{ "data_id": "28664", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL241", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL241", "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: CHEMBL241 (TID: 170), and it has 285 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 00:34:12", "update_comment": null, "last_update": "2016-07-15 00:34:12", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3368946\/data_52894.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL241", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL241 (TID: 170), and it has 285 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": 285, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8703122807017545, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.37353379863355285, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 183.79963439659747, "Quartile1SkewnessOfNumericAtts": -0.20119074299400283, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.19341762696850673, "AutoCorrelation": 0.24217253521126766, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.04110936734028714, "Dimensionality": 0.23508771929824562, "MeanSkewnessOfNumericAtts": 0.3363611849164782, "Quartile2MeansOfNumericAtts": 3.228552631578947, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 121.1538276149688, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.16922720855741052, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.1761536070888488, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.34148570270696743, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 4.706064153869331, "MinMeansOfNumericAtts": -0.02658245614035088, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 10611.596491228065, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9274084124642399, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 6.95545, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0454964999227088, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.4142488822854737, "MinStdDevOfNumericAtts": 0.02892037243337643, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7440946249612864, "MaxStdDevOfNumericAtts": 7336.847811694032, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.656683554396148, "Quartile3StdDevOfNumericAtts": 1.8568444902927959 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "215", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "285", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nDB", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "NdssC", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "ATSC7p", "index": "3", "type": "numeric", "distinct": "277", "missing": "0", "min": "2", "max": "16", "mean": "9", "stdev": "3" }, { "name": "SpMax4_Bh.m.", "index": "4", "type": "numeric", "distinct": "208", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "5", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC6p", "index": "6", "type": "numeric", "distinct": "274", "missing": "0", "min": "4", "max": "20", "mean": "10", "stdev": "3" }, { "name": "Eta_betaS_A", "index": "7", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "8", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.s.", "index": "9", "type": "numeric", "distinct": "140", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "10", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "11", "type": "numeric", "distinct": "142", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SdssC", "index": "12", "type": "numeric", "distinct": "176", "missing": "0", "min": "-2", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ATSC2p", "index": "13", "type": "numeric", "distinct": "248", "missing": "0", "min": "3", "max": "12", "mean": "7", "stdev": "2" }, { "name": "MATS6s", "index": "14", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS6e", "index": "15", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.038", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_EA.bo.", "index": "17", "type": "numeric", "distinct": "163", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM14_AEA.ri.", "index": "18", "type": "numeric", "distinct": "163", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_07_DD", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NRS", "index": "20", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Eig02_EA.ri.", "index": "21", "type": "numeric", "distinct": "189", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "LLS_01", "index": "22", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig10_AEA.ri.", "index": "23", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig10_EA.ri.", "index": "24", "type": "numeric", "distinct": "197", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig11_EA.bo.", "index": "25", "type": "numeric", "distinct": "168", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig05_EA.ri.", "index": "26", "type": "numeric", "distinct": "207", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "IDE", "index": "27", "type": "numeric", "distinct": "188", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SssO", "index": "28", "type": "numeric", "distinct": "191", "missing": "0", "min": "0", "max": "28", "mean": "7", "stdev": "7" }, { "name": "ICR", "index": "29", "type": "numeric", "distinct": "165", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "AECC", "index": "30", "type": "numeric", "distinct": "183", "missing": "0", "min": "6", "max": "18", "mean": "11", "stdev": "3" }, { "name": "HVcpx", "index": "31", "type": "numeric", "distinct": "182", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC5p", "index": "32", "type": "numeric", "distinct": "276", "missing": "0", "min": "4", "max": "17", "mean": "10", "stdev": "3" }, { "name": "MSD", "index": "33", "type": "numeric", "distinct": "204", "missing": "0", "min": "4", "max": "11", "mean": "6", "stdev": "2" }, { "name": "S2K", "index": "34", "type": "numeric", "distinct": "223", "missing": "0", "min": "3", "max": "13", "mean": "8", "stdev": "2" }, { "name": "Eig10_AEA.ed.", "index": "35", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "CSI", "index": "36", "type": "numeric", "distinct": "187", "missing": "0", "min": "207", "max": "1719", "mean": "699", "stdev": "334" }, { "name": "ATS6p", "index": "37", "type": "numeric", "distinct": "241", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS5p", "index": "38", "type": "numeric", "distinct": "233", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "39", "type": "numeric", "distinct": "171", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ECC", "index": "40", "type": "numeric", "distinct": "156", "missing": "0", "min": "101", "max": "794", "mean": "323", "stdev": "153" }, { "name": "Uindex", "index": "41", "type": "numeric", "distinct": "208", "missing": "0", "min": "23", "max": "75", "mean": "43", "stdev": "10" }, { "name": "nPyrrolidines", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS6e", "index": "43", "type": "numeric", "distinct": "246", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "UNIP", "index": "44", "type": "numeric", "distinct": "115", "missing": "0", "min": "37", "max": "280", "mean": "114", "stdev": "54" }, { "name": "Yindex", "index": "45", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC6v", "index": "46", "type": "numeric", "distinct": "277", "missing": "0", "min": "4", "max": "26", "mean": "13", "stdev": "4" }, { "name": "RFD", "index": "47", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.030", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS2p", "index": "49", "type": "numeric", "distinct": "212", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS5v", "index": "50", "type": "numeric", "distinct": "237", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_i_2", "index": "51", "type": "numeric", "distinct": "239", "missing": "0", "min": "55", "max": "188", "mean": "118", "stdev": "29" }, { "name": "ATS6i", "index": "52", "type": "numeric", "distinct": "240", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Vindex", "index": "53", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_LL", "index": "54", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "27", "mean": "7", "stdev": "5" }, { "name": "SMTI", "index": "55", "type": "numeric", "distinct": "208", "missing": "0", "min": "1817", "max": "35383", "mean": "10612", "stdev": "7337" }, { "name": "CATS2D_05_LL", "index": "56", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "27", "mean": "8", "stdev": "5" }, { "name": "SAdon", "index": "57", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "120", "mean": "25", "stdev": "24" }, { "name": "NNRS", "index": "58", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RCI", "index": "59", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nRCO", "index": "60", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS7i", "index": "61", "type": "numeric", "distinct": "249", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "62", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "63", "type": "numeric", "distinct": "159", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Xindex", "index": "64", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "65", "type": "numeric", "distinct": "205", "missing": "0", "min": "3", "max": "4", "mean": "3", "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 }