "mean": "68", "stdev": "45" }, { "name": "C.044", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NaasC", "index": "15", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "11", "mean": "7", "stdev": "2" }, { "name": "SpMax1_Bh.s.", "index": "14", "type": "numeric", "distinct": "36", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "MATS3v", "index": "13", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SaaS", "index": "12", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nThiazoles", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.031", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.028", "index": "9", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NaaS", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "7", "type": "numeric", "distinct": "75", "missing": "0", "min": "41", "max": "192", "mean": "100", "stdev": "38" }, { "name": "nPyrazines", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "H.049", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NaaN", "index": "4", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "N.075", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "SaaN", "index": "2", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "23", "mean": "11", "stdev": "7" }, { "name": "C.027", "index": "1", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "103", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_i_1", "index": "18", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "63", "mean": "12", "stdev": "16" }, { "name": "GATS8m", "index": "19", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS3v", "index": "20", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5s", "index": "21", "type": "numeric", "distinct": "103", "missing": "0", "min": "16", "max": "198", "mean": "68", "stdev": "39" }, { "name": "MATS3p", "index": "22", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_alpha_A", "index": "23", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "24", "type": "numeric", "distinct": "77", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "S.107", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "26", "type": "numeric", "distinct": "50", "missing": "0", "min": "18", "max": "166", "mean": "70", "stdev": "35" }, { "name": "SpMax2_Bh.v.", "index": "27", "type": "numeric", "distinct": "81", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS8p", "index": "28", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SaasC", "index": "29", "type": "numeric", "distinct": "103", "missing": "0", "min": "-4", "max": "8", "mean": "4", "stdev": "2" }, { "name": "SpMax2_Bh.e.", "index": "30", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS5i", "index": "31", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "32", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "2", "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 }