{ "data_id": "34957", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1785", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1785", "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: CHEMBL1785 (TID: 247), and it has 1171 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 16:44:23", "update_comment": null, "last_update": "2016-07-15 16:44:23", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3543485\/data_33940.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-CHEMBL1785", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1785 (TID: 247), and it has 1171 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": 1171, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 44, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 6.724578604923495, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 4.831170587687969, "MaxStdDevOfNumericAtts": 170.25498956203242, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.7219071065146481, "Quartile3StdDevOfNumericAtts": 11.894042714817697, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6657113578138343, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 22.176287922581746, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 29.22407712910488, "Quartile1SkewnessOfNumericAtts": 0.7470669232290326, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4291337685100602, "AutoCorrelation": -0.1805076923076921, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 13.707740374852115, "Dimensionality": 0.03842869342442357, "MeanSkewnessOfNumericAtts": 2.9453169155998173, "Quartile2MeansOfNumericAtts": 6.7938877028181075, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 9.960432278091956, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 3.3279141632049027, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6068505522520602, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 2.5905790719272934, "MaxKurtosisOfNumericAtts": 71.83793892212678, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 529.643877028181, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 42.71428919290338, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 97.77777777777777, "Quartile3MeansOfNumericAtts": 39.2997438087105, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.001565882592219102, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "685", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1171", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "725", "missing": "0", "min": "6", "max": "18", "mean": "9", "stdev": "2" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "151", "missing": "0", "min": "32", "max": "54", "mean": "42", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "196", "missing": "0", "min": "27", "max": "57", "mean": "42", "stdev": "5" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "52", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "175", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "822", "missing": "0", "min": "252", "max": "2657", "mean": "530", "stdev": "170" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "nAB", "index": "10", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "59", "mean": "19", "stdev": "6" }, { "name": "nAT", "index": "11", "type": "numeric", "distinct": "100", "missing": "0", "min": "23", "max": "355", "mean": "64", "stdev": "25" }, { "name": "nB", "index": "12", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nBM", "index": "13", "type": "numeric", "distinct": "44", "missing": "0", "min": "4", "max": "78", "mean": "22", "stdev": "7" }, { "name": "nBO", "index": "14", "type": "numeric", "distinct": "59", "missing": "0", "min": "17", "max": "193", "mean": "40", "stdev": "13" }, { "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": "100", "missing": "0", "min": "24", "max": "363", "mean": "68", "stdev": "26" }, { "name": "nC", "index": "17", "type": "numeric", "distinct": "52", "missing": "0", "min": "8", "max": "122", "mean": "27", "stdev": "9" }, { "name": "nCL", "index": "18", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "nCsp", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nCsp2", "index": "20", "type": "numeric", "distinct": "36", "missing": "0", "min": "7", "max": "70", "mean": "19", "stdev": "6" }, { "name": "nCsp3", "index": "21", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "63", "mean": "8", "stdev": "6" }, { "name": "nDB", "index": "22", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "29", "mean": "3", "stdev": "2" }, { "name": "nF", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "nH", "index": "24", "type": "numeric", "distinct": "63", "missing": "0", "min": "7", "max": "170", "mean": "27", "stdev": "13" }, { "name": "nHet", "index": "25", "type": "numeric", "distinct": "27", "missing": "0", "min": "2", "max": "69", "mean": "10", "stdev": "4" }, { "name": "nHM", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nI", "index": "27", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nN", "index": "28", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "27", "mean": "3", "stdev": "3" }, { "name": "nO", "index": "29", "type": "numeric", "distinct": "21", "missing": "0", "min": "1", "max": "37", "mean": "6", "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": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "nSK", "index": "32", "type": "numeric", "distinct": "59", "missing": "0", "min": "16", "max": "185", "mean": "37", "stdev": "13" }, { "name": "nTB", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nX", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "19", "mean": "9", "stdev": "3" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "53", "mean": "9", "stdev": "5" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "111", "missing": "0", "min": "24", "max": "237", "mean": "53", "stdev": "17" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "835", "missing": "0", "min": "24", "max": "360", "mean": "65", "stdev": "25" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "831", "missing": "0", "min": "26", "max": "404", "mean": "72", "stdev": "29" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "802", "missing": "0", "min": "18", "max": "225", "mean": "43", "stdev": "16" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "836", "missing": "0", "min": "17", "max": "215", "mean": "42", "stdev": "15" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" } ], "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 }