{ "data_id": "38283", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3983", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3983", "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: CHEMBL3983 (TID: 30011), and it has 154 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": "2016-07-16 03:37:08", "update_comment": null, "last_update": "2016-07-16 03:37:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3635160\/data_53005.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3983", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3983 (TID: 30011), and it has 154 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": 154, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 6.533458668790529, "MinMeansOfNumericAtts": -0.16547402597402597, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.026412137102095445, "MaxMeansOfNumericAtts": 86.87625324675325, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 5.131102272727272, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1277966153073848, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 0.8291945933090598, "MaxSkewnessOfNumericAtts": 1.6438164577108272, "MinStdDevOfNumericAtts": 0.027194237775731777, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 3.00397571755573, "MaxStdDevOfNumericAtts": 26.208575179671996, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6999752586599856, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6355681818181819, "MeanKurtosisOfNumericAtts": -0.10009772110209239, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.1225934671389215, "Quartile1SkewnessOfNumericAtts": -0.16604797956418024, "AutoCorrelation": 0.21988235294117653, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11777902111125418, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.43506493506493504, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.5108153385437981, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.28038012337759344, "Quartile2MeansOfNumericAtts": 1.3891883116883115, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.084937735944823, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.26121762162297557, "Quartile2StdDevOfNumericAtts": 0.4745655572338076, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.0202068300000935, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "77", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "154", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin1_Bh.s.", "index": "1", "type": "numeric", "distinct": "89", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nCrs", "index": "2", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "C.002", "index": "3", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "3" }, { "name": "nCs", "index": "4", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "CATS2D_03_DA", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "C.042", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_DL", "index": "7", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "Eta_betaS_A", "index": "8", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.031", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS1v", "index": "10", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS2v", "index": "11", "type": "numeric", "distinct": "129", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "12", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "NssCH2", "index": "13", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "16", "mean": "6", "stdev": "4" }, { "name": "SpMin2_Bh.s.", "index": "14", "type": "numeric", "distinct": "107", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin2_Bh.v.", "index": "15", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SssCH2", "index": "16", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "16", "mean": "5", "stdev": "4" }, { "name": "nArNHR", "index": "17", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "C.025", "index": "18", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "MATS1i", "index": "19", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "20", "type": "numeric", "distinct": "148", "missing": "0", "min": "0", "max": "79", "mean": "42", "stdev": "19" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "8", "stdev": "5" }, { "name": "Mv", "index": "22", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "23", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1i", "index": "24", "type": "numeric", "distinct": "134", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "N.070", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CIC5", "index": "26", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC5", "index": "27", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "28", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "AMW", "index": "29", "type": "numeric", "distinct": "133", "missing": "0", "min": "6", "max": "12", "mean": "8", "stdev": "1" }, { "name": "H.", "index": "30", "type": "numeric", "distinct": "89", "missing": "0", "min": "24", "max": "53", "mean": "44", "stdev": "5" }, { "name": "N.071", "index": "31", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS1m", "index": "32", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nArNR2", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.p.", "index": "34", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "35", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "36", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "139", "mean": "87", "stdev": "26" }, { "name": "ATS3i", "index": "37", "type": "numeric", "distinct": "142", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GATS2m", "index": "38", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nN", "index": "39", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "10", "mean": "6", "stdev": "2" }, { "name": "CATS2D_03_DD", "index": "40", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig01_EA.ri.", "index": "41", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "42", "type": "numeric", "distinct": "100", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "43", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SsssCH", "index": "44", "type": "numeric", "distinct": "75", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.", "index": "45", "type": "numeric", "distinct": "95", "missing": "0", "min": "34", "max": "56", "mean": "41", "stdev": "4" }, { "name": "CIC4", "index": "46", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nImidazoles", "index": "47", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SIC4", "index": "48", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS2p", "index": "49", "type": "numeric", "distinct": "121", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.046", "index": "50", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "5" }, { "name": "Eta_betaP_A", "index": "51", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "52", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "ATSC3v", "index": "53", "type": "numeric", "distinct": "150", "missing": "0", "min": "5", "max": "28", "mean": "16", "stdev": "6" }, { "name": "PCR", "index": "54", "type": "numeric", "distinct": "111", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_LL", "index": "55", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "20", "mean": "6", "stdev": "5" }, { "name": "SpMin1_Bh.m.", "index": "56", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.032", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "H.052", "index": "58", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "15", "mean": "3", "stdev": "3" }, { "name": "Eta_L_A", "index": "59", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_LL", "index": "60", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "21", "mean": "6", "stdev": "5" }, { "name": "Eta_FL_A", "index": "61", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC1m", "index": "62", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "23", "mean": "12", "stdev": "5" }, { "name": "Rperim", "index": "63", "type": "numeric", "distinct": "22", "missing": "0", "min": "13", "max": "35", "mean": "25", "stdev": "5" }, { "name": "GATS1p", "index": "64", "type": "numeric", "distinct": "132", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCsp2", "index": "65", "type": "numeric", "distinct": "20", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" } ], "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 }