{ "data_id": "34558", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5414", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5414", "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: CHEMBL5414 (TID: 100863), and it has 350 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 15:41:04", "update_comment": null, "last_update": "2016-07-15 15:41:04", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3532204\/data_52726.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5414", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5414 (TID: 100863), and it has 350 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": 350, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -0.5157357902178108, "Dimensionality": 0.19142857142857142, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 0.9329071428571427, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.41218091368875454, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.63466090871742, "Quartile2SkewnessOfNumericAtts": 0.11734355711975997, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9737894835251711, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3940985461430664, "MinMeansOfNumericAtts": -0.9596199999999999, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 9.324845507342227, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.0222450296244583, "MaxMeansOfNumericAtts": 160.8661914285714, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 3.7548964285714286, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.6669354099324125, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.058818706943734735, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.206540962769816, "MaxSkewnessOfNumericAtts": 2.7886835233874785, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.2298798350708016, "Quartile3StdDevOfNumericAtts": 2.334546698580048, "MaxStdDevOfNumericAtts": 164.20778324724674, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": -0.03302285714285705, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 0.8462268983388767, "Quartile1SkewnessOfNumericAtts": -0.05793557573365304, "MeanMeansOfNumericAtts": 6.085157835497834, "Quartile1StdDevOfNumericAtts": 0.5109536652040856, "AutoCorrelation": -0.3180573065902563, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "234", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "350", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_04_DL", "index": "1", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "4" }, { "name": "Eig05_AEA.dm.", "index": "2", "type": "numeric", "distinct": "239", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "CATS2D_07_LL", "index": "3", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "34", "mean": "3", "stdev": "5" }, { "name": "N.072", "index": "4", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "P_VSA_LogP_3", "index": "5", "type": "numeric", "distinct": "59", "missing": "0", "min": "18", "max": "231", "mean": "108", "stdev": "40" }, { "name": "CATS2D_07_DD", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "LLS_01", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_DD", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_LL", "index": "9", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "39", "mean": "4", "stdev": "6" }, { "name": "Eig04_EA.ri.", "index": "10", "type": "numeric", "distinct": "231", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_09_LL", "index": "11", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "34", "mean": "5", "stdev": "5" }, { "name": "NssNH", "index": "12", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SssNH", "index": "13", "type": "numeric", "distinct": "238", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "SpMin3_Bh.e.", "index": "14", "type": "numeric", "distinct": "184", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "15", "type": "numeric", "distinct": "239", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMin1_Bh.i.", "index": "16", "type": "numeric", "distinct": "109", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "17", "type": "numeric", "distinct": "212", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "18", "type": "numeric", "distinct": "237", "missing": "0", "min": "6", "max": "77", "mean": "26", "stdev": "9" }, { "name": "IC4", "index": "19", "type": "numeric", "distinct": "248", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "CATS2D_02_DL", "index": "20", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "3", "stdev": "2" }, { "name": "SdO", "index": "21", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "38", "mean": "6", "stdev": "8" }, { "name": "SpMin1_Bh.e.", "index": "22", "type": "numeric", "distinct": "111", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig13_AEA.dm.", "index": "23", "type": "numeric", "distinct": "201", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "IC5", "index": "24", "type": "numeric", "distinct": "245", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig12_EA", "index": "25", "type": "numeric", "distinct": "183", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM06_AEA.dm.", "index": "26", "type": "numeric", "distinct": "183", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATS3p", "index": "27", "type": "numeric", "distinct": "276", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig13_EA", "index": "28", "type": "numeric", "distinct": "171", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM07_AEA.dm.", "index": "29", "type": "numeric", "distinct": "171", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig11_EA.ri.", "index": "30", "type": "numeric", "distinct": "218", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.025", "index": "31", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "ATSC8i", "index": "32", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ed.", "index": "33", "type": "numeric", "distinct": "221", "missing": "0", "min": "-6", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "SM08_AEA.ri.", "index": "34", "type": "numeric", "distinct": "221", "missing": "0", "min": "-6", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "ATSC8v", "index": "35", "type": "numeric", "distinct": "304", "missing": "0", "min": "0", "max": "47", "mean": "10", "stdev": "6" }, { "name": "D.Dtr06", "index": "36", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "1015", "mean": "161", "stdev": "164" }, { "name": "Eig14_AEA.dm.", "index": "37", "type": "numeric", "distinct": "191", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.bo.", "index": "38", "type": "numeric", "distinct": "194", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_AEA.ri.", "index": "39", "type": "numeric", "distinct": "227", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_DL", "index": "40", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "2" }, { "name": "Eig13_AEA.ri.", "index": "41", "type": "numeric", "distinct": "216", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig13_EA.ri.", "index": "42", "type": "numeric", "distinct": "216", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "43", "type": "numeric", "distinct": "232", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.bo.", "index": "44", "type": "numeric", "distinct": "202", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig11_EA.ed.", "index": "45", "type": "numeric", "distinct": "207", "missing": "0", "min": "-6", "max": "5", "mean": "0", "stdev": "2" }, { "name": "SM06_AEA.ri.", "index": "46", "type": "numeric", "distinct": "207", "missing": "0", "min": "-6", "max": "5", "mean": "0", "stdev": "2" }, { "name": "Eig10_EA", "index": "47", "type": "numeric", "distinct": "196", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM04_AEA.dm.", "index": "48", "type": "numeric", "distinct": "196", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "DLS_01", "index": "49", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS3v", "index": "50", "type": "numeric", "distinct": "275", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.041", "index": "51", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig11_AEA.ri.", "index": "52", "type": "numeric", "distinct": "226", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig12_AEA.ri.", "index": "53", "type": "numeric", "distinct": "219", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig12_EA.ri.", "index": "54", "type": "numeric", "distinct": "225", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATS2p", "index": "55", "type": "numeric", "distinct": "260", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS2v", "index": "56", "type": "numeric", "distinct": "254", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS5s", "index": "57", "type": "numeric", "distinct": "282", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax6_Bh.v.", "index": "58", "type": "numeric", "distinct": "187", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM02_EA.ri.", "index": "59", "type": "numeric", "distinct": "241", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig12_EA.ed.", "index": "60", "type": "numeric", "distinct": "217", "missing": "0", "min": "-6", "max": "5", "mean": "-1", "stdev": "2" }, { "name": "SM07_AEA.ri.", "index": "61", "type": "numeric", "distinct": "217", "missing": "0", "min": "-6", "max": "5", "mean": "-1", "stdev": "2" }, { "name": "Eig11_EA", "index": "62", "type": "numeric", "distinct": "185", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM05_AEA.dm.", "index": "63", "type": "numeric", "distinct": "185", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_03_DL", "index": "64", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "3", "stdev": "4" }, { "name": "BIC4", "index": "65", "type": "numeric", "distinct": "157", "missing": "0", "min": "1", "max": "1", "mean": "1", "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 }