{ "data_id": "32836", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5784", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5784", "version": 9, "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: CHEMBL5784 (TID: 101332), and it has 106 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": "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 11:14:14", "update_comment": null, "last_update": "2016-07-15 11:14:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3490764\/data_52982.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-CHEMBL5784", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5784 (TID: 101332), and it has 106 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": 106, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.894682065605918, "MinStdDevOfNumericAtts": 0.014512036086458137, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1906017854833741, "MaxStdDevOfNumericAtts": 94.98771642189654, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.22383626469777518, "Quartile3StdDevOfNumericAtts": 6.373380380965922, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0022735849056605, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.7839918708045746, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 16.25957975986278, "Quartile1SkewnessOfNumericAtts": -0.35355102095244095, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.20532916443650684, "AutoCorrelation": 0.2441523809523809, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.0146893729905004, "Dimensionality": 0.6320754716981132, "MeanSkewnessOfNumericAtts": 0.42727875346166594, "Quartile2MeansOfNumericAtts": 4.054764150943397, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.828631574307978, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.34372934481813716, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.668161808708013, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1438372813939812, "MaxKurtosisOfNumericAtts": 11.688056049335243, "MinMeansOfNumericAtts": -4.115377358490566, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 239.93942452830188, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.6213016113358893, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 8.226415094339622, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.7808764799123002, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "37", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "106", "missing": "0", "identifier": "1", "distr": [] }, { "name": "IC1", "index": "1", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nN", "index": "2", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "2" }, { "name": "TPSA.NO.", "index": "3", "type": "numeric", "distinct": "97", "missing": "0", "min": "37", "max": "295", "mean": "90", "stdev": "35" }, { "name": "JGI2", "index": "4", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SsCH3", "index": "5", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "JGT", "index": "6", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "N.", "index": "7", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "4" }, { "name": "P_VSA_i_4", "index": "8", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "177", "mean": "69", "stdev": "39" }, { "name": "Ui", "index": "9", "type": "numeric", "distinct": "24", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "piID", "index": "10", "type": "numeric", "distinct": "105", "missing": "0", "min": "8", "max": "17", "mean": "12", "stdev": "2" }, { "name": "P_VSA_m_2", "index": "11", "type": "numeric", "distinct": "106", "missing": "0", "min": "57", "max": "334", "mean": "193", "stdev": "51" }, { "name": "Eta_betaS_A", "index": "12", "type": "numeric", "distinct": "61", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_beta", "index": "13", "type": "numeric", "distinct": "77", "missing": "0", "min": "23", "max": "94", "mean": "41", "stdev": "10" }, { "name": "nBM", "index": "14", "type": "numeric", "distinct": "25", "missing": "0", "min": "6", "max": "42", "mean": "19", "stdev": "6" }, { "name": "Uc", "index": "15", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "16", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "369", "mean": "69", "stdev": "52" }, { "name": "AAC", "index": "17", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "H.046", "index": "18", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "35", "mean": "4", "stdev": "9" }, { "name": "IC0", "index": "19", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nHet", "index": "20", "type": "numeric", "distinct": "14", "missing": "0", "min": "2", "max": "24", "mean": "8", "stdev": "3" }, { "name": "SIC0", "index": "21", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "HNar", "index": "22", "type": "numeric", "distinct": "70", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "PDI", "index": "23", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "24", "type": "numeric", "distinct": "49", "missing": "0", "min": "24", "max": "483", "mean": "240", "stdev": "95" }, { "name": "SpMin1_Bh.m.", "index": "25", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "N.075", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NaaN", "index": "27", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SaaN", "index": "28", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "22", "mean": "6", "stdev": "5" }, { "name": "Eta_F", "index": "29", "type": "numeric", "distinct": "106", "missing": "0", "min": "11", "max": "92", "mean": "33", "stdev": "12" }, { "name": "Eta_FL", "index": "30", "type": "numeric", "distinct": "104", "missing": "0", "min": "3", "max": "18", "mean": "8", "stdev": "2" }, { "name": "Eig03_EA.bo.", "index": "31", "type": "numeric", "distinct": "100", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC02", "index": "32", "type": "numeric", "distinct": "82", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "33", "type": "numeric", "distinct": "82", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "34", "type": "numeric", "distinct": "103", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "35", "type": "numeric", "distinct": "100", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC04", "index": "36", "type": "numeric", "distinct": "98", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "37", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "PCD", "index": "38", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "39", "type": "numeric", "distinct": "99", "missing": "0", "min": "37", "max": "295", "mean": "96", "stdev": "37" }, { "name": "BLTA96", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "-7", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "BLTD48", "index": "41", "type": "numeric", "distinct": "87", "missing": "0", "min": "-7", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "BLTF96", "index": "42", "type": "numeric", "distinct": "89", "missing": "0", "min": "-6", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "MLOGP", "index": "43", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "MLOGP2", "index": "44", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "32", "mean": "10", "stdev": "7" }, { "name": "piPC07", "index": "45", "type": "numeric", "distinct": "99", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "X0A", "index": "46", "type": "numeric", "distinct": "46", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "AMW", "index": "47", "type": "numeric", "distinct": "101", "missing": "0", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "ARR", "index": "48", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1v", "index": "49", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "12", "mean": "6", "stdev": "2" }, { "name": "BIC0", "index": "50", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.001", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "C.003", "index": "52", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "CATS2D_02_LL", "index": "53", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "38", "mean": "11", "stdev": "9" }, { "name": "CATS2D_03_LL", "index": "54", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "41", "mean": "9", "stdev": "9" }, { "name": "CATS2D_04_LL", "index": "55", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "33", "mean": "8", "stdev": "8" }, { "name": "CATS2D_05_LL", "index": "56", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "7" }, { "name": "CATS2D_06_LL", "index": "57", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "30", "mean": "9", "stdev": "7" }, { "name": "CATS2D_08_LL", "index": "58", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "29", "mean": "7", "stdev": "7" }, { "name": "CIC1", "index": "59", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "60", "type": "numeric", "distinct": "81", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP", "index": "61", "type": "numeric", "distinct": "38", "missing": "0", "min": "7", "max": "48", "mean": "20", "stdev": "6" }, { "name": "Eta_betaP_A", "index": "62", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_F_A", "index": "63", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_FL_A", "index": "64", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_L_A", "index": "65", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "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 }