{ "data_id": "32649", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3235", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3235", "version": 8, "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: CHEMBL3235 (TID: 11787), and it has 38 rows and 61 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 10:45:50", "update_comment": null, "last_update": "2016-07-15 10:45:50", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3486393\/data_52249.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-CHEMBL3235", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3235 (TID: 11787), and it has 38 rows and 61 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": 38, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.2711549463867537, "MinStdDevOfNumericAtts": 0.053917202473954026, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": -0.20542896400288863, "MaxStdDevOfNumericAtts": 47.534031955015415, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.2863297517089838, "Quartile3StdDevOfNumericAtts": 2.8600740373788858, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.395625, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.8171234395067681, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 21.91618039049236, "Quartile1SkewnessOfNumericAtts": -0.6420487153241632, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.18318711361878415, "AutoCorrelation": -0.1720810810810812, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.8996916604394452, "Dimensionality": 1.6578947368421053, "MeanSkewnessOfNumericAtts": -0.3618083236275361, "Quartile2MeansOfNumericAtts": 7.673986842105263, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.104389162344689, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.349436900078132, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.703244941994118, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5048399472057429, "MaxKurtosisOfNumericAtts": 1.7234821657101493, "MinMeansOfNumericAtts": 0.004447368421052636, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 178.41121052631578, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.5877587483360751, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 16.53407236842105, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.9752378035712678, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "33", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "38", "missing": "0", "identifier": "1", "distr": [] }, { "name": "BAC", "index": "1", "type": "numeric", "distinct": "21", "missing": "0", "min": "37", "max": "124", "mean": "78", "stdev": "24" }, { "name": "DBI", "index": "2", "type": "numeric", "distinct": "19", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "TIE", "index": "3", "type": "numeric", "distinct": "37", "missing": "0", "min": "63", "max": "229", "mean": "120", "stdev": "41" }, { "name": "ATSC6m", "index": "4", "type": "numeric", "distinct": "37", "missing": "0", "min": "22", "max": "84", "mean": "41", "stdev": "13" }, { "name": "SPI", "index": "5", "type": "numeric", "distinct": "34", "missing": "0", "min": "16", "max": "27", "mean": "21", "stdev": "3" }, { "name": "Eig01_AEA.ed.", "index": "6", "type": "numeric", "distinct": "19", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig01_EA", "index": "7", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "8", "type": "numeric", "distinct": "25", "missing": "0", "min": "9", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SM09_AEA.bo.", "index": "9", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "10", "type": "numeric", "distinct": "25", "missing": "0", "min": "9", "max": "13", "mean": "11", "stdev": "1" }, { "name": "SpDiam_EA", "index": "11", "type": "numeric", "distinct": "25", "missing": "0", "min": "5", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "12", "type": "numeric", "distinct": "19", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA", "index": "13", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "14", "type": "numeric", "distinct": "25", "missing": "0", "min": "9", "max": "13", "mean": "11", "stdev": "1" }, { "name": "ATS5s", "index": "15", "type": "numeric", "distinct": "35", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "16", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5e", "index": "17", "type": "numeric", "distinct": "37", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GGI3", "index": "18", "type": "numeric", "distinct": "27", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SM07_EA.ri.", "index": "19", "type": "numeric", "distinct": "31", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "SM09_EA.ri.", "index": "20", "type": "numeric", "distinct": "33", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "SM10_EA.ri.", "index": "21", "type": "numeric", "distinct": "37", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "22", "type": "numeric", "distinct": "37", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "23", "type": "numeric", "distinct": "36", "missing": "0", "min": "13", "max": "15", "mean": "14", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "24", "type": "numeric", "distinct": "37", "missing": "0", "min": "14", "max": "16", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "25", "type": "numeric", "distinct": "37", "missing": "0", "min": "15", "max": "17", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "26", "type": "numeric", "distinct": "35", "missing": "0", "min": "16", "max": "18", "mean": "17", "stdev": "1" }, { "name": "ATSC2s", "index": "27", "type": "numeric", "distinct": "34", "missing": "0", "min": "41", "max": "131", "mean": "95", "stdev": "33" }, { "name": "ATSC5m", "index": "28", "type": "numeric", "distinct": "37", "missing": "0", "min": "29", "max": "67", "mean": "48", "stdev": "12" }, { "name": "ATSC5s", "index": "29", "type": "numeric", "distinct": "37", "missing": "0", "min": "91", "max": "259", "mean": "178", "stdev": "48" }, { "name": "ATSC4m", "index": "30", "type": "numeric", "distinct": "34", "missing": "0", "min": "29", "max": "64", "mean": "45", "stdev": "10" }, { "name": "ATS4s", "index": "31", "type": "numeric", "distinct": "37", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS6s", "index": "32", "type": "numeric", "distinct": "36", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "X3v", "index": "33", "type": "numeric", "distinct": "37", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "2" }, { "name": "ATSC8s", "index": "34", "type": "numeric", "distinct": "37", "missing": "0", "min": "47", "max": "205", "mean": "132", "stdev": "45" }, { "name": "SpMax8_Bh.e.", "index": "35", "type": "numeric", "distinct": "36", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "36", "type": "numeric", "distinct": "33", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "37", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.v.", "index": "38", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS3s", "index": "39", "type": "numeric", "distinct": "34", "missing": "0", "min": "6", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATSC7m", "index": "40", "type": "numeric", "distinct": "37", "missing": "0", "min": "20", "max": "52", "mean": "36", "stdev": "10" }, { "name": "ATSC8e", "index": "41", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DELS", "index": "42", "type": "numeric", "distinct": "37", "missing": "0", "min": "33", "max": "73", "mean": "57", "stdev": "13" }, { "name": "IC3", "index": "43", "type": "numeric", "distinct": "29", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MATS5m", "index": "44", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Psi_i_s", "index": "45", "type": "numeric", "distinct": "31", "missing": "0", "min": "59", "max": "104", "mean": "83", "stdev": "14" }, { "name": "GGI5", "index": "46", "type": "numeric", "distinct": "29", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MAXDP", "index": "47", "type": "numeric", "distinct": "37", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.", "index": "48", "type": "numeric", "distinct": "21", "missing": "0", "min": "28", "max": "38", "mean": "33", "stdev": "3" }, { "name": "Eig01_EA.ri.", "index": "49", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "50", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATSC3p", "index": "51", "type": "numeric", "distinct": "33", "missing": "0", "min": "8", "max": "17", "mean": "12", "stdev": "3" }, { "name": "ATSC4p", "index": "52", "type": "numeric", "distinct": "34", "missing": "0", "min": "8", "max": "18", "mean": "12", "stdev": "3" }, { "name": "P_VSA_s_3", "index": "53", "type": "numeric", "distinct": "27", "missing": "0", "min": "18", "max": "66", "mean": "39", "stdev": "14" }, { "name": "ATS3v", "index": "54", "type": "numeric", "distinct": "32", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS7s", "index": "55", "type": "numeric", "distinct": "36", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS8s", "index": "56", "type": "numeric", "distinct": "37", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "BID", "index": "57", "type": "numeric", "distinct": "23", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Chi1_AEA.bo.", "index": "58", "type": "numeric", "distinct": "30", "missing": "0", "min": "11", "max": "22", "mean": "16", "stdev": "3" }, { "name": "Chi1_AEA.dm.", "index": "59", "type": "numeric", "distinct": "30", "missing": "0", "min": "11", "max": "22", "mean": "16", "stdev": "3" }, { "name": "Chi1_AEA.ed.", "index": "60", "type": "numeric", "distinct": "30", "missing": "0", "min": "11", "max": "22", "mean": "16", "stdev": "3" }, { "name": "Chi1_AEA.ri.", "index": "61", "type": "numeric", "distinct": "30", "missing": "0", "min": "11", "max": "22", "mean": "16", "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 }