{ "data_id": "39319", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2649", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2649", "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: CHEMBL2649 (TID: 10575), and it has 167 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": "2016-07-16 07:29:57", "update_comment": null, "last_update": "2016-07-16 07:29:57", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3670514\/data_52297.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2649", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2649 (TID: 10575), and it has 167 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": 167, "NumberOfFeatures": 63, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 62, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3772455089820359, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9224789720706319, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.20935496412219698, "Quartile2MeansOfNumericAtts": 2.8060778443113774, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.536211069784112, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.6894754387991671, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2661680356516911, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4990654834214906, "MaxKurtosisOfNumericAtts": 44.18289597833967, "MinMeansOfNumericAtts": 0.010191616766467071, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 70.6989760479042, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.4654372380749336, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4126984126984, "Quartile3MeansOfNumericAtts": 6.130011976047904, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -6.4661692849528025, "PercentageOfSymbolicFeatures": 1.5873015873015872, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.324339553585958, "MinStdDevOfNumericAtts": 0.014166237115275338, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.162659656162295, "MaxStdDevOfNumericAtts": 37.965809465371194, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.1545352771429963, "Quartile3StdDevOfNumericAtts": 1.4821620371933624, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9713263473053892, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.4598460282149404, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.6279154915974505, "Quartile1SkewnessOfNumericAtts": -1.3132731112480764, "AutoCorrelation": 0.5246385542168674, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2206368648110486 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "62", "type": "numeric", "distinct": "39", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "167", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NNRS", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Rbrid", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "RCI", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "4", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GGI10", "index": "5", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCrs", "index": "6", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "SaasC", "index": "7", "type": "numeric", "distinct": "151", "missing": "0", "min": "-1", "max": "11", "mean": "4", "stdev": "2" }, { "name": "SpMax2_Bh.m.", "index": "8", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "AAC", "index": "9", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "10", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_LL", "index": "11", "type": "numeric", "distinct": "21", "missing": "0", "min": "1", "max": "26", "mean": "8", "stdev": "5" }, { "name": "MATS2m", "index": "12", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "BIC5", "index": "13", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "14", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "3" }, { "name": "D.Dtr09", "index": "15", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "164", "mean": "15", "stdev": "36" }, { "name": "nR09", "index": "16", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCIR", "index": "17", "type": "numeric", "distinct": "7", "missing": "0", "min": "2", "max": "8", "mean": "3", "stdev": "1" }, { "name": "CATS2D_03_DL", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "CATS2D_04_DL", "index": "19", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "GATS1p", "index": "20", "type": "numeric", "distinct": "94", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IDDE", "index": "21", "type": "numeric", "distinct": "74", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "PDI", "index": "22", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "23", "type": "numeric", "distinct": "87", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ATS2s", "index": "24", "type": "numeric", "distinct": "122", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATSC3e", "index": "25", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_5", "index": "26", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "46", "mean": "3", "stdev": "8" }, { "name": "ATSC3s", "index": "27", "type": "numeric", "distinct": "143", "missing": "0", "min": "12", "max": "173", "mean": "71", "stdev": "38" }, { "name": "piPC02", "index": "28", "type": "numeric", "distinct": "50", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "29", "type": "numeric", "distinct": "50", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig11_AEA.bo.", "index": "30", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "PW5", "index": "31", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig11_EA.bo.", "index": "32", "type": "numeric", "distinct": "47", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS8s", "index": "33", "type": "numeric", "distinct": "137", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SRW09", "index": "34", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Psi_e_A", "index": "35", "type": "numeric", "distinct": "106", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "36", "type": "numeric", "distinct": "106", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpAD_EA.bo.", "index": "37", "type": "numeric", "distinct": "122", "missing": "0", "min": "30", "max": "76", "mean": "60", "stdev": "12" }, { "name": "PW4", "index": "38", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "39", "type": "numeric", "distinct": "88", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "C.001", "index": "40", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X2", "index": "41", "type": "numeric", "distinct": "98", "missing": "0", "min": "6", "max": "16", "mean": "12", "stdev": "3" }, { "name": "GNar", "index": "42", "type": "numeric", "distinct": "50", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0A", "index": "43", "type": "numeric", "distinct": "40", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_F", "index": "44", "type": "numeric", "distinct": "153", "missing": "0", "min": "9", "max": "43", "mean": "29", "stdev": "9" }, { "name": "ON0", "index": "45", "type": "numeric", "distinct": "58", "missing": "0", "min": "7", "max": "20", "mean": "15", "stdev": "4" }, { "name": "ATS3s", "index": "46", "type": "numeric", "distinct": "132", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "47", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig09_EA.bo.", "index": "48", "type": "numeric", "distinct": "67", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATSC7e", "index": "49", "type": "numeric", "distinct": "140", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS4s", "index": "50", "type": "numeric", "distinct": "142", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "X0", "index": "51", "type": "numeric", "distinct": "60", "missing": "0", "min": "10", "max": "27", "mean": "20", "stdev": "4" }, { "name": "CATS2D_05_AA", "index": "52", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "53", "type": "numeric", "distinct": "68", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "1" }, { "name": "nS..O.2", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.p.", "index": "55", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "56", "type": "numeric", "distinct": "110", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATSC5e", "index": "57", "type": "numeric", "distinct": "138", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.bo.", "index": "58", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "S1K", "index": "59", "type": "numeric", "distinct": "107", "missing": "0", "min": "9", "max": "30", "mean": "20", "stdev": "5" }, { "name": "nCIC", "index": "60", "type": "numeric", "distinct": "5", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "TRS", "index": "61", "type": "numeric", "distinct": "10", "missing": "0", "min": "10", "max": "33", "mean": "18", "stdev": "4" } ], "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 }