{ "data_id": "35604", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1293319", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1293319", "version": 10, "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: CHEMBL1293319 (TID: 103752), and it has 833 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 18:29:50", "update_comment": null, "last_update": "2016-07-15 18:29:50", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3563007\/data_33846.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1293319", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1293319 (TID: 103752), and it has 833 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": 833, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 18, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.733510137659263, "MinStdDevOfNumericAtts": 0.012242639075724676, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.198275029676549, "MaxStdDevOfNumericAtts": 82.94280885889037, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.42023780026010094, "Quartile3StdDevOfNumericAtts": 7.35479304269753, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9703991596638654, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.346342129199989, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 36.32898145925037, "Quartile1SkewnessOfNumericAtts": 0.29871519551293085, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.0410617076552081, "AutoCorrelation": 0.43203485576923095, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.5793085509036477, "Dimensionality": 0.05402160864345738, "MeanSkewnessOfNumericAtts": 0.8698988118170016, "Quartile2MeansOfNumericAtts": 8.485593037214887, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.408765416148801, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6212549423361413, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.4183681742543883, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 4.468378848190453, "MaxKurtosisOfNumericAtts": 34.84688584070051, "MinMeansOfNumericAtts": 0.08950660264105642, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 355.7183553421369, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.834212014889262, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 40, "Quartile3MeansOfNumericAtts": 39.78881092436975, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.12055524472277043, "PercentageOfSymbolicFeatures": 2.2222222222222223, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "44", "type": "numeric", "distinct": "653", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "833", "missing": "0", "identifier": "1", "distr": [] }, { "name": "AMW", "index": "1", "type": "numeric", "distinct": "685", "missing": "0", "min": "6", "max": "16", "mean": "9", "stdev": "1" }, { "name": "C.", "index": "2", "type": "numeric", "distinct": "158", "missing": "0", "min": "30", "max": "56", "mean": "43", "stdev": "4" }, { "name": "H.", "index": "3", "type": "numeric", "distinct": "181", "missing": "0", "min": "19", "max": "58", "mean": "39", "stdev": "6" }, { "name": "Me", "index": "4", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mp", "index": "6", "type": "numeric", "distinct": "165", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "7", "type": "numeric", "distinct": "173", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MW", "index": "8", "type": "numeric", "distinct": "749", "missing": "0", "min": "142", "max": "909", "mean": "356", "stdev": "83" }, { "name": "N.", "index": "9", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "29", "mean": "7", "stdev": "5" }, { "name": "nAB", "index": "10", "type": "string", "distinct": "23", "missing": "0" }, { "name": "nAT", "index": "11", "type": "string", "distinct": "63", "missing": "0" }, { "name": "nB", "index": "12", "type": "string", "distinct": "2", "missing": "0" }, { "name": "nBM", "index": "13", "type": "string", "distinct": "32", "missing": "0" }, { "name": "nBO", "index": "14", "type": "string", "distinct": "38", "missing": "0" }, { "name": "nBR", "index": "15", "type": "string", "distinct": "4", "missing": "0" }, { "name": "nBT", "index": "16", "type": "string", "distinct": "65", "missing": "0" }, { "name": "nC", "index": "17", "type": "string", "distinct": "32", "missing": "0" }, { "name": "nCL", "index": "18", "type": "string", "distinct": "6", "missing": "0" }, { "name": "nCsp", "index": "19", "type": "string", "distinct": "6", "missing": "0" }, { "name": "nCsp2", "index": "20", "type": "string", "distinct": "30", "missing": "0" }, { "name": "nCsp3", "index": "21", "type": "string", "distinct": "19", "missing": "0" }, { "name": "nDB", "index": "22", "type": "string", "distinct": "11", "missing": "0" }, { "name": "nF", "index": "23", "type": "string", "distinct": "6", "missing": "0" }, { "name": "nH", "index": "24", "type": "string", "distinct": "37", "missing": "0" }, { "name": "nHet", "index": "25", "type": "string", "distinct": "18", "missing": "0" }, { "name": "nHM", "index": "26", "type": "string", "distinct": "8", "missing": "0" }, { "name": "nI", "index": "27", "type": "string", "distinct": "2", "missing": "0" }, { "name": "nN", "index": "28", "type": "string", "distinct": "11", "missing": "0" }, { "name": "nO", "index": "29", "type": "string", "distinct": "15", "missing": "0" }, { "name": "nP", "index": "30", "type": "string", "distinct": "3", "missing": "0" }, { "name": "nS", "index": "31", "type": "string", "distinct": "6", "missing": "0" }, { "name": "nSK", "index": "32", "type": "string", "distinct": "37", "missing": "0" }, { "name": "nTB", "index": "33", "type": "string", "distinct": "6", "missing": "0" }, { "name": "nX", "index": "34", "type": "string", "distinct": "7", "missing": "0" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "142", "missing": "0", "min": "0", "max": "27", "mean": "8", "stdev": "4" }, { "name": "RBF", "index": "36", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "string", "distinct": "15", "missing": "0" }, { "name": "SCBO", "index": "38", "type": "numeric", "distinct": "87", "missing": "0", "min": "13", "max": "85", "mean": "37", "stdev": "8" }, { "name": "Se", "index": "39", "type": "numeric", "distinct": "755", "missing": "0", "min": "15", "max": "137", "mean": "42", "stdev": "11" }, { "name": "Si", "index": "40", "type": "numeric", "distinct": "764", "missing": "0", "min": "17", "max": "158", "mean": "47", "stdev": "12" }, { "name": "Sp", "index": "41", "type": "numeric", "distinct": "728", "missing": "0", "min": "11", "max": "83", "mean": "29", "stdev": "7" }, { "name": "Sv", "index": "42", "type": "numeric", "distinct": "767", "missing": "0", "min": "10", "max": "78", "mean": "28", "stdev": "7" }, { "name": "X.", "index": "43", "type": "numeric", "distinct": "54", "missing": "0", "min": "0", "max": "22", "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 }