{ "data_id": "27916", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2978", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2978", "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: CHEMBL2978 (TID: 10113), and it has 131 rows and 63 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 22:42:21", "update_comment": null, "last_update": "2016-07-14 22:42:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3344196\/data_52573.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-CHEMBL2978", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2978 (TID: 10113), and it has 131 rows and 63 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": 131, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 9.223796852343009, "MinStdDevOfNumericAtts": 0.016310338089585825, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 5.599130731544343, "MaxStdDevOfNumericAtts": 98.91295465003087, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 11.848938348115016, "Quartile3StdDevOfNumericAtts": 1.048525860871361, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6081812977099237, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 30.25547549252642, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.131333373091603, "Quartile1SkewnessOfNumericAtts": 2.3095744855451428, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.10580738877631198, "AutoCorrelation": 0.555523076923077, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 17.314431554455844, "Dimensionality": 0.4961832061068702, "MeanSkewnessOfNumericAtts": 4.115153798063618, "Quartile2MeansOfNumericAtts": 2.7294503816793894, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.141453535320184, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 3.304450668539542, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": 0.1657932680803076, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3293993216364273, "MaxKurtosisOfNumericAtts": 91.57508488979077, "MinMeansOfNumericAtts": 0.10613740458015268, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 50.239969465648855, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 35.40772088848453, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 4.347465648854962, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.796202245224967, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "87", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "131", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax2_Bh.v.", "index": "1", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "2", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "3", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "4", "type": "numeric", "distinct": "73", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig11_EA.bo.", "index": "5", "type": "numeric", "distinct": "75", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Eta_betaP", "index": "6", "type": "numeric", "distinct": "28", "missing": "0", "min": "8", "max": "181", "mean": "20", "stdev": "16" }, { "name": "Eig11_AEA.bo.", "index": "7", "type": "numeric", "distinct": "73", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IC2", "index": "8", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "9", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "10", "type": "numeric", "distinct": "57", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "C.002", "index": "11", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "40", "mean": "3", "stdev": "4" }, { "name": "Eig09_EA.bo.", "index": "12", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SpMaxA_AEA.ri.", "index": "13", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "14", "type": "numeric", "distinct": "48", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "15", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig13_AEA.bo.", "index": "16", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "ATS7v", "index": "17", "type": "numeric", "distinct": "111", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATS8v", "index": "18", "type": "numeric", "distinct": "109", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATSC4i", "index": "19", "type": "numeric", "distinct": "113", "missing": "0", "min": "2", "max": "25", "mean": "3", "stdev": "2" }, { "name": "ATSC4p", "index": "20", "type": "numeric", "distinct": "125", "missing": "0", "min": "14", "max": "169", "mean": "20", "stdev": "15" }, { "name": "Eig05_EA.bo.", "index": "21", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig14_AEA.ri.", "index": "22", "type": "numeric", "distinct": "53", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Eig14_EA", "index": "23", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig14_EA.ed.", "index": "24", "type": "numeric", "distinct": "44", "missing": "0", "min": "-1", "max": "9", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "25", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig15_AEA.ri.", "index": "26", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Eig15_EA", "index": "27", "type": "numeric", "distinct": "57", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig15_EA.ri.", "index": "28", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM08_AEA.dm.", "index": "29", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM09_AEA.dm.", "index": "30", "type": "numeric", "distinct": "57", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM09_AEA.ri.", "index": "31", "type": "numeric", "distinct": "44", "missing": "0", "min": "-1", "max": "9", "mean": "2", "stdev": "1" }, { "name": "SM15_AEA.ri.", "index": "32", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin3_Bh.m.", "index": "33", "type": "numeric", "distinct": "63", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCs", "index": "34", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "80", "mean": "5", "stdev": "8" }, { "name": "SpMin2_Bh.e.", "index": "35", "type": "numeric", "distinct": "50", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC7i", "index": "36", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "33", "mean": "2", "stdev": "3" }, { "name": "Eig13_AEA.ed.", "index": "37", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.v.", "index": "38", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.e.", "index": "39", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.i.", "index": "40", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.p.", "index": "41", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax6_Bh.e.", "index": "42", "type": "numeric", "distinct": "68", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "43", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS6p", "index": "44", "type": "numeric", "distinct": "102", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATS6v", "index": "45", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATS7e", "index": "46", "type": "numeric", "distinct": "109", "missing": "0", "min": "5", "max": "8", "mean": "5", "stdev": "0" }, { "name": "ATS7p", "index": "47", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATS8p", "index": "48", "type": "numeric", "distinct": "112", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATSC2p", "index": "49", "type": "numeric", "distinct": "114", "missing": "0", "min": "9", "max": "118", "mean": "12", "stdev": "11" }, { "name": "ATSC3i", "index": "50", "type": "numeric", "distinct": "110", "missing": "0", "min": "2", "max": "23", "mean": "3", "stdev": "2" }, { "name": "ATSC3p", "index": "51", "type": "numeric", "distinct": "121", "missing": "0", "min": "13", "max": "158", "mean": "17", "stdev": "14" }, { "name": "ATSC7p", "index": "52", "type": "numeric", "distinct": "127", "missing": "0", "min": "11", "max": "239", "mean": "18", "stdev": "23" }, { "name": "ATSC8i", "index": "53", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "36", "mean": "2", "stdev": "3" }, { "name": "ATSC8p", "index": "54", "type": "numeric", "distinct": "123", "missing": "0", "min": "9", "max": "270", "mean": "18", "stdev": "26" }, { "name": "Eta_C", "index": "55", "type": "numeric", "distinct": "127", "missing": "0", "min": "27", "max": "1074", "mean": "50", "stdev": "99" }, { "name": "Eta_L", "index": "56", "type": "numeric", "distinct": "119", "missing": "0", "min": "8", "max": "112", "mean": "11", "stdev": "10" }, { "name": "SpMin3_Bh.s.", "index": "57", "type": "numeric", "distinct": "48", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "58", "type": "numeric", "distinct": "41", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "59", "type": "numeric", "distinct": "56", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin7_Bh.e.", "index": "60", "type": "numeric", "distinct": "51", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "61", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X2sol", "index": "62", "type": "numeric", "distinct": "97", "missing": "0", "min": "11", "max": "183", "mean": "18", "stdev": "17" }, { "name": "IC3", "index": "63", "type": "numeric", "distinct": "86", "missing": "0", "min": "5", "max": "7", "mean": "5", "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 }