{ "data_id": "33946", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1926", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1926", "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: CHEMBL1926 (TID: 10460), and it has 580 rows and 67 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 14:05:46", "update_comment": null, "last_update": "2016-07-15 14:05:46", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3517792\/data_53219.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-CHEMBL1926", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1926 (TID: 10460), and it has 580 rows and 67 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": 580, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 3.089726724113746, "MinStdDevOfNumericAtts": 0.04318667301498541, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.4870968411224665, "MaxStdDevOfNumericAtts": 70.32565178781184, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.04004870633206559, "Quartile3StdDevOfNumericAtts": 0.9807223098375473, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.3300323275862067, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.092764275498097, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 9.313549112576066, "Quartile1SkewnessOfNumericAtts": -0.107986659496218, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.14672282585300317, "AutoCorrelation": -0.1125526770293602, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.7449613703303777, "Dimensionality": 0.11896551724137931, "MeanSkewnessOfNumericAtts": 0.6186576889918134, "Quartile2MeansOfNumericAtts": 2.6284853448275864, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.424831147259828, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3725358345214167, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2063861350736966, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.2759171189361075, "MaxKurtosisOfNumericAtts": 16.80899305915013, "MinMeansOfNumericAtts": 0.08275862068965524, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 214.88316379310345, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.0676691384136445, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 3.8969349137931033, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.1423803468223097, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "360", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "580", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.043", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SRW09", "index": "2", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "3" }, { "name": "SpMin1_Bh.v.", "index": "3", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "4", "type": "numeric", "distinct": "165", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "D.Dtr09", "index": "5", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "271", "mean": "18", "stdev": "41" }, { "name": "SpMin1_Bh.i.", "index": "6", "type": "numeric", "distinct": "148", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "7", "type": "numeric", "distinct": "136", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nR09", "index": "8", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "SRW07", "index": "9", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "SpMin2_Bh.s.", "index": "10", "type": "numeric", "distinct": "215", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nR05", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SRW05", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nArNR2", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "14", "type": "numeric", "distinct": "202", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig03_AEA.bo.", "index": "15", "type": "numeric", "distinct": "291", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "DECC", "index": "16", "type": "numeric", "distinct": "268", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "17", "type": "numeric", "distinct": "259", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_LL", "index": "18", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "D.Dtr06", "index": "19", "type": "numeric", "distinct": "386", "missing": "0", "min": "58", "max": "752", "mean": "208", "stdev": "70" }, { "name": "Eig05_AEA.bo.", "index": "20", "type": "numeric", "distinct": "216", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "21", "type": "numeric", "distinct": "275", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NaaNH", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaNH", "index": "23", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMax5_Bh.v.", "index": "24", "type": "numeric", "distinct": "290", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM03_EA.dm.", "index": "25", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "26", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "SM07_EA.dm.", "index": "27", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "28", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "3" }, { "name": "SM11_EA.dm.", "index": "29", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "4" }, { "name": "SM13_EA.dm.", "index": "30", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "4" }, { "name": "SM15_EA.dm.", "index": "31", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "21", "mean": "2", "stdev": "5" }, { "name": "SpMax5_Bh.p.", "index": "32", "type": "numeric", "distinct": "280", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "33", "type": "numeric", "distinct": "302", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "N.071", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC4i", "index": "35", "type": "numeric", "distinct": "433", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "36", "type": "numeric", "distinct": "178", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.s.", "index": "37", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ICR", "index": "38", "type": "numeric", "distinct": "229", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "39", "type": "numeric", "distinct": "281", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax6_Bh.p.", "index": "40", "type": "numeric", "distinct": "287", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS4p", "index": "41", "type": "numeric", "distinct": "420", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_04_DD", "index": "42", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "43", "type": "numeric", "distinct": "105", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "44", "type": "numeric", "distinct": "105", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "45", "type": "numeric", "distinct": "106", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "46", "type": "numeric", "distinct": "105", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TIC4", "index": "47", "type": "numeric", "distinct": "371", "missing": "0", "min": "93", "max": "574", "mean": "215", "stdev": "49" }, { "name": "SpMax3_Bh.i.", "index": "48", "type": "numeric", "distinct": "271", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC5i", "index": "49", "type": "numeric", "distinct": "461", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig03_EA", "index": "50", "type": "numeric", "distinct": "273", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "51", "type": "numeric", "distinct": "273", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS4e", "index": "52", "type": "numeric", "distinct": "417", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "53", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CIC0", "index": "54", "type": "numeric", "distinct": "303", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax6_Bh.m.", "index": "55", "type": "numeric", "distinct": "253", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nCsp2", "index": "56", "type": "numeric", "distinct": "17", "missing": "0", "min": "4", "max": "27", "mean": "13", "stdev": "3" }, { "name": "ATS4v", "index": "57", "type": "numeric", "distinct": "406", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3p", "index": "58", "type": "numeric", "distinct": "363", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "D.Dtr05", "index": "59", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "138", "mean": "11", "stdev": "23" }, { "name": "ATS5i", "index": "60", "type": "numeric", "distinct": "430", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3v", "index": "61", "type": "numeric", "distinct": "370", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "62", "type": "numeric", "distinct": "292", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig12_AEA.ed.", "index": "63", "type": "numeric", "distinct": "282", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "0" }, { "name": "ATS5e", "index": "64", "type": "numeric", "distinct": "434", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig03_EA.ed.", "index": "65", "type": "numeric", "distinct": "342", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "66", "type": "numeric", "distinct": "342", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "67", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" } ], "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 }