{ "data_id": "26620", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3368", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3368", "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: CHEMBL3368 (TID: 12104), and it has 118 rows and 62 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": "2016-07-14 19:40:14", "update_comment": null, "last_update": "2016-07-14 19:40:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3307847\/data_52437.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3368", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3368 (TID: 12104), and it has 118 rows and 62 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": 118, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.542372881355932, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.09790032489857219, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.790593892924401, "Quartile1SkewnessOfNumericAtts": -0.8318945391952307, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11324016801102936, "AutoCorrelation": 0.13420512820512856, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.32079871716201414, "Dimensionality": 0.5423728813559322, "MeanSkewnessOfNumericAtts": -0.21771889114123874, "Quartile2MeansOfNumericAtts": 3.991525423728813, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 3.192107360219261, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.49423766170135375, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.44873699024318, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4609002659940589, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 6.018843011544158, "MinMeansOfNumericAtts": -0.08372881355932202, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 174.716406779661, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.17861819939863466, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 5.964669491525424, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.4696819045952607, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.71707157758374, "MinStdDevOfNumericAtts": 0.01070691626556018, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.34775594587243686, "MaxStdDevOfNumericAtts": 116.76145496953323, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.8614437168072295, "Quartile3StdDevOfNumericAtts": 1.7968698136053733 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "94", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "118", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax1_Bh.e.", "index": "1", "type": "numeric", "distinct": "56", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.017", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MPC10", "index": "3", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "nCconj", "index": "4", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "nR.Ct", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.ri.", "index": "6", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM06_EA.ri.", "index": "7", "type": "numeric", "distinct": "105", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "SM07_EA.ri.", "index": "8", "type": "numeric", "distinct": "99", "missing": "0", "min": "8", "max": "10", "mean": "10", "stdev": "1" }, { "name": "SM08_EA.ri.", "index": "9", "type": "numeric", "distinct": "102", "missing": "0", "min": "10", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SpDiam_AEA.ri.", "index": "10", "type": "numeric", "distinct": "85", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "C.016", "index": "11", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig01_EA.ri.", "index": "12", "type": "numeric", "distinct": "40", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nCIR", "index": "13", "type": "numeric", "distinct": "16", "missing": "0", "min": "3", "max": "19", "mean": "12", "stdev": "5" }, { "name": "NdsCH", "index": "14", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "nR.Cs", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "16", "type": "numeric", "distinct": "40", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "17", "type": "numeric", "distinct": "40", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "H.052", "index": "18", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "3" }, { "name": "P_VSA_MR_5", "index": "19", "type": "numeric", "distinct": "72", "missing": "0", "min": "7", "max": "79", "mean": "40", "stdev": "16" }, { "name": "MWC09", "index": "20", "type": "numeric", "distinct": "85", "missing": "0", "min": "11", "max": "12", "mean": "12", "stdev": "0" }, { "name": "TWC", "index": "21", "type": "numeric", "distinct": "86", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "22", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "SdsCH", "index": "23", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "nCrt", "index": "24", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "Rbrid", "index": "25", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "SpMax1_Bh.i.", "index": "26", "type": "numeric", "distinct": "47", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X2A", "index": "27", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "28", "type": "numeric", "distinct": "31", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS4v", "index": "29", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "D.Dtr10", "index": "30", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "458", "mean": "175", "stdev": "117" }, { "name": "SpMin1_Bh.i.", "index": "31", "type": "numeric", "distinct": "34", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "32", "type": "numeric", "distinct": "36", "missing": "0", "min": "3", "max": "39", "mean": "15", "stdev": "7" }, { "name": "X1A", "index": "33", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCt", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SpMAD_EA.ri.", "index": "35", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "36", "type": "numeric", "distinct": "28", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "37", "type": "numeric", "distinct": "33", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS4v", "index": "38", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "39", "type": "numeric", "distinct": "66", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "40", "type": "numeric", "distinct": "39", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "41", "type": "numeric", "distinct": "39", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MATS4i", "index": "42", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "43", "type": "numeric", "distinct": "59", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MWC08", "index": "44", "type": "numeric", "distinct": "85", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "C.002", "index": "45", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "3" }, { "name": "MATS1p", "index": "46", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM05_AEA.ed.", "index": "47", "type": "numeric", "distinct": "87", "missing": "0", "min": "11", "max": "12", "mean": "12", "stdev": "0" }, { "name": "MPC07", "index": "48", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "49", "type": "numeric", "distinct": "68", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "1" }, { "name": "BIC3", "index": "50", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.026", "index": "51", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "MATS1v", "index": "52", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBnz", "index": "53", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "PW5", "index": "54", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "S3K", "index": "55", "type": "numeric", "distinct": "112", "missing": "0", "min": "2", "max": "13", "mean": "4", "stdev": "2" }, { "name": "MPC05", "index": "56", "type": "numeric", "distinct": "65", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "nCrq", "index": "57", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nCs", "index": "58", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "6", "stdev": "3" }, { "name": "SRW07", "index": "59", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SRW09", "index": "60", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "3" }, { "name": "MATS1i", "index": "61", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_LL", "index": "62", "type": "numeric", "distinct": "25", "missing": "0", "min": "3", "max": "48", "mean": "23", "stdev": "9" } ], "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 }