{ "data_id": "38604", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4188", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4188", "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: CHEMBL4188 (TID: 100063), and it has 149 rows and 65 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 04:49:08", "update_comment": null, "last_update": "2016-07-16 04:49:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3646287\/data_52884.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4188", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4188 (TID: 100063), and it has 149 rows and 65 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": 149, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 16.9380870068046, "MinMeansOfNumericAtts": -0.009221476510067094, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.7613770269670717, "MaxMeansOfNumericAtts": 149.95688590604024, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 5.942196308724832, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8647531771570869, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 0.623291304081909, "MaxSkewnessOfNumericAtts": 4.325608733830094, "MinStdDevOfNumericAtts": 0.016128488820766018, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.634060389908175, "MaxStdDevOfNumericAtts": 139.62214020959684, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5461034890748516, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0440285234899327, "MeanKurtosisOfNumericAtts": 1.2478622113668978, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 14.605080841976815, "Quartile1SkewnessOfNumericAtts": -0.8774959113456897, "AutoCorrelation": 0.26210810810810853, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.36833605732929126, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.44966442953020136, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.347189371908065, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.02998798277505487, "Quartile2MeansOfNumericAtts": 3.5412583892617446, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.382263097445009, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.10024321133115713, "Quartile2StdDevOfNumericAtts": 0.7987217792184458, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8426181378405575, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "85", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "149", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_s_6", "index": "1", "type": "numeric", "distinct": "53", "missing": "0", "min": "22", "max": "360", "mean": "150", "stdev": "66" }, { "name": "SIC5", "index": "2", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC2m", "index": "3", "type": "numeric", "distinct": "113", "missing": "0", "min": "5", "max": "49", "mean": "24", "stdev": "11" }, { "name": "GATS1v", "index": "4", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SPI", "index": "5", "type": "numeric", "distinct": "108", "missing": "0", "min": "4", "max": "50", "mean": "20", "stdev": "10" }, { "name": "JGI3", "index": "6", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "7", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "8", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "BAC", "index": "9", "type": "numeric", "distinct": "58", "missing": "0", "min": "2", "max": "440", "mean": "75", "stdev": "90" }, { "name": "TPSA.Tot.", "index": "10", "type": "numeric", "distinct": "54", "missing": "0", "min": "57", "max": "327", "mean": "124", "stdev": "54" }, { "name": "nRCONR2", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MATS4m", "index": "12", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nHAcc", "index": "13", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "20", "mean": "8", "stdev": "4" }, { "name": "GGI3", "index": "14", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpMax4_Bh.s.", "index": "15", "type": "numeric", "distinct": "80", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "1" }, { "name": "MATS2v", "index": "16", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC7e", "index": "17", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig04_EA.dm.", "index": "18", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig05_EA.dm.", "index": "19", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "20", "type": "numeric", "distinct": "119", "missing": "0", "min": "9", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "21", "type": "numeric", "distinct": "118", "missing": "0", "min": "10", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "22", "type": "numeric", "distinct": "120", "missing": "0", "min": "11", "max": "20", "mean": "17", "stdev": "1" }, { "name": "TIE", "index": "23", "type": "numeric", "distinct": "125", "missing": "0", "min": "14", "max": "765", "mean": "126", "stdev": "140" }, { "name": "Eig04_AEA.dm.", "index": "24", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "C.007", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS1v", "index": "26", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nAziridines", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SRW05", "index": "28", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "SRW07", "index": "29", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "3" }, { "name": "P_VSA_m_3", "index": "30", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "294", "mean": "100", "stdev": "79" }, { "name": "SM03_EA.ri.", "index": "31", "type": "numeric", "distinct": "80", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SRW09", "index": "32", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "9", "mean": "5", "stdev": "4" }, { "name": "ATSC5e", "index": "33", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "34", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eta_B", "index": "35", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SsssN", "index": "36", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_AA", "index": "37", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "CATS2D_05_AA", "index": "38", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "5" }, { "name": "Eig07_AEA.dm.", "index": "39", "type": "numeric", "distinct": "89", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GATS1p", "index": "40", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "41", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "PW3", "index": "42", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "43", "type": "numeric", "distinct": "94", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA", "index": "44", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "45", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM03_EA", "index": "46", "type": "numeric", "distinct": "20", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SpMin6_Bh.p.", "index": "47", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "48", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig03_AEA.dm.", "index": "49", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "AAC", "index": "50", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AECC", "index": "51", "type": "numeric", "distinct": "101", "missing": "0", "min": "4", "max": "23", "mean": "13", "stdev": "4" }, { "name": "ALOGP", "index": "52", "type": "numeric", "distinct": "113", "missing": "0", "min": "-1", "max": "7", "mean": "3", "stdev": "2" }, { "name": "ALOGP2", "index": "53", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "50", "mean": "15", "stdev": "11" }, { "name": "AMR", "index": "54", "type": "numeric", "distinct": "114", "missing": "0", "min": "47", "max": "225", "mean": "128", "stdev": "39" }, { "name": "AMW", "index": "55", "type": "numeric", "distinct": "104", "missing": "0", "min": "6", "max": "12", "mean": "8", "stdev": "1" }, { "name": "ARR", "index": "56", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS1e", "index": "57", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "58", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "59", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1p", "index": "60", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1s", "index": "61", "type": "numeric", "distinct": "110", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS1v", "index": "62", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2e", "index": "63", "type": "numeric", "distinct": "105", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS2i", "index": "64", "type": "numeric", "distinct": "100", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS2m", "index": "65", "type": "numeric", "distinct": "108", "missing": "0", "min": "3", "max": "5", "mean": "4", "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 }