{ "data_id": "32856", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4599", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4599", "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: CHEMBL4599 (TID: 30023), and it has 526 rows and 68 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": "2016-07-15 11:17:25", "update_comment": null, "last_update": "2016-07-15 11:17:25", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3491388\/data_53432.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4599", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4599 (TID: 30023), and it has 526 rows and 68 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": 526, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.13307984790874525, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.35253336361355014, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.20494483363802618, "Quartile2MeansOfNumericAtts": 5.114068441064637, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.382508899192693, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.4007268739634132, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8367087360488035, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8213700166431981, "MaxKurtosisOfNumericAtts": 172.59930062014706, "MinMeansOfNumericAtts": 0.12797718631178737, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 204.18715019011407, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.274213424231442, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 14.290867870722428, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.2661739738113416, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 10.05619916074765, "MinStdDevOfNumericAtts": 0.12860078205168715, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.17202027009109816, "MaxStdDevOfNumericAtts": 82.86798198517627, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.4355719723427227, "Quartile3StdDevOfNumericAtts": 3.8610810360890637, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.3474866920152093, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 3.056459020328907, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 12.088203614922575, "Quartile1SkewnessOfNumericAtts": -0.8612045078982744, "AutoCorrelation": 0.2808685714285723, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2909393875970212 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "155", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "526", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_05_AL", "index": "1", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "18", "mean": "7", "stdev": "4" }, { "name": "CATS2D_06_AL", "index": "2", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "25", "mean": "6", "stdev": "4" }, { "name": "NRS", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "CATS2D_07_AL", "index": "4", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "22", "mean": "5", "stdev": "4" }, { "name": "Eig15_AEA.ri.", "index": "5", "type": "numeric", "distinct": "339", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig01_EA.bo.", "index": "6", "type": "numeric", "distinct": "258", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "7", "type": "numeric", "distinct": "258", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "8", "type": "numeric", "distinct": "258", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "9", "type": "numeric", "distinct": "258", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig14_EA.ed.", "index": "10", "type": "numeric", "distinct": "333", "missing": "0", "min": "-7", "max": "4", "mean": "0", "stdev": "2" }, { "name": "SM09_AEA.ri.", "index": "11", "type": "numeric", "distinct": "333", "missing": "0", "min": "-7", "max": "4", "mean": "0", "stdev": "2" }, { "name": "TRS", "index": "12", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "52", "mean": "24", "stdev": "7" }, { "name": "nCIC", "index": "13", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "9", "mean": "4", "stdev": "1" }, { "name": "Eig14_AEA.ri.", "index": "14", "type": "numeric", "distinct": "352", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA", "index": "15", "type": "numeric", "distinct": "293", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM08_AEA.dm.", "index": "16", "type": "numeric", "distinct": "293", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Rperim", "index": "17", "type": "numeric", "distinct": "29", "missing": "0", "min": "6", "max": "42", "mean": "21", "stdev": "6" }, { "name": "Eig14_AEA.bo.", "index": "18", "type": "numeric", "distinct": "319", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "H.047", "index": "19", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "34", "mean": "13", "stdev": "7" }, { "name": "LLS_02", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM15_EA.bo.", "index": "21", "type": "numeric", "distinct": "368", "missing": "0", "min": "19", "max": "25", "mean": "23", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "22", "type": "numeric", "distinct": "329", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "LLS_01", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig15_AEA.bo.", "index": "24", "type": "numeric", "distinct": "335", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "25", "type": "numeric", "distinct": "368", "missing": "0", "min": "18", "max": "24", "mean": "21", "stdev": "1" }, { "name": "Pol", "index": "26", "type": "numeric", "distinct": "64", "missing": "0", "min": "11", "max": "100", "mean": "46", "stdev": "13" }, { "name": "piPC08", "index": "27", "type": "numeric", "distinct": "399", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "28", "type": "numeric", "distinct": "362", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpDiam_AEA.ri.", "index": "29", "type": "numeric", "distinct": "304", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC5i", "index": "30", "type": "numeric", "distinct": "449", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "31", "type": "numeric", "distinct": "310", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SaasC", "index": "32", "type": "numeric", "distinct": "496", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "ATSC6m", "index": "33", "type": "numeric", "distinct": "514", "missing": "0", "min": "1", "max": "324", "mean": "27", "stdev": "17" }, { "name": "Eig13_AEA.ri.", "index": "34", "type": "numeric", "distinct": "368", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.p.", "index": "35", "type": "numeric", "distinct": "270", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "36", "type": "numeric", "distinct": "368", "missing": "0", "min": "16", "max": "22", "mean": "20", "stdev": "1" }, { "name": "SM13_EA.ed.", "index": "37", "type": "numeric", "distinct": "385", "missing": "0", "min": "28", "max": "37", "mean": "32", "stdev": "1" }, { "name": "D.Dtr09", "index": "38", "type": "numeric", "distinct": "264", "missing": "0", "min": "0", "max": "428", "mean": "85", "stdev": "76" }, { "name": "ATSC5v", "index": "39", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "31", "mean": "13", "stdev": "6" }, { "name": "ATSC2v", "index": "40", "type": "numeric", "distinct": "487", "missing": "0", "min": "1", "max": "19", "mean": "10", "stdev": "4" }, { "name": "SpMin3_Bh.s.", "index": "41", "type": "numeric", "distinct": "315", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "42", "type": "numeric", "distinct": "368", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "nArNHR", "index": "43", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SssCH2", "index": "44", "type": "numeric", "distinct": "377", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "ATSC1v", "index": "45", "type": "numeric", "distinct": "476", "missing": "0", "min": "0", "max": "11", "mean": "6", "stdev": "2" }, { "name": "SM10_EA.bo.", "index": "46", "type": "numeric", "distinct": "367", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "nPyrimidines", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig15_AEA.dm.", "index": "48", "type": "numeric", "distinct": "336", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC6v", "index": "49", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "35", "mean": "12", "stdev": "6" }, { "name": "SpMin4_Bh.v.", "index": "50", "type": "numeric", "distinct": "330", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "51", "type": "numeric", "distinct": "350", "missing": "0", "min": "14", "max": "27", "mean": "19", "stdev": "2" }, { "name": "nAB", "index": "52", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "34", "mean": "19", "stdev": "5" }, { "name": "CIC3", "index": "53", "type": "numeric", "distinct": "373", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaasC", "index": "54", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "6", "stdev": "2" }, { "name": "nH", "index": "55", "type": "numeric", "distinct": "42", "missing": "0", "min": "3", "max": "44", "mean": "22", "stdev": "8" }, { "name": "P_VSA_MR_1", "index": "56", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "412", "mean": "204", "stdev": "83" }, { "name": "SM11_EA.bo.", "index": "57", "type": "numeric", "distinct": "368", "missing": "0", "min": "14", "max": "19", "mean": "17", "stdev": "1" }, { "name": "ATSC1m", "index": "58", "type": "numeric", "distinct": "483", "missing": "0", "min": "0", "max": "33", "mean": "10", "stdev": "4" }, { "name": "X0sol", "index": "59", "type": "numeric", "distinct": "344", "missing": "0", "min": "7", "max": "32", "mean": "20", "stdev": "5" }, { "name": "SpMin4_Bh.p.", "index": "60", "type": "numeric", "distinct": "331", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "61", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "62", "type": "numeric", "distinct": "339", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SaaN", "index": "63", "type": "numeric", "distinct": "427", "missing": "0", "min": "0", "max": "26", "mean": "8", "stdev": "4" }, { "name": "SpMax4_Bh.i.", "index": "64", "type": "numeric", "distinct": "344", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "65", "type": "numeric", "distinct": "340", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "MPC08", "index": "66", "type": "numeric", "distinct": "211", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "piPC04", "index": "67", "type": "numeric", "distinct": "346", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "68", "type": "numeric", "distinct": "252", "missing": "0", "min": "4", "max": "5", "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 }