{ "data_id": "36297", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1889", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1889", "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: CHEMBL1889 (TID: 134), and it has 878 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": "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 20:44:09", "update_comment": null, "last_update": "2016-07-15 20:44:09", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3584509\/data_53606.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1889", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1889 (TID: 134), and it has 878 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": 878, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.618342600276552, "MinMeansOfNumericAtts": -1.9634020501138958, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.8568351556699911, "MaxMeansOfNumericAtts": 246.8978701594533, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 9.20155410022779, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8340708571619821, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3SkewnessOfNumericAtts": 1.6001149495937397, "MaxSkewnessOfNumericAtts": 3.0931539695240606, "MinStdDevOfNumericAtts": 0.0533270226371225, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 3.494419699496744, "MaxStdDevOfNumericAtts": 266.748930077411, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.05514807302355984, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4079330865603645, "MeanKurtosisOfNumericAtts": 1.0411543556548044, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 19.69021976895542, "Quartile1SkewnessOfNumericAtts": 0.001657174979077608, "AutoCorrelation": -0.03389053591790075, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4208892676623817, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08086560364464693, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.4339456367519916, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.7168857109643739, "Quartile2MeansOfNumericAtts": 3.9259681093394048, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 15.126667957150602, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4720172166691121, "Quartile2StdDevOfNumericAtts": 0.7183071920483362, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3799867058431565, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "593", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "878", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM06_EA.ri.", "index": "1", "type": "numeric", "distinct": "614", "missing": "0", "min": "7", "max": "10", "mean": "8", "stdev": "0" }, { "name": "MAXDP", "index": "2", "type": "numeric", "distinct": "693", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "2" }, { "name": "GGI10", "index": "3", "type": "numeric", "distinct": "376", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "4", "type": "numeric", "distinct": "378", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM07_EA.ri.", "index": "5", "type": "numeric", "distinct": "593", "missing": "0", "min": "7", "max": "11", "mean": "9", "stdev": "0" }, { "name": "SM05_EA.ri.", "index": "6", "type": "numeric", "distinct": "548", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig05_AEA.ri.", "index": "7", "type": "numeric", "distinct": "484", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "8", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin6_Bh.e.", "index": "9", "type": "numeric", "distinct": "383", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_AEA.dm.", "index": "10", "type": "numeric", "distinct": "449", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM08_EA.ri.", "index": "11", "type": "numeric", "distinct": "611", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SpMin6_Bh.i.", "index": "12", "type": "numeric", "distinct": "395", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "S2K", "index": "13", "type": "numeric", "distinct": "644", "missing": "0", "min": "4", "max": "50", "mean": "14", "stdev": "9" }, { "name": "Eig04_AEA.dm.", "index": "14", "type": "numeric", "distinct": "404", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig12_EA.dm.", "index": "15", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig09_EA.dm.", "index": "16", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMin7_Bh.p.", "index": "17", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.008", "index": "18", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "SpAD_EA.dm.", "index": "19", "type": "numeric", "distinct": "335", "missing": "0", "min": "0", "max": "83", "mean": "17", "stdev": "16" }, { "name": "Eig12_AEA.dm.", "index": "20", "type": "numeric", "distinct": "368", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig05_EA.dm.", "index": "21", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SIC1", "index": "22", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI7", "index": "23", "type": "numeric", "distinct": "468", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "DLS_02", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM02_EA.dm.", "index": "25", "type": "numeric", "distinct": "304", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig05_EA.ed.", "index": "26", "type": "numeric", "distinct": "522", "missing": "0", "min": "3", "max": "11", "mean": "8", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "27", "type": "numeric", "distinct": "522", "missing": "0", "min": "3", "max": "11", "mean": "8", "stdev": "1" }, { "name": "Eig04_EA.ed.", "index": "28", "type": "numeric", "distinct": "470", "missing": "0", "min": "3", "max": "12", "mean": "8", "stdev": "1" }, { "name": "SM13_AEA.dm.", "index": "29", "type": "numeric", "distinct": "470", "missing": "0", "min": "3", "max": "12", "mean": "8", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "30", "type": "numeric", "distinct": "426", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig11_EA.dm.", "index": "31", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "PHI", "index": "32", "type": "numeric", "distinct": "670", "missing": "0", "min": "3", "max": "42", "mean": "11", "stdev": "8" }, { "name": "Psi_i_s", "index": "33", "type": "numeric", "distinct": "597", "missing": "0", "min": "34", "max": "374", "mean": "105", "stdev": "54" }, { "name": "Eig09_AEA.dm.", "index": "34", "type": "numeric", "distinct": "484", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "S3K", "index": "35", "type": "numeric", "distinct": "700", "missing": "0", "min": "2", "max": "33", "mean": "8", "stdev": "6" }, { "name": "ATS7m", "index": "36", "type": "numeric", "distinct": "668", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax5_Bh.s.", "index": "37", "type": "numeric", "distinct": "350", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "SpMax7_Bh.s.", "index": "38", "type": "numeric", "distinct": "375", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig08_AEA.dm.", "index": "39", "type": "numeric", "distinct": "473", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig07_EA.dm.", "index": "40", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC5s", "index": "41", "type": "numeric", "distinct": "828", "missing": "0", "min": "11", "max": "928", "mean": "205", "stdev": "201" }, { "name": "Eig05_AEA.ed.", "index": "42", "type": "numeric", "distinct": "433", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "BIC1", "index": "43", "type": "numeric", "distinct": "212", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig13_EA.dm.", "index": "44", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "45", "type": "numeric", "distinct": "392", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "TIE", "index": "46", "type": "numeric", "distinct": "831", "missing": "0", "min": "17", "max": "1005", "mean": "168", "stdev": "189" }, { "name": "X4sol", "index": "47", "type": "numeric", "distinct": "689", "missing": "0", "min": "3", "max": "44", "mean": "13", "stdev": "5" }, { "name": "CATS2D_08_DL", "index": "48", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "34", "mean": "4", "stdev": "6" }, { "name": "Eig10_EA.dm.", "index": "49", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MWC08", "index": "50", "type": "numeric", "distinct": "541", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "0" }, { "name": "Ram", "index": "51", "type": "numeric", "distinct": "38", "missing": "0", "min": "2", "max": "56", "mean": "15", "stdev": "6" }, { "name": "Eig07_AEA.dm.", "index": "52", "type": "numeric", "distinct": "484", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "CIC3", "index": "53", "type": "numeric", "distinct": "543", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATSC8s", "index": "54", "type": "numeric", "distinct": "818", "missing": "0", "min": "7", "max": "1385", "mean": "221", "stdev": "267" }, { "name": "CATS2D_05_AA", "index": "55", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "4" }, { "name": "Eig08_EA.dm.", "index": "56", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsssCH", "index": "57", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "MWC07", "index": "58", "type": "numeric", "distinct": "519", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "59", "type": "numeric", "distinct": "714", "missing": "0", "min": "74", "max": "779", "mean": "247", "stdev": "120" }, { "name": "DELS", "index": "60", "type": "numeric", "distinct": "831", "missing": "0", "min": "3", "max": "344", "mean": "66", "stdev": "54" }, { "name": "ATSC2s", "index": "61", "type": "numeric", "distinct": "802", "missing": "0", "min": "9", "max": "408", "mean": "73", "stdev": "62" }, { "name": "SM03_EA.dm.", "index": "62", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SdssC", "index": "63", "type": "numeric", "distinct": "616", "missing": "0", "min": "-18", "max": "4", "mean": "-2", "stdev": "3" }, { "name": "MWC09", "index": "64", "type": "numeric", "distinct": "542", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "0" }, { "name": "CATS2D_08_DA", "index": "65", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "25", "mean": "3", "stdev": "5" }, { "name": "SpMax6_Bh.s.", "index": "66", "type": "numeric", "distinct": "380", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "H.052", "index": "67", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "34", "mean": "5", "stdev": "5" }, { "name": "CIC2", "index": "68", "type": "numeric", "distinct": "604", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM09_EA.ri.", "index": "69", "type": "numeric", "distinct": "611", "missing": "0", "min": "9", "max": "13", "mean": "11", "stdev": "1" } ], "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 }