{ "data_id": "33051", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL263", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL263", "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: CHEMBL263 (TID: 10273), and it has 449 rows and 67 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 11:47:15", "update_comment": null, "last_update": "2016-07-15 11:47:15", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3495759\/data_53231.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-CHEMBL263", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL263 (TID: 10273), and it has 449 rows and 67 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": 449, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.299869534913301, "MinStdDevOfNumericAtts": 0.0056386218383644125, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9311921590466655, "MaxStdDevOfNumericAtts": 117.20224518003911, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.2604209909221611, "Quartile3StdDevOfNumericAtts": 2.4575962154063373, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.948627505567929, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.349613814049985, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 26.30020277086335, "Quartile1SkewnessOfNumericAtts": -0.012916481587127836, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11282370655163233, "AutoCorrelation": -0.16097098214285818, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8447644212828349, "Dimensionality": 0.15367483296213807, "MeanSkewnessOfNumericAtts": 0.5945630103965901, "Quartile2MeansOfNumericAtts": 2.4436870824053454, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.875441184128487, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.35874811882287033, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9999146162018235, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.43865964490793774, "MaxKurtosisOfNumericAtts": 21.42942316629927, "MinMeansOfNumericAtts": 0.031236080178173718, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 543.8655924276169, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.585547503267625, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 7.765919821826281, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.052721374694189, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "271", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "449", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaaNH", "index": "1", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.", "index": "2", "type": "numeric", "distinct": "109", "missing": "0", "min": "3", "max": "16", "mean": "9", "stdev": "4" }, { "name": "NaaNH", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "4", "type": "numeric", "distinct": "98", "missing": "0", "min": "19", "max": "260", "mean": "75", "stdev": "46" }, { "name": "CATS2D_01_DA", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "6", "type": "numeric", "distinct": "93", "missing": "0", "min": "19", "max": "260", "mean": "75", "stdev": "47" }, { "name": "MATS1m", "index": "7", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2i", "index": "8", "type": "numeric", "distinct": "243", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1e", "index": "9", "type": "numeric", "distinct": "156", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaN", "index": "10", "type": "numeric", "distinct": "340", "missing": "0", "min": "0", "max": "27", "mean": "11", "stdev": "8" }, { "name": "CATS2D_02_AA", "index": "11", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SssCH2", "index": "12", "type": "numeric", "distinct": "425", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "2" }, { "name": "N.075", "index": "13", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "NaaN", "index": "14", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "nN", "index": "15", "type": "numeric", "distinct": "11", "missing": "0", "min": "2", "max": "13", "mean": "5", "stdev": "2" }, { "name": "P_VSA_m_2", "index": "16", "type": "numeric", "distinct": "364", "missing": "0", "min": "92", "max": "471", "mean": "225", "stdev": "61" }, { "name": "MATS1e", "index": "17", "type": "numeric", "distinct": "232", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4Av", "index": "18", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CIC2", "index": "19", "type": "numeric", "distinct": "325", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "CATS2D_04_AL", "index": "20", "type": "numeric", "distinct": "28", "missing": "0", "min": "6", "max": "48", "mean": "16", "stdev": "6" }, { "name": "P_VSA_MR_7", "index": "21", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "144", "mean": "49", "stdev": "33" }, { "name": "X3Av", "index": "22", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig04_AEA.bo.", "index": "24", "type": "numeric", "distinct": "235", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_01_AA", "index": "25", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig05_AEA.ri.", "index": "26", "type": "numeric", "distinct": "280", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "C.031", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "28", "type": "numeric", "distinct": "159", "missing": "0", "min": "33", "max": "459", "mean": "109", "stdev": "53" }, { "name": "TPSA.NO.", "index": "29", "type": "numeric", "distinct": "146", "missing": "0", "min": "33", "max": "409", "mean": "105", "stdev": "51" }, { "name": "BLI", "index": "30", "type": "numeric", "distinct": "175", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig14_EA.ed.", "index": "31", "type": "numeric", "distinct": "200", "missing": "0", "min": "-2", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM09_AEA.ri.", "index": "32", "type": "numeric", "distinct": "200", "missing": "0", "min": "-2", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig05_EA.ri.", "index": "33", "type": "numeric", "distinct": "272", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "BIC2", "index": "34", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "35", "type": "numeric", "distinct": "115", "missing": "0", "min": "34", "max": "54", "mean": "44", "stdev": "4" }, { "name": "MATS2i", "index": "36", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin8_Bh.p.", "index": "37", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA", "index": "38", "type": "numeric", "distinct": "289", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "39", "type": "numeric", "distinct": "289", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "X2Av", "index": "40", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "41", "type": "numeric", "distinct": "140", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_LogP_5", "index": "42", "type": "numeric", "distinct": "186", "missing": "0", "min": "9", "max": "138", "mean": "41", "stdev": "19" }, { "name": "Eig04_EA.ed.", "index": "43", "type": "numeric", "distinct": "286", "missing": "0", "min": "5", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SM13_AEA.dm.", "index": "44", "type": "numeric", "distinct": "286", "missing": "0", "min": "5", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SpMax6_Bh.i.", "index": "45", "type": "numeric", "distinct": "258", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_i_2", "index": "46", "type": "numeric", "distinct": "363", "missing": "0", "min": "73", "max": "336", "mean": "152", "stdev": "36" }, { "name": "SpMax4_Bh.m.", "index": "47", "type": "numeric", "distinct": "217", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig11_AEA.bo.", "index": "48", "type": "numeric", "distinct": "188", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_EA.bo.", "index": "49", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_AL", "index": "50", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "27", "mean": "10", "stdev": "5" }, { "name": "CATS2D_04_AA", "index": "51", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "Eta_FL_A", "index": "52", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "53", "type": "numeric", "distinct": "187", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "54", "type": "numeric", "distinct": "224", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "X1Av", "index": "55", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "UNIP", "index": "56", "type": "numeric", "distinct": "142", "missing": "0", "min": "59", "max": "583", "mean": "174", "stdev": "73" }, { "name": "ZM2Kup", "index": "57", "type": "numeric", "distinct": "390", "missing": "0", "min": "284", "max": "1051", "mean": "544", "stdev": "117" }, { "name": "Eta_F", "index": "58", "type": "numeric", "distinct": "441", "missing": "0", "min": "16", "max": "106", "mean": "38", "stdev": "13" }, { "name": "SpMax6_Bh.e.", "index": "59", "type": "numeric", "distinct": "244", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.v.", "index": "60", "type": "numeric", "distinct": "192", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Xindex", "index": "61", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1e", "index": "62", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC2", "index": "63", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig15_AEA.ed.", "index": "64", "type": "numeric", "distinct": "197", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA", "index": "65", "type": "numeric", "distinct": "272", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "66", "type": "numeric", "distinct": "272", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig15_EA", "index": "67", "type": "numeric", "distinct": "193", "missing": "0", "min": "-1", "max": "2", "mean": "1", "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 }