{ "data_id": "38070", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4617", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4617", "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: CHEMBL4617 (TID: 10911), and it has 192 rows and 64 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 02:49:48", "update_comment": null, "last_update": "2016-07-16 02:49:48", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3627827\/data_52699.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4617", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4617 (TID: 10911), and it has 192 rows and 64 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": 192, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 17.411564818333524, "MinMeansOfNumericAtts": -0.24866145833333334, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.972135957773594, "MaxMeansOfNumericAtts": 395.09479166666665, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 6.673559895833334, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.706739081523485, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3SkewnessOfNumericAtts": 0.5697909157466896, "MaxSkewnessOfNumericAtts": 3.9419857175128397, "MinStdDevOfNumericAtts": 0.01073868448456271, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.6477661672113637, "MaxStdDevOfNumericAtts": 143.73260146367826, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.5354721480648401, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8308958333333334, "MeanKurtosisOfNumericAtts": 1.3264596343651767, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 38.666618269230774, "Quartile1SkewnessOfNumericAtts": -0.19277435793072745, "AutoCorrelation": -0.12582198952879586, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2628096586740178, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.34375, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.02907331843320904, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.15250868615280283, "Quartile2MeansOfNumericAtts": 3.5263958333333334, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 13.675198853549373, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.21363809967849565, "Quartile2StdDevOfNumericAtts": 0.36476967196478477, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0555977014941285, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "130", "missing": "0", "target": "1", "min": "3", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "192", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CIC2", "index": "1", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SIC2", "index": "2", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC3", "index": "3", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "BIC2", "index": "4", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SIC3", "index": "5", "type": "numeric", "distinct": "68", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "JGI4", "index": "6", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1s", "index": "7", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PCD", "index": "8", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "MATS8v", "index": "9", "type": "numeric", "distinct": "127", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "H.052", "index": "10", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "BIC1", "index": "11", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1e", "index": "12", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "13", "type": "numeric", "distinct": "77", "missing": "0", "min": "33", "max": "64", "mean": "45", "stdev": "5" }, { "name": "BIC3", "index": "14", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "15", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "158", "mean": "64", "stdev": "37" }, { "name": "ZM1MulPer", "index": "16", "type": "numeric", "distinct": "154", "missing": "0", "min": "90", "max": "621", "mean": "308", "stdev": "117" }, { "name": "ZM1Per", "index": "17", "type": "numeric", "distinct": "154", "missing": "0", "min": "116", "max": "759", "mean": "395", "stdev": "144" }, { "name": "ZM1V", "index": "18", "type": "numeric", "distinct": "108", "missing": "0", "min": "84", "max": "562", "mean": "284", "stdev": "106" }, { "name": "SpDiam_EA.bo.", "index": "19", "type": "numeric", "distinct": "74", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "ZM2MulPer", "index": "20", "type": "numeric", "distinct": "154", "missing": "0", "min": "76", "max": "482", "mean": "264", "stdev": "92" }, { "name": "ZM2Per", "index": "21", "type": "numeric", "distinct": "154", "missing": "0", "min": "108", "max": "706", "mean": "388", "stdev": "138" }, { "name": "ZM2V", "index": "22", "type": "numeric", "distinct": "121", "missing": "0", "min": "72", "max": "448", "mean": "247", "stdev": "86" }, { "name": "MATS1p", "index": "23", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS7m", "index": "24", "type": "numeric", "distinct": "152", "missing": "0", "min": "-2", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "25", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "21", "mean": "8", "stdev": "4" }, { "name": "Mv", "index": "26", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_6", "index": "27", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "111", "mean": "46", "stdev": "19" }, { "name": "GATS1m", "index": "28", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS8p", "index": "29", "type": "numeric", "distinct": "135", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "1" }, { "name": "ZM2Kup", "index": "30", "type": "numeric", "distinct": "162", "missing": "0", "min": "75", "max": "465", "mean": "244", "stdev": "87" }, { "name": "Eig02_AEA.dm.", "index": "31", "type": "numeric", "distinct": "114", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SaaCH", "index": "32", "type": "numeric", "distinct": "157", "missing": "0", "min": "0", "max": "18", "mean": "6", "stdev": "3" }, { "name": "SpMAD_EA.dm.", "index": "33", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "34", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AAC", "index": "35", "type": "numeric", "distinct": "128", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AECC", "index": "36", "type": "numeric", "distinct": "92", "missing": "0", "min": "4", "max": "16", "mean": "7", "stdev": "2" }, { "name": "ALOGP", "index": "37", "type": "numeric", "distinct": "155", "missing": "0", "min": "-2", "max": "9", "mean": "2", "stdev": "1" }, { "name": "ALOGP2", "index": "38", "type": "numeric", "distinct": "158", "missing": "0", "min": "0", "max": "79", "mean": "8", "stdev": "12" }, { "name": "AMR", "index": "39", "type": "numeric", "distinct": "158", "missing": "0", "min": "39", "max": "141", "mean": "67", "stdev": "19" }, { "name": "AMW", "index": "40", "type": "numeric", "distinct": "153", "missing": "0", "min": "5", "max": "14", "mean": "9", "stdev": "1" }, { "name": "ARR", "index": "41", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS1e", "index": "42", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "43", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "44", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1p", "index": "45", "type": "numeric", "distinct": "144", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS1s", "index": "46", "type": "numeric", "distinct": "154", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS1v", "index": "47", "type": "numeric", "distinct": "151", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS2e", "index": "48", "type": "numeric", "distinct": "148", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2i", "index": "49", "type": "numeric", "distinct": "140", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2m", "index": "50", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2p", "index": "51", "type": "numeric", "distinct": "148", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2s", "index": "52", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS2v", "index": "53", "type": "numeric", "distinct": "150", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS3e", "index": "54", "type": "numeric", "distinct": "146", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3i", "index": "55", "type": "numeric", "distinct": "152", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS3m", "index": "56", "type": "numeric", "distinct": "146", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3p", "index": "57", "type": "numeric", "distinct": "156", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3s", "index": "58", "type": "numeric", "distinct": "154", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3v", "index": "59", "type": "numeric", "distinct": "152", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4e", "index": "60", "type": "numeric", "distinct": "154", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS4i", "index": "61", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS4m", "index": "62", "type": "numeric", "distinct": "159", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS4p", "index": "63", "type": "numeric", "distinct": "154", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4s", "index": "64", "type": "numeric", "distinct": "159", "missing": "0", "min": "4", "max": "6", "mean": "5", "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 }