DEVELOPMENT... { "data_id": "32064", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4237", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4237", "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: CHEMBL4237 (TID: 10850), and it has 622 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": "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": "2016-07-15 09:13:30", "update_comment": null, "last_update": "2016-07-15 09:13:30", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3469008\/data_53504.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4237", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4237 (TID: 10850), and it has 622 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": 622, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.59154929577466, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 2.52819630606621, "Quartile1MeansOfNumericAtts": 1.2285514469453376, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 0.7428444669032079, "Quartile1StdDevOfNumericAtts": 0.7152838430590922, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 45.695260698298625, "Quartile2MeansOfNumericAtts": 8.337754823151124, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 4.686292851777762, "Quartile2StdDevOfNumericAtts": 4.114732642384954, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 88.29791721282837, "Quartile3MeansOfNumericAtts": 148.20096262057876, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 7.353286015503407, "Quartile3StdDevOfNumericAtts": 103.21273186457735, "AutoCorrelation": 0.34668599033816483, "MeanMeansOfNumericAtts": 961.7807708314195, "ClassEntropy": null, "Dimensionality": 0.11414790996784566, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 389.32568139845097, "MaxMeansOfNumericAtts": 31523.816382636658, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 19.027575992086454, "MaxStdDevOfNumericAtts": 186362.44479614554, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 68.58499566393299, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 5.104888222535491, "MeanStdDevOfNumericAtts": 4594.369461253113, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.056996721053719224, "MinMeansOfNumericAtts": -0.01619614147909968, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8663218750808765, "MinStdDevOfNumericAtts": 0.03090686383645358, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "104", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "X0", "index": "52", "type": "numeric", "distinct": "292", "missing": "0", "min": "10", "max": "117", "mean": "20", "stdev": "7" }, { "name": "ATSC7m", "index": "36", "type": "numeric", "distinct": "603", "missing": "0", "min": "3", "max": "286", "mean": "24", "stdev": "18" }, { "name": "CATS2D_02_AL", "index": "51", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "5", "stdev": "3" }, { "name": "P_VSA_v_3", "index": "50", "type": "numeric", "distinct": "573", "missing": "0", "min": "16", "max": "383", "mean": "136", "stdev": "45" }, { "name": "P_VSA_p_3", "index": "49", "type": "numeric", "distinct": "573", "missing": "0", "min": "16", "max": "383", "mean": "136", "stdev": "45" }, { "name": "ON1V", "index": "48", "type": "numeric", "distinct": "532", "missing": "0", "min": "1", "max": "20", "mean": "3", "stdev": "1" }, { "name": "SAtot", "index": "47", "type": "numeric", "distinct": "584", "missing": "0", "min": "207", "max": "3095", "mean": "463", "stdev": "187" }, { "name": "TIC5", "index": "46", "type": "numeric", "distinct": "482", "missing": "0", "min": "86", "max": "2192", "mean": "244", "stdev": "132" }, { "name": "ATS3e", "index": "45", "type": "numeric", "distinct": "454", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "S1K", "index": "44", "type": "numeric", "distinct": "502", "missing": "0", "min": "8", "max": "133", "mean": "19", "stdev": "8" }, { "name": "Si", "index": "43", "type": "numeric", "distinct": "548", "missing": "0", "min": "22", "max": "377", "mean": "53", "stdev": "23" }, { "name": "Xu", "index": "42", "type": "numeric", "distinct": "556", "missing": "0", "min": "14", "max": "105", "mean": "26", "stdev": "7" }, { "name": "SMTI", "index": "41", "type": "numeric", "distinct": "554", "missing": "0", "min": "1392", "max": "1290030", "mean": "13880", "stdev": "59169" }, { "name": "IDMT", "index": "40", "type": "numeric", "distinct": "559", "missing": "0", "min": "2088", "max": "4095250", "mean": "31524", "stdev": "186362" }, { "name": "IDET", "index": "39", "type": "numeric", "distinct": "558", "missing": "0", "min": "259", "max": "73822", "mean": "1631", "stdev": "3608" }, { "name": "nAT", "index": "38", "type": "numeric", "distinct": "67", "missing": "0", "min": "20", "max": "328", "mean": "47", "stdev": "20" }, { "name": "ISIZ", "index": "37", "type": "numeric", "distinct": "67", "missing": "0", "min": "86", "max": "2741", "mean": "267", "stdev": "161" }, { "name": "P_VSA_v_1", "index": "35", "type": "numeric", "distinct": "43", "missing": "0", "min": "24", "max": "1471", "mean": "197", "stdev": "104" }, { "name": "GMTI", "index": "61", "type": "numeric", "distinct": "557", "missing": "0", "min": "1269", "max": "1351930", "mean": "14564", "stdev": "61726" }, { "name": "Eta_epsi", "index": "69", "type": "numeric", "distinct": "487", "missing": "0", "min": "15", "max": "190", "mean": "29", "stdev": "12" }, { "name": "SpMin5_Bh.v.", "index": "68", "type": "numeric", "distinct": "387", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS3i", "index": "67", "type": "numeric", "distinct": "463", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "nHDon", "index": "66", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "3" }, { "name": "H.050", "index": "65", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "43", "mean": "3", "stdev": "3" }, { "name": "SpMaxA_EA.bo.", "index": "64", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS4i", "index": "63", "type": "numeric", "distinct": "487", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "MATS3s", "index": "62", "type": "numeric", "distinct": "305", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "TIC4", "index": "53", "type": "numeric", "distinct": "484", "missing": "0", "min": "86", "max": "2149", "mean": "243", "stdev": "130" }, { "name": "Eig12_AEA.dm.", "index": "60", "type": "numeric", "distinct": "433", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "VvdwZAZ", "index": "59", "type": "numeric", "distinct": "562", "missing": "0", "min": "136", "max": "2172", "mean": "329", "stdev": "132" }, { "name": "SaasN", "index": "58", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATS4e", "index": "57", "type": "numeric", "distinct": "493", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "ATS2i", "index": "56", "type": "numeric", "distinct": "449", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "PHI", "index": "55", "type": "numeric", "distinct": "528", "missing": "0", "min": "2", "max": "55", "mean": "5", "stdev": "4" }, { "name": "ATS1e", "index": "54", "type": "numeric", "distinct": "430", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "NsNH2", "index": "9", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "17", "type": "numeric", "distinct": "532", "missing": "0", "min": "0", "max": "158", "mean": "23", "stdev": "15" }, { "name": "Eta_betaS_A", "index": "16", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "15", "type": "numeric", "distinct": "522", "missing": "0", "min": "0", "max": "137", "mean": "18", "stdev": "11" }, { "name": "CATS2D_04_AP", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "P_VSA_i_3", "index": "13", "type": "numeric", "distinct": "375", "missing": "0", "min": "24", "max": "1865", "mean": "245", "stdev": "127" }, { "name": "D.Dtr10", "index": "12", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "2934", "mean": "34", "stdev": "167" }, { "name": "ATSC3m", "index": "11", "type": "numeric", "distinct": "596", "missing": "0", "min": "5", "max": "217", "mean": "23", "stdev": "14" }, { "name": "Hy", "index": "10", "type": "numeric", "distinct": "347", "missing": "0", "min": "-1", "max": "32", "mean": "1", "stdev": "2" }, { "name": "ATS5i", "index": "18", "type": "numeric", "distinct": "487", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "0" }, { "name": "CATS2D_00_PP", "index": "8", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "7", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "6", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "N.", "index": "5", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "29", "mean": "11", "stdev": "4" }, { "name": "P_VSA_e_2", "index": "4", "type": "numeric", "distinct": "573", "missing": "0", "min": "39", "max": "383", "mean": "128", "stdev": "42" }, { "name": "CATS2D_03_AP", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SsNH2", "index": "2", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "68", "mean": "3", "stdev": "5" }, { "name": "CATS2D_06_PL", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.m.", "index": "26", "type": "numeric", "distinct": "362", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_2", "index": "34", "type": "numeric", "distinct": "66", "missing": "0", "min": "24", "max": "1471", "mean": "198", "stdev": "104" }, { "name": "P_VSA_m_1", "index": "33", "type": "numeric", "distinct": "43", "missing": "0", "min": "24", "max": "1471", "mean": "197", "stdev": "104" }, { "name": "P_VSA_e_1", "index": "32", "type": "numeric", "distinct": "43", "missing": "0", "min": "24", "max": "1471", "mean": "197", "stdev": "104" }, { "name": "S2K", "index": "31", "type": "numeric", "distinct": "537", "missing": "0", "min": "3", "max": "66", "mean": "8", "stdev": "4" }, { "name": "SpMin8_Bh.v.", "index": "30", "type": "numeric", "distinct": "356", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Se", "index": "29", "type": "numeric", "distinct": "543", "missing": "0", "min": "21", "max": "330", "mean": "48", "stdev": "20" }, { "name": "SpMin7_Bh.p.", "index": "28", "type": "numeric", "distinct": "376", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_p_1", "index": "27", "type": "numeric", "distinct": "106", "missing": "0", "min": "24", "max": "1471", "mean": "204", "stdev": "104" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "622", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ON0V", "index": "25", "type": "numeric", "distinct": "478", "missing": "0", "min": "4", "max": "55", "mean": "9", "stdev": "4" }, { "name": "CATS2D_01_AA", "index": "24", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ATS2e", "index": "23", "type": "numeric", "distinct": "465", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "22", "type": "numeric", "distinct": "101", "missing": "0", "min": "12", "max": "1424", "mean": "186", "stdev": "103" }, { "name": "CENT", "index": "21", "type": "numeric", "distinct": "500", "missing": "0", "min": "158", "max": "190314", "mean": "1872", "stdev": "8738" }, { "name": "SpMin7_Bh.m.", "index": "20", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC2m", "index": "19", "type": "numeric", "distinct": "575", "missing": "0", "min": "1", "max": "146", "mean": "16", "stdev": "10" } ], "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 }