{ "data_id": "35650", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5631", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5631", "version": 10, "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: CHEMBL5631 (TID: 101488), and it has 122 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": "2016-07-15 18:37:05", "update_comment": null, "last_update": "2016-07-15 18:37:05", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3564029\/data_52913.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5631", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5631 (TID: 101488), and it has 122 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": 122, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.5491803278688525, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9832722247668153, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.4111115010229711, "Quartile2MeansOfNumericAtts": 3.6823688524590166, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 210.25146092663462, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4142719090410716, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2755004912547026, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7403759685906217, "MaxKurtosisOfNumericAtts": 7.298389140231227, "MinMeansOfNumericAtts": -1.729581967213115, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 18370.836065573774, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.5037836993955223, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 6.337793032786886, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9320336983485276, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.3251001459764424, "MinStdDevOfNumericAtts": 0.07612362395361547, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1876255472080675, "MaxStdDevOfNumericAtts": 13362.688439701782, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.4617816772937777, "Quartile3StdDevOfNumericAtts": 2.164279963499003, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4471598360655738, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.351998786630273, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 298.30347925981135, "Quartile1SkewnessOfNumericAtts": -0.2579343504798268, "AutoCorrelation": 0.1802314049586782, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.47946410698886677 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "112", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "122", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DA", "index": "1", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "P_VSA_s_5", "index": "2", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "82", "mean": "19", "stdev": "20" }, { "name": "GGI9", "index": "3", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC8s", "index": "4", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "431", "mean": "77", "stdev": "68" }, { "name": "SpDiam_AEA.bo.", "index": "5", "type": "numeric", "distinct": "76", "missing": "0", "min": "4", "max": "6", "mean": "6", "stdev": "0" }, { "name": "CATS2D_04_DL", "index": "6", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "3" }, { "name": "NaaNH", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nPyrroles", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaNH", "index": "9", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "10", "type": "numeric", "distinct": "71", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "11", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "5", "stdev": "3" }, { "name": "Eig04_AEA.dm.", "index": "12", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_08_AP", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_AA", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_07_LL", "index": "15", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "4" }, { "name": "P_VSA_MR_5", "index": "16", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "75", "mean": "29", "stdev": "24" }, { "name": "SpMax8_Bh.s.", "index": "17", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "CATS2D_08_DP", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.034", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_06_DL", "index": "20", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "3" }, { "name": "CATS2D_06_PL", "index": "21", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SpMax1_Bh.e.", "index": "22", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "23", "type": "numeric", "distinct": "67", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "24", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI6", "index": "25", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GGI2", "index": "26", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SM06_AEA.bo.", "index": "27", "type": "numeric", "distinct": "90", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "nCsp2", "index": "28", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "20", "mean": "12", "stdev": "5" }, { "name": "Psi_i_s", "index": "29", "type": "numeric", "distinct": "101", "missing": "0", "min": "18", "max": "115", "mean": "58", "stdev": "17" }, { "name": "Eig08_EA.bo.", "index": "30", "type": "numeric", "distinct": "61", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS4s", "index": "31", "type": "numeric", "distinct": "117", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "CATS2D_08_DD", "index": "32", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig05_AEA.dm.", "index": "33", "type": "numeric", "distinct": "106", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.ri.", "index": "34", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "GMTIV", "index": "35", "type": "numeric", "distinct": "108", "missing": "0", "min": "500", "max": "75475", "mean": "18371", "stdev": "13363" }, { "name": "piPC05", "index": "36", "type": "numeric", "distinct": "91", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "piPC06", "index": "37", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "38", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "39", "type": "numeric", "distinct": "88", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SM06_EA.bo.", "index": "40", "type": "numeric", "distinct": "93", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "1" }, { "name": "SM07_AEA.bo.", "index": "41", "type": "numeric", "distinct": "91", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM08_AEA.bo.", "index": "42", "type": "numeric", "distinct": "93", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "1" }, { "name": "Eig03_AEA.dm.", "index": "43", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATSC8e", "index": "44", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ZM1Kup", "index": "45", "type": "numeric", "distinct": "104", "missing": "0", "min": "94", "max": "951", "mean": "393", "stdev": "142" }, { "name": "CATS2D_05_DL", "index": "46", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "3" }, { "name": "ATS6s", "index": "47", "type": "numeric", "distinct": "117", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SssNH", "index": "48", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "ATS5s", "index": "49", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ZM1MulPer", "index": "50", "type": "numeric", "distinct": "108", "missing": "0", "min": "94", "max": "824", "mean": "403", "stdev": "126" }, { "name": "Eig02_AEA.dm.", "index": "51", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "52", "type": "numeric", "distinct": "104", "missing": "0", "min": "39", "max": "224", "mean": "142", "stdev": "49" }, { "name": "C.028", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_01_DP", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_PL", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_09_PP", "index": "56", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig14_AEA.ri.", "index": "57", "type": "numeric", "distinct": "49", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "1" }, { "name": "Eig14_EA", "index": "58", "type": "numeric", "distinct": "41", "missing": "0", "min": "-2", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "59", "type": "numeric", "distinct": "66", "missing": "0", "min": "-3", "max": "1", "mean": "-1", "stdev": "1" }, { "name": "Eig14_EA.ed.", "index": "60", "type": "numeric", "distinct": "48", "missing": "0", "min": "-7", "max": "1", "mean": "-2", "stdev": "2" }, { "name": "Eig14_EA.ri.", "index": "61", "type": "numeric", "distinct": "47", "missing": "0", "min": "-2", "max": "0", "mean": "-1", "stdev": "1" }, { "name": "H.051", "index": "62", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "nAB", "index": "63", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "22", "mean": "12", "stdev": "6" }, { "name": "nCar", "index": "64", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "19", "mean": "11", "stdev": "5" }, { "name": "nN.", "index": "65", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "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 }