{ "data_id": "37794", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4303", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4303", "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: CHEMBL4303 (TID: 11748), and it has 324 rows and 67 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": "2016-07-16 01:53:12", "update_comment": null, "last_update": "2016-07-16 01:53:12", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3622027\/data_53273.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4303", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4303 (TID: 11748), and it has 324 rows and 67 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": 324, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.21296296296296297, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9596544218653507, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.177985420565426, "Quartile2MeansOfNumericAtts": 2.268816358024692, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.408672100881139, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.1538119489817177, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1487896305244156, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3940383545939223, "MaxKurtosisOfNumericAtts": 16.296370912545974, "MinMeansOfNumericAtts": -0.06838271604938272, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 93.44758024691359, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.501893438733735, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 7.194627314814815, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.7876258085242984, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.5548098690528445, "MinStdDevOfNumericAtts": 0.03380922799309117, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1035569451970844, "MaxStdDevOfNumericAtts": 57.871232128113384, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.2631855293200229, "Quartile3StdDevOfNumericAtts": 2.7349713703725227, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8144398148148148, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.183407384448341, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.24263834422658, "Quartile1SkewnessOfNumericAtts": -0.6892646173987186, "AutoCorrelation": 0.2599721362229106, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.15842408704144917 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "187", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "324", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MATS3v", "index": "1", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.026", "index": "2", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "CATS2D_06_LL", "index": "3", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "7" }, { "name": "CATS2D_07_DD", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "D.Dtr05", "index": "5", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "536", "mean": "76", "stdev": "58" }, { "name": "GATS3v", "index": "6", "type": "numeric", "distinct": "226", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_LL", "index": "7", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "22", "mean": "6", "stdev": "5" }, { "name": "ATS6m", "index": "8", "type": "numeric", "distinct": "278", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NaasC", "index": "9", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "6", "stdev": "3" }, { "name": "MATS6s", "index": "10", "type": "numeric", "distinct": "202", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "11", "type": "numeric", "distinct": "211", "missing": "0", "min": "32", "max": "180", "mean": "88", "stdev": "32" }, { "name": "SssNH", "index": "12", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "26", "mean": "2", "stdev": "3" }, { "name": "ATS7m", "index": "13", "type": "numeric", "distinct": "287", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "RBF", "index": "14", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.040", "index": "15", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "SpMin1_Bh.m.", "index": "16", "type": "numeric", "distinct": "114", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_s_4", "index": "17", "type": "numeric", "distinct": "178", "missing": "0", "min": "18", "max": "172", "mean": "82", "stdev": "32" }, { "name": "GATS6s", "index": "18", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS5m", "index": "19", "type": "numeric", "distinct": "279", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS6m", "index": "20", "type": "numeric", "distinct": "218", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "21", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "22", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "23", "type": "numeric", "distinct": "87", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "24", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GATS3p", "index": "25", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "26", "type": "numeric", "distinct": "142", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nArCONHR", "index": "27", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ARR", "index": "28", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "29", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS5v", "index": "30", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "StN", "index": "31", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "19", "mean": "1", "stdev": "3" }, { "name": "nArCONR2", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "33", "type": "numeric", "distinct": "135", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_s_5", "index": "34", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "162", "mean": "27", "stdev": "18" }, { "name": "MATS3p", "index": "35", "type": "numeric", "distinct": "213", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SRW09", "index": "36", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "3" }, { "name": "TRS", "index": "37", "type": "numeric", "distinct": "21", "missing": "0", "min": "6", "max": "43", "mean": "21", "stdev": "5" }, { "name": "GATS3i", "index": "38", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_LL", "index": "39", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "21", "mean": "8", "stdev": "3" }, { "name": "nHAcc", "index": "40", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "21", "mean": "8", "stdev": "3" }, { "name": "GATS6v", "index": "41", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.", "index": "42", "type": "numeric", "distinct": "92", "missing": "0", "min": "33", "max": "56", "mean": "41", "stdev": "4" }, { "name": "ATSC8e", "index": "43", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "LOC", "index": "44", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "IAC", "index": "45", "type": "numeric", "distinct": "244", "missing": "0", "min": "35", "max": "253", "mean": "93", "stdev": "28" }, { "name": "TIC0", "index": "46", "type": "numeric", "distinct": "244", "missing": "0", "min": "35", "max": "253", "mean": "93", "stdev": "28" }, { "name": "O.060", "index": "47", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax7_Bh.m.", "index": "48", "type": "numeric", "distinct": "217", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "49", "type": "numeric", "distinct": "86", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0sol", "index": "50", "type": "numeric", "distinct": "185", "missing": "0", "min": "7", "max": "55", "mean": "23", "stdev": "6" }, { "name": "CATS2D_03_AA", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "GGI7", "index": "52", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC3e", "index": "53", "type": "numeric", "distinct": "256", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nPyrazoles", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "55", "type": "numeric", "distinct": "21", "missing": "0", "min": "4", "max": "29", "mean": "15", "stdev": "4" }, { "name": "Eig04_EA.bo.", "index": "56", "type": "numeric", "distinct": "155", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "57", "type": "numeric", "distinct": "155", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5e", "index": "58", "type": "numeric", "distinct": "285", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "MATS3m", "index": "59", "type": "numeric", "distinct": "198", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "60", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_L", "index": "61", "type": "numeric", "distinct": "294", "missing": "0", "min": "2", "max": "24", "mean": "8", "stdev": "3" }, { "name": "SpMin4_Bh.i.", "index": "62", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "63", "type": "numeric", "distinct": "192", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "64", "type": "numeric", "distinct": "136", "missing": "0", "min": "5", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SM15_EA", "index": "65", "type": "numeric", "distinct": "194", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "0" }, { "name": "CATS2D_01_DA", "index": "66", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "67", "type": "numeric", "distinct": "309", "missing": "0", "min": "7", "max": "215", "mean": "45", "stdev": "36" } ], "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 }