{ "data_id": "28934", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1250375", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1250375", "version": 8, "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: CHEMBL1250375 (TID: 103508), and it has 110 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": "2016-07-15 01:15:26", "update_comment": null, "last_update": "2016-07-15 01:15:26", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3378260\/data_52583.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1250375", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1250375 (TID: 103508), and it has 110 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": 110, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.7238363636363637, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.80169378925766, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.170573579545454, "Quartile1SkewnessOfNumericAtts": -0.4626642565165385, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3486247810683834, "AutoCorrelation": 0.46036697247706415, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.3830968560759542, "Dimensionality": 0.5909090909090909, "MeanSkewnessOfNumericAtts": 0.6986111218764183, "Quartile2MeansOfNumericAtts": 2.620777272727273, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 8.039144778458223, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.9926547960538399, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.8209829756799505, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.1336787418064929, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 16.998318147347664, "MinMeansOfNumericAtts": -0.07805454545454545, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 123.18973636363636, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.751772275746699, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 7.250202272727274, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.1110746880215756, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.129944216324108, "MinStdDevOfNumericAtts": 0.03875870479859618, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.9169932399046143, "MaxStdDevOfNumericAtts": 68.64388718882157, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.42640059493065163, "Quartile3StdDevOfNumericAtts": 2.3383392235059874 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "92", "missing": "0", "target": "1", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "110", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS1e", "index": "1", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1e", "index": "2", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NsssN", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SsssN", "index": "4", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "CATS2D_05_AA", "index": "5", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "MATS1m", "index": "6", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_AA", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "MATS1s", "index": "8", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1s", "index": "9", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_AEA.dm.", "index": "10", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "D.Dtr07", "index": "11", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "80", "mean": "10", "stdev": "25" }, { "name": "D.Dtr11", "index": "12", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "124", "mean": "15", "stdev": "39" }, { "name": "nR07", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nR11", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAdon", "index": "15", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "341", "mean": "51", "stdev": "65" }, { "name": "SM15_EA.ri.", "index": "16", "type": "numeric", "distinct": "101", "missing": "0", "min": "15", "max": "18", "mean": "18", "stdev": "1" }, { "name": "Eta_C_A", "index": "17", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Hy", "index": "18", "type": "numeric", "distinct": "76", "missing": "0", "min": "-1", "max": "5", "mean": "0", "stdev": "1" }, { "name": "PDI", "index": "19", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nArOH", "index": "20", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "SsOH", "index": "21", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "79", "mean": "7", "stdev": "15" }, { "name": "SM03_EA.dm.", "index": "22", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM05_EA.dm.", "index": "23", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SM07_EA.dm.", "index": "24", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SM09_EA.dm.", "index": "25", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "SM11_EA.dm.", "index": "26", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "15", "mean": "3", "stdev": "3" }, { "name": "SM13_EA.dm.", "index": "27", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "17", "mean": "3", "stdev": "3" }, { "name": "SM15_EA.dm.", "index": "28", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "4" }, { "name": "CATS2D_02_AL", "index": "29", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "8", "stdev": "4" }, { "name": "nRCONR2", "index": "30", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "31", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "H.050", "index": "32", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "nHDon", "index": "33", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "P_VSA_e_5", "index": "34", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "400", "mean": "88", "stdev": "69" }, { "name": "P_VSA_p_2", "index": "35", "type": "numeric", "distinct": "63", "missing": "0", "min": "18", "max": "400", "mean": "121", "stdev": "62" }, { "name": "O.057", "index": "36", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GATS2p", "index": "37", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM13_EA.ri.", "index": "38", "type": "numeric", "distinct": "104", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "0" }, { "name": "nCb.", "index": "39", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "nCconj", "index": "40", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "2" }, { "name": "NdssC", "index": "41", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "nN.N", "index": "42", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nR.Cs", "index": "43", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "44", "type": "numeric", "distinct": "105", "missing": "0", "min": "14", "max": "17", "mean": "17", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "45", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "46", "type": "numeric", "distinct": "80", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "47", "type": "numeric", "distinct": "63", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SdO", "index": "48", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "50", "mean": "25", "stdev": "9" }, { "name": "P_VSA_v_2", "index": "49", "type": "numeric", "distinct": "68", "missing": "0", "min": "43", "max": "400", "mean": "123", "stdev": "61" }, { "name": "SAacc", "index": "50", "type": "numeric", "distinct": "67", "missing": "0", "min": "43", "max": "400", "mean": "122", "stdev": "61" }, { "name": "Cl.089", "index": "51", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nCL", "index": "52", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NsCl", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "P_VSA_e_4", "index": "54", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "78", "mean": "19", "stdev": "24" }, { "name": "Eig01_AEA.dm.", "index": "55", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NsOH", "index": "56", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SpDiam_AEA.dm.", "index": "57", "type": "numeric", "distinct": "66", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax_AEA.dm.", "index": "58", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "59", "type": "numeric", "distinct": "66", "missing": "0", "min": "41", "max": "211", "mean": "89", "stdev": "30" }, { "name": "NaasC", "index": "60", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "X3v", "index": "61", "type": "numeric", "distinct": "108", "missing": "0", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "nCp", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "63", "type": "numeric", "distinct": "103", "missing": "0", "min": "13", "max": "15", "mean": "14", "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 }