{ "data_id": "29093", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3018", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3018", "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: CHEMBL3018 (TID: 12725), and it has 141 rows and 64 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 01:39:00", "update_comment": null, "last_update": "2016-07-15 01:39:00", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3382991\/data_52651.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3018", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3018 (TID: 12725), and it has 141 rows and 64 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": 141, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 71.10325600237499, "MinMeansOfNumericAtts": -3.056758865248227, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.0669867597805425, "MaxMeansOfNumericAtts": 22.82376595744681, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 7.0369361702127655, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.9035451847505644, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3SkewnessOfNumericAtts": -0.36288988928949273, "MaxSkewnessOfNumericAtts": 7.2785697907917335, "MinStdDevOfNumericAtts": 0.0016227236413544766, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 0.8067996902119994, "MaxStdDevOfNumericAtts": 9.656874965740808, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.5599104712524821, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.839854609929078, "MeanKurtosisOfNumericAtts": 3.9120559840662597, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.33978483360611, "Quartile1SkewnessOfNumericAtts": -1.780064607306619, "AutoCorrelation": -0.048421428571429156, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.08023244839434415, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.46808510638297873, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.0593341091795048, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.9737102551676801, "Quartile2MeansOfNumericAtts": 4.19436170212766, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.947934830378677, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -1.4025410660493465, "Quartile2StdDevOfNumericAtts": 0.39948615374178953, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8239970394891145, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "117", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "141", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM11_EA.bo.", "index": "1", "type": "numeric", "distinct": "81", "missing": "0", "min": "14", "max": "18", "mean": "17", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "2", "type": "numeric", "distinct": "86", "missing": "0", "min": "15", "max": "19", "mean": "18", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "3", "type": "numeric", "distinct": "85", "missing": "0", "min": "16", "max": "21", "mean": "20", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "4", "type": "numeric", "distinct": "82", "missing": "0", "min": "17", "max": "22", "mean": "21", "stdev": "1" }, { "name": "SsOH", "index": "5", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "42", "mean": "4", "stdev": "10" }, { "name": "SM10_EA.bo.", "index": "6", "type": "numeric", "distinct": "87", "missing": "0", "min": "13", "max": "16", "mean": "16", "stdev": "1" }, { "name": "JGI8", "index": "7", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NsOH", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "MAXDN", "index": "9", "type": "numeric", "distinct": "117", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SddssS", "index": "10", "type": "numeric", "distinct": "86", "missing": "0", "min": "-4", "max": "0", "mean": "-3", "stdev": "2" }, { "name": "SpMin2_Bh.i.", "index": "11", "type": "numeric", "distinct": "46", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "12", "type": "numeric", "distinct": "92", "missing": "0", "min": "11", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "13", "type": "numeric", "distinct": "88", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "1" }, { "name": "nROH", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "15", "type": "numeric", "distinct": "88", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "16", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "17", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "11", "mean": "5", "stdev": "1" }, { "name": "SpMin2_Bh.e.", "index": "18", "type": "numeric", "distinct": "44", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS1m", "index": "19", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "20", "type": "numeric", "distinct": "59", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_sh_x", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "N.067", "index": "22", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NddssS", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nSO2N", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "3" }, { "name": "S.110", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1e", "index": "27", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "O.057", "index": "28", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "BIC2", "index": "29", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "30", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "31", "type": "numeric", "distinct": "35", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "32", "type": "numeric", "distinct": "35", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "33", "type": "numeric", "distinct": "35", "missing": "0", "min": "6", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "34", "type": "numeric", "distinct": "35", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "35", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SssCH2", "index": "36", "type": "numeric", "distinct": "129", "missing": "0", "min": "-7", "max": "10", "mean": "3", "stdev": "3" }, { "name": "GATS8s", "index": "37", "type": "numeric", "distinct": "119", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "38", "type": "numeric", "distinct": "48", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "39", "type": "numeric", "distinct": "78", "missing": "0", "min": "18", "max": "24", "mean": "23", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "40", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "41", "type": "numeric", "distinct": "57", "missing": "0", "min": "5", "max": "7", "mean": "7", "stdev": "0" }, { "name": "MATS2i", "index": "42", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "43", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nN.C.N.", "index": "44", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SdNH", "index": "45", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "22", "mean": "8", "stdev": "5" }, { "name": "SpDiam_AEA.ri.", "index": "46", "type": "numeric", "distinct": "59", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "47", "type": "numeric", "distinct": "35", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "48", "type": "numeric", "distinct": "43", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "49", "type": "numeric", "distinct": "35", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "O.", "index": "50", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "10", "mean": "6", "stdev": "2" }, { "name": "SIC3", "index": "51", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "52", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig01_AEA.dm.", "index": "53", "type": "numeric", "distinct": "29", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.dm.", "index": "54", "type": "numeric", "distinct": "31", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "55", "type": "numeric", "distinct": "29", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CATS2D_09_LL", "index": "56", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "39", "mean": "17", "stdev": "8" }, { "name": "SpMax1_Bh.s.", "index": "57", "type": "numeric", "distinct": "16", "missing": "0", "min": "6", "max": "8", "mean": "8", "stdev": "0" }, { "name": "X5Av", "index": "58", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BIC3", "index": "59", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "60", "type": "numeric", "distinct": "24", "missing": "0", "min": "3", "max": "28", "mean": "17", "stdev": "7" }, { "name": "Eig01_AEA.ed.", "index": "61", "type": "numeric", "distinct": "28", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_AEA.ed.", "index": "62", "type": "numeric", "distinct": "28", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "C.006", "index": "63", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "GATS4m", "index": "64", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" } ], "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 }