{ "data_id": "39365", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1995", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1995", "version": 12, "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: CHEMBL1995 (TID: 143), and it has 393 rows and 66 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": "2016-07-16 07:39:58", "update_comment": null, "last_update": "2016-07-16 07:39:58", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3671842\/data_53062.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1995", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1995 (TID: 143), and it has 393 rows and 66 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": 393, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.17302798982188294, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.2965767447029606, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.06548016245571853, "Quartile2MeansOfNumericAtts": 3.363867684478371, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.308236391594202, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.10537298231158725, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2714213151274438, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9283099061932055, "MaxKurtosisOfNumericAtts": 11.602356865197732, "MinMeansOfNumericAtts": 0.00793384223918575, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 270.4662086513995, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.05262704521414463, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 7.768447837150129, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0963304737841173, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.6801273062848683, "MinStdDevOfNumericAtts": 0.0019234587642851036, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.46104104638299254, "MaxStdDevOfNumericAtts": 162.58732512343352, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6004192810712827, "Quartile3StdDevOfNumericAtts": 4.321850260765788, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0099033078880406, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.0626107233602739, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 17.5836482852911, "Quartile1SkewnessOfNumericAtts": -0.343192623478253, "AutoCorrelation": 0.283734693877551, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.23976152663784267 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "185", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "393", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nBnz", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "nCb.", "index": "2", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "3" }, { "name": "GATS2v", "index": "3", "type": "numeric", "distinct": "239", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "4", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "246", "mean": "107", "stdev": "52" }, { "name": "piPC08", "index": "5", "type": "numeric", "distinct": "270", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eta_FL_A", "index": "6", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DLS_05", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCar", "index": "8", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "30", "mean": "14", "stdev": "7" }, { "name": "piPC06", "index": "9", "type": "numeric", "distinct": "268", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "10", "type": "numeric", "distinct": "270", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "NaaCH", "index": "11", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "4" }, { "name": "piPC09", "index": "12", "type": "numeric", "distinct": "277", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "X4Av", "index": "13", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_L_A", "index": "14", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC05", "index": "15", "type": "numeric", "distinct": "263", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "Eta_betaP", "index": "16", "type": "numeric", "distinct": "54", "missing": "0", "min": "2", "max": "37", "mean": "18", "stdev": "7" }, { "name": "nCsp2", "index": "17", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "32", "mean": "16", "stdev": "6" }, { "name": "JGI9", "index": "18", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_NL", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATSC3m", "index": "20", "type": "numeric", "distinct": "355", "missing": "0", "min": "14", "max": "50", "mean": "33", "stdev": "7" }, { "name": "PCD", "index": "21", "type": "numeric", "distinct": "258", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nAB", "index": "22", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "30", "mean": "15", "stdev": "7" }, { "name": "ATSC4m", "index": "23", "type": "numeric", "distinct": "369", "missing": "0", "min": "12", "max": "62", "mean": "36", "stdev": "9" }, { "name": "DLS_04", "index": "24", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaasC", "index": "25", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "SaasC", "index": "26", "type": "numeric", "distinct": "336", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "nCsp3", "index": "27", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "20", "mean": "8", "stdev": "4" }, { "name": "P_VSA_LogP_5", "index": "28", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "187", "mean": "33", "stdev": "23" }, { "name": "nR06", "index": "29", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATSC2m", "index": "30", "type": "numeric", "distinct": "315", "missing": "0", "min": "7", "max": "36", "mean": "22", "stdev": "6" }, { "name": "C.", "index": "31", "type": "numeric", "distinct": "114", "missing": "0", "min": "32", "max": "53", "mean": "43", "stdev": "5" }, { "name": "NRS", "index": "32", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Eta_C_A", "index": "33", "type": "numeric", "distinct": "283", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X0A", "index": "34", "type": "numeric", "distinct": "59", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Ui", "index": "35", "type": "numeric", "distinct": "32", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.008", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eta_L", "index": "37", "type": "numeric", "distinct": "328", "missing": "0", "min": "4", "max": "12", "mean": "8", "stdev": "2" }, { "name": "piPC04", "index": "38", "type": "numeric", "distinct": "254", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "H.050", "index": "39", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "nHDon", "index": "40", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "nCIR", "index": "41", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "9", "mean": "4", "stdev": "2" }, { "name": "CATS2D_06_DD", "index": "42", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "Mv", "index": "43", "type": "numeric", "distinct": "134", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr06", "index": "44", "type": "numeric", "distinct": "249", "missing": "0", "min": "0", "max": "737", "mean": "270", "stdev": "163" }, { "name": "P_VSA_e_5", "index": "45", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "221", "mean": "105", "stdev": "50" }, { "name": "Eta_FL", "index": "46", "type": "numeric", "distinct": "310", "missing": "0", "min": "2", "max": "13", "mean": "7", "stdev": "2" }, { "name": "X2Av", "index": "47", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "48", "type": "numeric", "distinct": "245", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "GATS2p", "index": "49", "type": "numeric", "distinct": "240", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X3Av", "index": "50", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "51", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "HNar", "index": "52", "type": "numeric", "distinct": "119", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "TPSA.NO.", "index": "53", "type": "numeric", "distinct": "111", "missing": "0", "min": "12", "max": "150", "mean": "78", "stdev": "20" }, { "name": "CATS2D_03_DL", "index": "54", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "GATS2i", "index": "55", "type": "numeric", "distinct": "241", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PHI", "index": "56", "type": "numeric", "distinct": "277", "missing": "0", "min": "3", "max": "13", "mean": "7", "stdev": "2" }, { "name": "nRCONR2", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.060", "index": "58", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig03_AEA.bo.", "index": "59", "type": "numeric", "distinct": "199", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piPC03", "index": "60", "type": "numeric", "distinct": "214", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "61", "type": "numeric", "distinct": "197", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "62", "type": "numeric", "distinct": "197", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS1v", "index": "63", "type": "numeric", "distinct": "210", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "TIE", "index": "64", "type": "numeric", "distinct": "371", "missing": "0", "min": "12", "max": "204", "mean": "75", "stdev": "30" }, { "name": "P_VSA_m_2", "index": "65", "type": "numeric", "distinct": "300", "missing": "0", "min": "43", "max": "282", "mean": "154", "stdev": "49" }, { "name": "CATS2D_04_DL", "index": "66", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "3" } ], "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 }