{ "data_id": "39607", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5038", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5038", "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: CHEMBL5038 (TID: 20162), and it has 156 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": "2016-07-16 08:33:22", "update_comment": null, "last_update": "2016-07-16 08:33:22", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3678934\/data_52624.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5038", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5038 (TID: 20162), and it has 156 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": 156, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.4230769230769231, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 4.070744218114651, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 2.565839730729313, "Quartile2MeansOfNumericAtts": 3.6858974358974352, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 204.23407135254777, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.0219035592548917, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3641196541661875, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.31236679854314325, "MaxKurtosisOfNumericAtts": 154.060437966028, "MinMeansOfNumericAtts": 0.02134615384615384, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 3932.2115384615436, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 30.216624804038887, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 6.236432692307693, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.05294526024038, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 12.37414162568126, "MinStdDevOfNumericAtts": 0.014264319202680646, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.5192690535710422, "MaxStdDevOfNumericAtts": 12894.343749707, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.03818813163529211, "Quartile3StdDevOfNumericAtts": 1.2130926544918776, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4210416666666665, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 28.017757039174306, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 76.62127179487184, "Quartile1SkewnessOfNumericAtts": -0.15593220930682836, "AutoCorrelation": 0.38627096774193537, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.10366721542819451 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "37", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "156", "missing": "0", "identifier": "1", "distr": [] }, { "name": "NaasC", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "3", "max": "8", "mean": "6", "stdev": "2" }, { "name": "SaaaC", "index": "2", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "NNRS", "index": "3", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8v", "index": "4", "type": "numeric", "distinct": "130", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "RCI", "index": "5", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "6", "type": "numeric", "distinct": "86", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "RFD", "index": "7", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MAXDP", "index": "8", "type": "numeric", "distinct": "134", "missing": "0", "min": "1", "max": "9", "mean": "6", "stdev": "1" }, { "name": "NRS", "index": "9", "type": "numeric", "distinct": "4", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "CATS2D_09_AL", "index": "10", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "45", "mean": "5", "stdev": "5" }, { "name": "ATS8p", "index": "11", "type": "numeric", "distinct": "131", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Eig13_AEA.bo.", "index": "12", "type": "numeric", "distinct": "75", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SpMin1_Bh.m.", "index": "13", "type": "numeric", "distinct": "56", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS8m", "index": "14", "type": "numeric", "distinct": "129", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.m.", "index": "15", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS7v", "index": "16", "type": "numeric", "distinct": "129", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "GGI10", "index": "17", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "NaaaC", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "ATS7m", "index": "19", "type": "numeric", "distinct": "132", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS8s", "index": "20", "type": "numeric", "distinct": "136", "missing": "0", "min": "5", "max": "9", "mean": "6", "stdev": "0" }, { "name": "ATSC8p", "index": "21", "type": "numeric", "distinct": "141", "missing": "0", "min": "7", "max": "111", "mean": "14", "stdev": "8" }, { "name": "ATSC8i", "index": "22", "type": "numeric", "distinct": "135", "missing": "0", "min": "1", "max": "15", "mean": "2", "stdev": "1" }, { "name": "Eta_betaS_A", "index": "23", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8e", "index": "24", "type": "numeric", "distinct": "132", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "SpMin5_Bh.i.", "index": "25", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC4s", "index": "26", "type": "numeric", "distinct": "143", "missing": "0", "min": "26", "max": "804", "mean": "96", "stdev": "80" }, { "name": "SpMaxA_EA.bo.", "index": "27", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "28", "type": "numeric", "distinct": "96", "missing": "0", "min": "15", "max": "760", "mean": "70", "stdev": "59" }, { "name": "DLS_cons", "index": "29", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin5_Bh.e.", "index": "30", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "31", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "ATS6m", "index": "32", "type": "numeric", "distinct": "129", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS7p", "index": "33", "type": "numeric", "distinct": "127", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMax5_Bh.p.", "index": "34", "type": "numeric", "distinct": "98", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Rbrid", "index": "35", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax5_Bh.v.", "index": "36", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS7s", "index": "37", "type": "numeric", "distinct": "131", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "38", "type": "numeric", "distinct": "82", "missing": "0", "min": "43", "max": "305", "mean": "139", "stdev": "28" }, { "name": "SM08_EA.bo.", "index": "39", "type": "numeric", "distinct": "110", "missing": "0", "min": "12", "max": "14", "mean": "12", "stdev": "0" }, { "name": "Eig12_AEA.bo.", "index": "40", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "piPC08", "index": "41", "type": "numeric", "distinct": "109", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "42", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "43", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "piPC05", "index": "44", "type": "numeric", "distinct": "95", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin6_Bh.p.", "index": "45", "type": "numeric", "distinct": "106", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMaxA_AEA.bo.", "index": "46", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "VvdwZAZ", "index": "47", "type": "numeric", "distinct": "123", "missing": "0", "min": "336", "max": "2279", "mean": "467", "stdev": "155" }, { "name": "HDcpx", "index": "48", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "piPC09", "index": "49", "type": "numeric", "distinct": "115", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "1" }, { "name": "nPyridines", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "51", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.029", "index": "52", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS2p", "index": "53", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ON1", "index": "54", "type": "numeric", "distinct": "97", "missing": "0", "min": "6", "max": "38", "mean": "8", "stdev": "3" }, { "name": "Eta_alpha", "index": "55", "type": "numeric", "distinct": "104", "missing": "0", "min": "14", "max": "78", "mean": "18", "stdev": "5" }, { "name": "Chi0_EA.ed.", "index": "56", "type": "numeric", "distinct": "117", "missing": "0", "min": "11", "max": "66", "mean": "14", "stdev": "4" }, { "name": "SpMin6_Bh.i.", "index": "57", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CENT", "index": "58", "type": "numeric", "distinct": "112", "missing": "0", "min": "1080", "max": "163460", "mean": "3932", "stdev": "12894" }, { "name": "BID", "index": "59", "type": "numeric", "distinct": "34", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IDM", "index": "60", "type": "numeric", "distinct": "100", "missing": "0", "min": "8", "max": "14", "mean": "9", "stdev": "0" }, { "name": "piPC06", "index": "61", "type": "numeric", "distinct": "108", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eta_beta", "index": "62", "type": "numeric", "distinct": "55", "missing": "0", "min": "31", "max": "169", "mean": "45", "stdev": "11" }, { "name": "SpMin5_Bh.v.", "index": "63", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Chi1_EA.ed.", "index": "64", "type": "numeric", "distinct": "116", "missing": "0", "min": "5", "max": "31", "mean": "7", "stdev": "2" } ], "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 }