{ "data_id": "32941", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4824", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4824", "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: CHEMBL4824 (TID: 10275), and it has 129 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": "2016-07-15 11:29:58", "update_comment": null, "last_update": "2016-07-15 11:29:58", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3492859\/data_52968.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4824", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4824 (TID: 10275), and it has 129 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": 129, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.5193798449612403, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.9239002147634461, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.1271949281708088, "Quartile2MeansOfNumericAtts": 2.5093527131782944, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 11.742975332349937, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.12166863825671766, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.7003305643130513, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.23281668029600472, "MaxKurtosisOfNumericAtts": 4.37831075813485, "MinMeansOfNumericAtts": -0.14742635658914727, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 1449.7364341085274, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.31714782055640145, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 4.81988953488372, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.6055344691278162, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.0019874312755634, "MinStdDevOfNumericAtts": 0.009333668581326775, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.36777531609730124, "MaxStdDevOfNumericAtts": 713.0095603253228, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.3143749057845155, "Quartile3StdDevOfNumericAtts": 0.38900221750611313, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1223042635658915, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.5668107399067736, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 26.440400281888653, "Quartile1SkewnessOfNumericAtts": -0.29715998388089704, "AutoCorrelation": 0.05292187499999956, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1513815160897178 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "44", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "129", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SaaCH", "index": "1", "type": "numeric", "distinct": "124", "missing": "0", "min": "2", "max": "29", "mean": "10", "stdev": "7" }, { "name": "CATS2D_05_DA", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "MATS7p", "index": "3", "type": "numeric", "distinct": "110", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC8v", "index": "4", "type": "numeric", "distinct": "125", "missing": "0", "min": "5", "max": "21", "mean": "12", "stdev": "4" }, { "name": "AMW", "index": "5", "type": "numeric", "distinct": "90", "missing": "0", "min": "7", "max": "12", "mean": "8", "stdev": "1" }, { "name": "GATS7v", "index": "6", "type": "numeric", "distinct": "116", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "AAC", "index": "7", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "8", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC8i", "index": "9", "type": "numeric", "distinct": "121", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "10", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS5e", "index": "11", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS5e", "index": "12", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ON1V", "index": "13", "type": "numeric", "distinct": "104", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eta_sh_p", "index": "14", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS7i", "index": "15", "type": "numeric", "distinct": "118", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS8e", "index": "16", "type": "numeric", "distinct": "116", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SIC2", "index": "17", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BIC2", "index": "18", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS3e", "index": "19", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "20", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "21", "type": "numeric", "distinct": "14", "missing": "0", "min": "2", "max": "16", "mean": "6", "stdev": "3" }, { "name": "SpMax6_Bh.e.", "index": "22", "type": "numeric", "distinct": "100", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "23", "type": "numeric", "distinct": "92", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "24", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS3i", "index": "25", "type": "numeric", "distinct": "108", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Si", "index": "26", "type": "numeric", "distinct": "96", "missing": "0", "min": "39", "max": "77", "mean": "59", "stdev": "11" }, { "name": "ATS7v", "index": "27", "type": "numeric", "distinct": "113", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS7p", "index": "28", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS7i", "index": "29", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_06_LL", "index": "30", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "16", "mean": "4", "stdev": "3" }, { "name": "SpMin4_Bh.m.", "index": "31", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS2e", "index": "32", "type": "numeric", "distinct": "97", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS2i", "index": "33", "type": "numeric", "distinct": "99", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS4i", "index": "34", "type": "numeric", "distinct": "109", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Se", "index": "35", "type": "numeric", "distinct": "96", "missing": "0", "min": "34", "max": "67", "mean": "53", "stdev": "10" }, { "name": "SpMin4_Bh.s.", "index": "36", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "37", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "38", "type": "numeric", "distinct": "94", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nHM", "index": "39", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.m.", "index": "40", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig14_AEA.dm.", "index": "41", "type": "numeric", "distinct": "84", "missing": "0", "min": "-1", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MATS7i", "index": "42", "type": "numeric", "distinct": "111", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "43", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "JGI4", "index": "44", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS6e", "index": "45", "type": "numeric", "distinct": "118", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS4m", "index": "46", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC2", "index": "47", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GNar", "index": "48", "type": "numeric", "distinct": "55", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "X0A", "index": "49", "type": "numeric", "distinct": "42", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "50", "type": "numeric", "distinct": "79", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "51", "type": "numeric", "distinct": "79", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "52", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax5_Bh.i.", "index": "53", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS7e", "index": "54", "type": "numeric", "distinct": "114", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ATS8i", "index": "55", "type": "numeric", "distinct": "116", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "56", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "MATS7v", "index": "57", "type": "numeric", "distinct": "106", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CENT", "index": "58", "type": "numeric", "distinct": "85", "missing": "0", "min": "344", "max": "3260", "mean": "1450", "stdev": "713" }, { "name": "SIC0", "index": "59", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IC1", "index": "60", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC7i", "index": "61", "type": "numeric", "distinct": "119", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.m.", "index": "62", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "11", "mean": "6", "stdev": "3" }, { "name": "ATS8p", "index": "63", "type": "numeric", "distinct": "120", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS4e", "index": "64", "type": "numeric", "distinct": "112", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SssO", "index": "65", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "6" } ], "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 }