{ "data_id": "27008", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2568", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2568", "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: CHEMBL2568 (TID: 11442), and it has 517 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": "2016-07-14 20:34:35", "update_comment": null, "last_update": "2016-07-14 20:34:35", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3318833\/data_53242.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-CHEMBL2568", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2568 (TID: 11442), and it has 517 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": 517, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 7.023651802915434, "MinStdDevOfNumericAtts": 0.005565737499523687, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8374441610267891, "MaxStdDevOfNumericAtts": 33.33951894305095, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.10071006966207974, "Quartile3StdDevOfNumericAtts": 0.44530172573353344, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.43845793036750486, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 7.25821221800852, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 3.977274405506883, "Quartile1SkewnessOfNumericAtts": -0.8795677797475203, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.06756144407200085, "AutoCorrelation": 0.1543178294573639, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.7643488816306214, "Dimensionality": 0.13346228239845262, "MeanSkewnessOfNumericAtts": -0.2501620813716438, "Quartile2MeansOfNumericAtts": 2.0064555125725336, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.4985366522466406, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.09479456257181589, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8825765842885944, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.16542455434349537, "MaxKurtosisOfNumericAtts": 60.30430928431456, "MinMeansOfNumericAtts": 0.03854738878143134, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 37.364187620889744, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 7.204144649344725, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 4.207641199226305, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.450652547689361, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "307", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "517", "missing": "0", "identifier": "1", "distr": [] }, { "name": "X4A", "index": "1", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW5", "index": "2", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5A", "index": "3", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3A", "index": "4", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.bo.", "index": "5", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "6", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "68", "mean": "11", "stdev": "14" }, { "name": "RCI", "index": "7", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "8", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.ri.", "index": "9", "type": "numeric", "distinct": "124", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "D.Dtr08", "index": "10", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "146", "mean": "12", "stdev": "33" }, { "name": "Eig05_AEA.ed.", "index": "11", "type": "numeric", "distinct": "246", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMAD_EA.ed.", "index": "12", "type": "numeric", "distinct": "291", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "13", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "C.035", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Cl.090", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Rbrid", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nR08", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_sh_y", "index": "19", "type": "numeric", "distinct": "155", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCIR", "index": "20", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SaaS", "index": "21", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "22", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "23", "type": "numeric", "distinct": "148", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.v.", "index": "24", "type": "numeric", "distinct": "170", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nThiophenes", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SRW09", "index": "26", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "4" }, { "name": "SpMax1_Bh.s.", "index": "27", "type": "numeric", "distinct": "36", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "NNRS", "index": "28", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "DECC", "index": "29", "type": "numeric", "distinct": "262", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SRW07", "index": "30", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "GATS4m", "index": "31", "type": "numeric", "distinct": "291", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MPC06", "index": "32", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig02_AEA.ri.", "index": "33", "type": "numeric", "distinct": "231", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS6m", "index": "34", "type": "numeric", "distinct": "281", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "35", "type": "numeric", "distinct": "176", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.041", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "37", "type": "numeric", "distinct": "205", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "38", "type": "numeric", "distinct": "99", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "39", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC1", "index": "40", "type": "numeric", "distinct": "316", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "41", "type": "numeric", "distinct": "146", "missing": "0", "min": "4", "max": "11", "mean": "4", "stdev": "1" }, { "name": "SpMin1_Bh.p.", "index": "42", "type": "numeric", "distinct": "121", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MWC10", "index": "43", "type": "numeric", "distinct": "299", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "0" }, { "name": "NaaS", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "45", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "97", "mean": "37", "stdev": "18" }, { "name": "SpMin1_Bh.v.", "index": "46", "type": "numeric", "distinct": "116", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig02_EA.ri.", "index": "47", "type": "numeric", "distinct": "220", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig02_EA", "index": "48", "type": "numeric", "distinct": "200", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.bo.", "index": "49", "type": "numeric", "distinct": "200", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SIC1", "index": "50", "type": "numeric", "distinct": "195", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_AEA.ed.", "index": "51", "type": "numeric", "distinct": "165", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "JGI3", "index": "52", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCONN", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMAD_EA", "index": "54", "type": "numeric", "distinct": "111", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MPC07", "index": "55", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS3m", "index": "56", "type": "numeric", "distinct": "281", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X2A", "index": "57", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2m", "index": "58", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_5", "index": "59", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "102", "mean": "31", "stdev": "15" }, { "name": "SpMAD_AEA.ed.", "index": "60", "type": "numeric", "distinct": "139", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM05_EA.bo.", "index": "61", "type": "numeric", "distinct": "237", "missing": "0", "min": "5", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "62", "type": "numeric", "distinct": "286", "missing": "0", "min": "10", "max": "14", "mean": "14", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "63", "type": "numeric", "distinct": "292", "missing": "0", "min": "11", "max": "16", "mean": "15", "stdev": "0" }, { "name": "Eig01_EA", "index": "64", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "65", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA", "index": "66", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CIC1", "index": "67", "type": "numeric", "distinct": "366", "missing": "0", "min": "1", "max": "3", "mean": "2", "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 }