{ "data_id": "31958", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6000", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6000", "version": 8, "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: CHEMBL6000 (TID: 101405), and it has 117 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 08:57:14", "update_comment": null, "last_update": "2016-07-15 08:57:14", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3465814\/data_52933.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL6000", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL6000 (TID: 101405), and it has 117 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": 117, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 4.807130341880342, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9353164446859648, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.142488277965265, "MaxSkewnessOfNumericAtts": 3.0842434601211752, "MinStdDevOfNumericAtts": 0.0022107166042958297, "Quartile1KurtosisOfNumericAtts": -0.13495660270341203, "Quartile3StdDevOfNumericAtts": 2.476143358256288, "MaxStdDevOfNumericAtts": 87.92121459033609, "MinorityClassPercentage": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.079147435897436, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.0652253417566515, "Quartile1SkewnessOfNumericAtts": 0.041991808369293684, "MeanMeansOfNumericAtts": 15.977058793058793, "Quartile1StdDevOfNumericAtts": 0.25701559447849265, "AutoCorrelation": 0.3482758620689653, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 0.6093703888621693, "Dimensionality": 0.5726495726495726, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.185709401709402, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5501465103506843, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.103403888971784, "Quartile2SkewnessOfNumericAtts": 0.7202850791265005, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7992543621087385, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.0323401180296274, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 12.293982735520693, "MinMeansOfNumericAtts": -3.770854700854701, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.7883443122670255, "MaxMeansOfNumericAtts": 151.90334188034188, "MinMutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "46", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "117", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig02_EA.bo.", "index": "1", "type": "numeric", "distinct": "85", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "2", "type": "numeric", "distinct": "85", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_MR_7", "index": "3", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "121", "mean": "41", "stdev": "27" }, { "name": "CATS2D_01_DA", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "D.Dtr05", "index": "5", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "472", "mean": "114", "stdev": "84" }, { "name": "nPyrroles", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nPyrazoles", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SaaNH", "index": "8", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "Eig02_AEA.dm.", "index": "9", "type": "numeric", "distinct": "101", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SRW09", "index": "10", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "3" }, { "name": "CATS2D_09_DA", "index": "11", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "12", "type": "numeric", "distinct": "79", "missing": "0", "min": "42", "max": "218", "mean": "97", "stdev": "41" }, { "name": "nR05", "index": "13", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "N.073", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "15", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SRW05", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SRW07", "index": "17", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "C.026", "index": "18", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SM02_EA.dm.", "index": "19", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SpMax2_Bh.m.", "index": "20", "type": "numeric", "distinct": "75", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS4s", "index": "21", "type": "numeric", "distinct": "108", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC3e", "index": "22", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DELS", "index": "23", "type": "numeric", "distinct": "117", "missing": "0", "min": "12", "max": "71", "mean": "32", "stdev": "13" }, { "name": "SpMax8_Bh.s.", "index": "24", "type": "numeric", "distinct": "103", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "D.Dtr09", "index": "25", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "439", "mean": "99", "stdev": "88" }, { "name": "ATSC4s", "index": "26", "type": "numeric", "distinct": "117", "missing": "0", "min": "20", "max": "227", "mean": "64", "stdev": "34" }, { "name": "Eig02_AEA.bo.", "index": "27", "type": "numeric", "distinct": "88", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.dm.", "index": "28", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "SM12_EA.dm.", "index": "29", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "30", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "19", "mean": "5", "stdev": "6" }, { "name": "GATS2e", "index": "31", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "32", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "4" }, { "name": "Eig01_EA.dm.", "index": "33", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax_EA.dm.", "index": "34", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MLOGP2", "index": "35", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "30", "mean": "7", "stdev": "5" }, { "name": "GATS6s", "index": "36", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax1_Bh.e.", "index": "37", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "38", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM06_EA.dm.", "index": "39", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "40", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "ATSC4e", "index": "41", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "42", "type": "numeric", "distinct": "71", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "43", "type": "numeric", "distinct": "102", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "44", "type": "numeric", "distinct": "104", "missing": "0", "min": "74", "max": "243", "mean": "152", "stdev": "34" }, { "name": "P_VSA_v_3", "index": "45", "type": "numeric", "distinct": "104", "missing": "0", "min": "74", "max": "243", "mean": "152", "stdev": "34" }, { "name": "BLTA96", "index": "46", "type": "numeric", "distinct": "82", "missing": "0", "min": "-7", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "BLTD48", "index": "47", "type": "numeric", "distinct": "78", "missing": "0", "min": "-7", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "BLTF96", "index": "48", "type": "numeric", "distinct": "77", "missing": "0", "min": "-6", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "MLOGP", "index": "49", "type": "numeric", "distinct": "94", "missing": "0", "min": "-1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig03_AEA.dm.", "index": "50", "type": "numeric", "distinct": "84", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "TIE", "index": "51", "type": "numeric", "distinct": "117", "missing": "0", "min": "21", "max": "123", "mean": "57", "stdev": "19" }, { "name": "SM04_EA.dm.", "index": "52", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "C.033", "index": "53", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.bo.", "index": "54", "type": "numeric", "distinct": "73", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "55", "type": "numeric", "distinct": "73", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nR09", "index": "56", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "GATS1m", "index": "57", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "58", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "59", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "60", "type": "numeric", "distinct": "103", "missing": "0", "min": "7", "max": "20", "mean": "12", "stdev": "2" }, { "name": "SAacc", "index": "61", "type": "numeric", "distinct": "92", "missing": "0", "min": "56", "max": "218", "mean": "108", "stdev": "38" }, { "name": "ATSC6e", "index": "62", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "JGI8", "index": "63", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "H.048", "index": "64", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax7_Bh.s.", "index": "65", "type": "numeric", "distinct": "106", "missing": "0", "min": "4", "max": "5", "mean": "4", "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 }