{ "data_id": "31374", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4564", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4564", "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: CHEMBL4564 (TID: 12409), and it has 119 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 07:24:52", "update_comment": null, "last_update": "2016-07-15 07:24:52", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3447364\/data_52609.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-CHEMBL4564", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4564 (TID: 12409), and it has 119 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": 119, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.769809042974179, "MinStdDevOfNumericAtts": 0.006233926775500474, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.44638858160563, "MaxStdDevOfNumericAtts": 81.5135205418527, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.2814078700945115, "Quartile3StdDevOfNumericAtts": 1.4050653875633707, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6523760504201674, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 5.524260374203831, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 14.830329175420166, "Quartile1SkewnessOfNumericAtts": -1.1747797604155137, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1958901567729303, "AutoCorrelation": -0.05755932203389832, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.2830096952487433, "Dimensionality": 0.5462184873949579, "MeanSkewnessOfNumericAtts": -0.46853042009589635, "Quartile2MeansOfNumericAtts": 1.3843067226890757, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.087149405430397, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.21977449855894382, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0358705750932082, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5007577551995551, "MaxKurtosisOfNumericAtts": 79.06069143713773, "MinMeansOfNumericAtts": -0.062134453781512604, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 202.13487394957983, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.757546226715288, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 4.10793487394958, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -7.940786566962372, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "97", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "119", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Mi", "index": "1", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Hy", "index": "2", "type": "numeric", "distinct": "79", "missing": "0", "min": "2", "max": "11", "mean": "4", "stdev": "2" }, { "name": "P_VSA_e_3", "index": "3", "type": "numeric", "distinct": "30", "missing": "0", "min": "84", "max": "344", "mean": "155", "stdev": "45" }, { "name": "P_VSA_i_4", "index": "4", "type": "numeric", "distinct": "29", "missing": "0", "min": "84", "max": "344", "mean": "154", "stdev": "45" }, { "name": "TPSA.NO.", "index": "5", "type": "numeric", "distinct": "45", "missing": "0", "min": "84", "max": "405", "mean": "202", "stdev": "55" }, { "name": "SpMin7_Bh.v.", "index": "6", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "AAC", "index": "7", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC1e", "index": "8", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC3e", "index": "9", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "C.", "index": "10", "type": "numeric", "distinct": "47", "missing": "0", "min": "32", "max": "43", "mean": "37", "stdev": "2" }, { "name": "C.043", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "12", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "13", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig04_EA.dm.", "index": "14", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "IC0", "index": "15", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS4s", "index": "16", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaO", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nFuranes", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "19", "type": "numeric", "distinct": "34", "missing": "0", "min": "21", "max": "428", "mean": "172", "stdev": "82" }, { "name": "SaaO", "index": "20", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "SM04_EA.dm.", "index": "21", "type": "numeric", "distinct": "43", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "22", "type": "numeric", "distinct": "42", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "2" }, { "name": "SpMAD_EA.dm.", "index": "23", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X3A", "index": "24", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "25", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "26", "type": "numeric", "distinct": "63", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ARR", "index": "27", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "BAC", "index": "28", "type": "numeric", "distinct": "53", "missing": "0", "min": "5", "max": "263", "mean": "73", "stdev": "39" }, { "name": "P_VSA_LogP_6", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "2", "max": "56", "mean": "10", "stdev": "13" }, { "name": "Eig02_EA.ri.", "index": "30", "type": "numeric", "distinct": "39", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "PW5", "index": "31", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SssNH", "index": "32", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "16", "mean": "4", "stdev": "3" }, { "name": "C.033", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.e.", "index": "34", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "35", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "36", "type": "numeric", "distinct": "97", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5e", "index": "37", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC6e", "index": "38", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "39", "type": "numeric", "distinct": "77", "missing": "0", "min": "11", "max": "59", "mean": "27", "stdev": "8" }, { "name": "Eig04_AEA.dm.", "index": "40", "type": "numeric", "distinct": "72", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "41", "type": "numeric", "distinct": "58", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_AEA.ri.", "index": "42", "type": "numeric", "distinct": "71", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig05_EA", "index": "43", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig13_EA", "index": "44", "type": "numeric", "distinct": "65", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.bo.", "index": "45", "type": "numeric", "distinct": "78", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "46", "type": "numeric", "distinct": "56", "missing": "0", "min": "-2", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "47", "type": "numeric", "distinct": "80", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_AEA.dm.", "index": "48", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA", "index": "49", "type": "numeric", "distinct": "66", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "50", "type": "numeric", "distinct": "84", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA.ed.", "index": "51", "type": "numeric", "distinct": "64", "missing": "0", "min": "-2", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "52", "type": "numeric", "distinct": "77", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "53", "type": "numeric", "distinct": "63", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig15_EA", "index": "54", "type": "numeric", "distinct": "61", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA.bo.", "index": "55", "type": "numeric", "distinct": "84", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig15_EA.ed.", "index": "56", "type": "numeric", "distinct": "68", "missing": "0", "min": "-3", "max": "6", "mean": "1", "stdev": "1" }, { "name": "Eig15_EA.ri.", "index": "57", "type": "numeric", "distinct": "78", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "GATS4e", "index": "58", "type": "numeric", "distinct": "101", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS4s", "index": "59", "type": "numeric", "distinct": "106", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nHAcc", "index": "60", "type": "numeric", "distinct": "17", "missing": "0", "min": "5", "max": "26", "mean": "12", "stdev": "4" }, { "name": "nHet", "index": "61", "type": "numeric", "distinct": "17", "missing": "0", "min": "5", "max": "26", "mean": "13", "stdev": "4" }, { "name": "Psi_e_A", "index": "62", "type": "numeric", "distinct": "89", "missing": "0", "min": "8", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "63", "type": "numeric", "distinct": "89", "missing": "0", "min": "2", "max": "3", "mean": "3", "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 }