{ "data_id": "31335", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4644", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4644", "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: CHEMBL4644 (TID: 11003), and it has 866 rows and 68 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 07:18:35", "update_comment": null, "last_update": "2016-07-15 07:18:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3445909\/data_53385.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-CHEMBL4644", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4644 (TID: 11003), and it has 866 rows and 68 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": 866, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 3.7349073244149977, "MinStdDevOfNumericAtts": 0.0011901360962927507, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.5220652374425407, "MaxStdDevOfNumericAtts": 1060.9504583509504, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.18006520001380188, "Quartile3StdDevOfNumericAtts": 3.3555539625431665, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9939884526558891, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.4661383569514854, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 71.41333726612446, "Quartile1SkewnessOfNumericAtts": -0.3157547261836724, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.24317892210551645, "AutoCorrelation": 0.07883352601156007, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8783275655062042, "Dimensionality": 0.08083140877598152, "MeanSkewnessOfNumericAtts": 0.5833850026941736, "Quartile2MeansOfNumericAtts": 3.353379907621247, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 43.76121244884378, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.39227344028360317, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5896950130204002, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5123934089962262, "MaxKurtosisOfNumericAtts": 17.17043978392806, "MinMeansOfNumericAtts": 0.006329099307159352, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 1033.4780138568128, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.4091666506824008, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 9.890983256351035, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.2205155652780453, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "489", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "866", "missing": "0", "identifier": "1", "distr": [] }, { "name": "JGI5", "index": "1", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "2", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "HNar", "index": "3", "type": "numeric", "distinct": "233", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "4", "type": "numeric", "distinct": "388", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "5", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "X0A", "index": "6", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI6", "index": "7", "type": "numeric", "distinct": "506", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "8", "type": "numeric", "distinct": "383", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig06_EA.dm.", "index": "9", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "10", "type": "numeric", "distinct": "242", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "NdO", "index": "11", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "5", "stdev": "4" }, { "name": "O.058", "index": "12", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "5", "stdev": "4" }, { "name": "ON0", "index": "13", "type": "numeric", "distinct": "274", "missing": "0", "min": "8", "max": "107", "mean": "28", "stdev": "14" }, { "name": "Psi_i_s", "index": "14", "type": "numeric", "distinct": "619", "missing": "0", "min": "32", "max": "525", "mean": "128", "stdev": "70" }, { "name": "SM04_EA.dm.", "index": "15", "type": "numeric", "distinct": "339", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "16", "type": "numeric", "distinct": "324", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "17", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "10", "mean": "5", "stdev": "1" }, { "name": "ZM2MulPer", "index": "18", "type": "numeric", "distinct": "761", "missing": "0", "min": "171", "max": "2596", "mean": "715", "stdev": "351" }, { "name": "ZM2Per", "index": "19", "type": "numeric", "distinct": "758", "missing": "0", "min": "246", "max": "3746", "mean": "1033", "stdev": "504" }, { "name": "PCR", "index": "20", "type": "numeric", "distinct": "270", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2s", "index": "21", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ZM2V", "index": "22", "type": "numeric", "distinct": "491", "missing": "0", "min": "162", "max": "2439", "mean": "672", "stdev": "330" }, { "name": "DELS", "index": "23", "type": "numeric", "distinct": "783", "missing": "0", "min": "7", "max": "480", "mean": "82", "stdev": "66" }, { "name": "SM11_EA.ed.", "index": "24", "type": "numeric", "distinct": "528", "missing": "0", "min": "23", "max": "31", "mean": "27", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "25", "type": "numeric", "distinct": "514", "missing": "0", "min": "27", "max": "37", "mean": "32", "stdev": "1" }, { "name": "CATS2D_05_AL", "index": "26", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "11", "stdev": "4" }, { "name": "ZM1Kup", "index": "27", "type": "numeric", "distinct": "708", "missing": "0", "min": "156", "max": "3272", "mean": "794", "stdev": "439" }, { "name": "Eta_B", "index": "28", "type": "numeric", "distinct": "360", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "JGI10", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA.dm.", "index": "30", "type": "numeric", "distinct": "345", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_DD", "index": "31", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "3" }, { "name": "SpMax6_Bh.m.", "index": "32", "type": "numeric", "distinct": "421", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS5s", "index": "33", "type": "numeric", "distinct": "318", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS2s", "index": "34", "type": "numeric", "distinct": "597", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "AAC", "index": "35", "type": "numeric", "distinct": "338", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "36", "type": "numeric", "distinct": "338", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Me", "index": "37", "type": "numeric", "distinct": "48", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig11_EA.dm.", "index": "38", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig06_AEA.ri.", "index": "39", "type": "numeric", "distinct": "466", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CMC.80", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_epsi", "index": "41", "type": "numeric", "distinct": "637", "missing": "0", "min": "17", "max": "225", "mean": "60", "stdev": "29" }, { "name": "ATS1s", "index": "42", "type": "numeric", "distinct": "575", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC6m", "index": "43", "type": "numeric", "distinct": "778", "missing": "0", "min": "12", "max": "308", "mean": "82", "stdev": "43" }, { "name": "SpMax7_Bh.m.", "index": "44", "type": "numeric", "distinct": "435", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "PDI", "index": "45", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "46", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "41", "mean": "9", "stdev": "7" }, { "name": "Infective.80", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_DL", "index": "48", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "46", "mean": "11", "stdev": "10" }, { "name": "MATS3i", "index": "49", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "50", "type": "numeric", "distinct": "361", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "51", "type": "numeric", "distinct": "361", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ECC", "index": "52", "type": "numeric", "distinct": "497", "missing": "0", "min": "136", "max": "9537", "mean": "999", "stdev": "1061" }, { "name": "ATSC5m", "index": "53", "type": "numeric", "distinct": "778", "missing": "0", "min": "14", "max": "279", "mean": "76", "stdev": "38" }, { "name": "Eig07_EA.dm.", "index": "54", "type": "numeric", "distinct": "121", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "GNar", "index": "55", "type": "numeric", "distinct": "205", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig12_EA.dm.", "index": "56", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpAD_EA.dm.", "index": "57", "type": "numeric", "distinct": "367", "missing": "0", "min": "1", "max": "134", "mean": "23", "stdev": "19" }, { "name": "ATS5e", "index": "58", "type": "numeric", "distinct": "612", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig04_EA", "index": "59", "type": "numeric", "distinct": "370", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "60", "type": "numeric", "distinct": "370", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Psychotic.80", "index": "61", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "62", "type": "numeric", "distinct": "404", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM07_EA", "index": "63", "type": "numeric", "distinct": "453", "missing": "0", "min": "7", "max": "10", "mean": "9", "stdev": "0" }, { "name": "DLS_01", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "65", "type": "numeric", "distinct": "401", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS5i", "index": "66", "type": "numeric", "distinct": "585", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM09_AEA.ed.", "index": "67", "type": "numeric", "distinct": "539", "missing": "0", "min": "16", "max": "20", "mean": "18", "stdev": "1" }, { "name": "IDDE", "index": "68", "type": "numeric", "distinct": "469", "missing": "0", "min": "3", "max": "7", "mean": "5", "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 }