{ "data_id": "32768", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4072", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4072", "version": 11, "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: CHEMBL4072 (TID: 10378), and it has 1330 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median).", "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 11:03:27", "update_comment": null, "last_update": "2016-07-15 11:03:27", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3488884\/data_35328.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4072", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4072 (TID: 10378), and it has 1330 rows and 43 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Basic Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1330, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 36.469165057620145, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.3149066653344876, "MaxStdDevOfNumericAtts": 128.99326430194338, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.0453647154045105, "Quartile3StdDevOfNumericAtts": 8.869370379210913, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6601939849624057, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 40.26051966750954, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 25.20837928913192, "Quartile1SkewnessOfNumericAtts": 0.6746071623152351, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5185620346166415, "AutoCorrelation": 0.17644920993228075, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.8858384296472113, "Dimensionality": 0.03383458646616541, "MeanSkewnessOfNumericAtts": 2.1960074547006245, "Quartile2MeansOfNumericAtts": 6.3537492481203, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.874445616374219, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.862260532910267, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4246497335101753, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.9971576436298992, "MaxKurtosisOfNumericAtts": 1330.0000000000728, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 443.68593984962405, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.326373633942523, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 32.51221804511278, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.45974345313302006, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "593", "missing": "0", "target": "1", "min": "2", "max": "11", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1330", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "913", "missing": "0", "min": "6", "max": "15", "mean": "8", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "174", "missing": "0", "min": "26", "max": "57", "mean": "40", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "219", "missing": "0", "min": "23", "max": "63", "mean": "45", "stdev": "6" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "187", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "194", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "1053", "missing": "0", "min": "82", "max": "1297", "mean": "444", "stdev": "129" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "46", "mean": "12", "stdev": "6" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "107", "missing": "0", "min": "12", "max": "178", "mean": "57", "stdev": "19" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "38", "missing": "0", "min": "1", "max": "63", "mean": "16", "stdev": "6" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "62", "missing": "0", "min": "6", "max": "93", "mean": "33", "stdev": "10" }, { "name": "nBR", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nBT", "index": "16", "type": "numeric", "distinct": "107", "missing": "0", "min": "12", "max": "179", "mean": "59", "stdev": "20" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "44", "missing": "0", "min": "4", "max": "58", "mean": "23", "stdev": "7" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "49", "mean": "14", "stdev": "5" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "41", "mean": "9", "stdev": "5" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "17", "mean": "3", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "60", "missing": "0", "min": "5", "max": "95", "mean": "26", "stdev": "11" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "22", "missing": "0", "min": "2", "max": "35", "mean": "8", "stdev": "3" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "2" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "23", "mean": "3", "stdev": "2" }, { "name": "nP", "index": "30", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "31", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "57", "missing": "0", "min": "6", "max": "86", "mean": "31", "stdev": "9" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "23", "mean": "5", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "36", "mean": "8", "stdev": "5" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "120", "missing": "0", "min": "8", "max": "133", "mean": "43", "stdev": "13" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "1057", "missing": "0", "min": "12", "max": "179", "mean": "58", "stdev": "20" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "1076", "missing": "0", "min": "14", "max": "204", "mean": "65", "stdev": "22" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "1037", "missing": "0", "min": "8", "max": "107", "mean": "38", "stdev": "12" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "1070", "missing": "0", "min": "7", "max": "101", "mean": "36", "stdev": "11" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "3" } ], "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 }