{ "data_id": "32885", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2492", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2492", "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: CHEMBL2492 (TID: 10635), and it has 639 rows and 69 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 11:21:45", "update_comment": null, "last_update": "2016-07-15 11:21:45", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3491985\/data_53441.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2492", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2492 (TID: 10635), and it has 639 rows and 69 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": 639, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 7.5113959857413475, "MinStdDevOfNumericAtts": 0.056730134468796545, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.133234506204249, "MaxStdDevOfNumericAtts": 222.88137424743604, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.7161050865415929, "Quartile3StdDevOfNumericAtts": 2.7345979251759527, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4210219092331768, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 10.39582243374547, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 8.349589291303376, "Quartile1SkewnessOfNumericAtts": -0.36426077432258475, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.40443458824163164, "AutoCorrelation": 0.11268652037617609, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.5639526624297675, "Dimensionality": 0.1111111111111111, "MeanSkewnessOfNumericAtts": 1.3662796530263737, "Quartile2MeansOfNumericAtts": 2.7128309859154935, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.924637359581407, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4466861549692811, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1982312010313647, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.8602793086386645, "MaxKurtosisOfNumericAtts": 62.701983961866134, "MinMeansOfNumericAtts": 0.09859154929577443, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 218.46244131455398, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 13.544981318043657, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 6.501497261345852, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.381177543581397, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "381", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "639", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MAXDP", "index": "1", "type": "numeric", "distinct": "533", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "2" }, { "name": "nArCONHR", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.002", "index": "3", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "21", "mean": "3", "stdev": "2" }, { "name": "SpMin6_Bh.s.", "index": "4", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "5", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "33", "mean": "1", "stdev": "3" }, { "name": "SpMax3_Bh.v.", "index": "6", "type": "numeric", "distinct": "350", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_AEA.ri.", "index": "7", "type": "numeric", "distinct": "398", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SdO", "index": "8", "type": "numeric", "distinct": "301", "missing": "0", "min": "0", "max": "374", "mean": "13", "stdev": "35" }, { "name": "SpMaxA_EA.bo.", "index": "9", "type": "numeric", "distinct": "178", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "TRS", "index": "10", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "97", "mean": "23", "stdev": "12" }, { "name": "Eig04_EA.ed.", "index": "11", "type": "numeric", "distinct": "355", "missing": "0", "min": "-3", "max": "14", "mean": "6", "stdev": "2" }, { "name": "SM13_AEA.dm.", "index": "12", "type": "numeric", "distinct": "355", "missing": "0", "min": "-3", "max": "14", "mean": "6", "stdev": "2" }, { "name": "Eig09_AEA.ri.", "index": "13", "type": "numeric", "distinct": "352", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_AEA.ed.", "index": "14", "type": "numeric", "distinct": "322", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "1" }, { "name": "P_VSA_LogP_2", "index": "15", "type": "numeric", "distinct": "163", "missing": "0", "min": "0", "max": "777", "mean": "29", "stdev": "67" }, { "name": "X2v", "index": "16", "type": "numeric", "distinct": "564", "missing": "0", "min": "2", "max": "43", "mean": "7", "stdev": "4" }, { "name": "SpMax6_Bh.i.", "index": "17", "type": "numeric", "distinct": "338", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.e.", "index": "18", "type": "numeric", "distinct": "332", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "19", "type": "numeric", "distinct": "367", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC3m", "index": "20", "type": "numeric", "distinct": "578", "missing": "0", "min": "6", "max": "212", "mean": "31", "stdev": "21" }, { "name": "Eig06_EA", "index": "21", "type": "numeric", "distinct": "333", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM14_AEA.bo.", "index": "22", "type": "numeric", "distinct": "333", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax3_Bh.i.", "index": "23", "type": "numeric", "distinct": "324", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "24", "type": "numeric", "distinct": "346", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X3sol", "index": "25", "type": "numeric", "distinct": "436", "missing": "0", "min": "0", "max": "53", "mean": "10", "stdev": "6" }, { "name": "Eig06_AEA.ri.", "index": "26", "type": "numeric", "distinct": "433", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nArCONR2", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC3v", "index": "28", "type": "numeric", "distinct": "563", "missing": "0", "min": "4", "max": "78", "mean": "15", "stdev": "9" }, { "name": "SpMax8_Bh.v.", "index": "29", "type": "numeric", "distinct": "362", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X5sol", "index": "30", "type": "numeric", "distinct": "435", "missing": "0", "min": "0", "max": "33", "mean": "7", "stdev": "4" }, { "name": "X4sol", "index": "31", "type": "numeric", "distinct": "442", "missing": "0", "min": "0", "max": "42", "mean": "8", "stdev": "5" }, { "name": "NdssC", "index": "32", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "30", "mean": "1", "stdev": "3" }, { "name": "Eig09_EA.ri.", "index": "33", "type": "numeric", "distinct": "350", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS2p", "index": "34", "type": "numeric", "distinct": "419", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "piPC05", "index": "35", "type": "numeric", "distinct": "392", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig06_EA.ri.", "index": "36", "type": "numeric", "distinct": "431", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig10_AEA.bo.", "index": "37", "type": "numeric", "distinct": "303", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SRW08", "index": "38", "type": "numeric", "distinct": "356", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "0" }, { "name": "Eig12_AEA.bo.", "index": "39", "type": "numeric", "distinct": "337", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS1s", "index": "40", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "41", "type": "numeric", "distinct": "361", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_09_AA", "index": "42", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "15", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_AA", "index": "43", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "27", "mean": "1", "stdev": "3" }, { "name": "X3", "index": "44", "type": "numeric", "distinct": "412", "missing": "0", "min": "0", "max": "50", "mean": "10", "stdev": "6" }, { "name": "CATS2D_03_DL", "index": "45", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "23", "mean": "2", "stdev": "3" }, { "name": "SpMin2_Bh.i.", "index": "46", "type": "numeric", "distinct": "286", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin8_Bh.e.", "index": "47", "type": "numeric", "distinct": "340", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC3p", "index": "48", "type": "numeric", "distinct": "566", "missing": "0", "min": "3", "max": "53", "mean": "11", "stdev": "6" }, { "name": "SpMin8_Bh.i.", "index": "49", "type": "numeric", "distinct": "317", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig11_AEA.bo.", "index": "50", "type": "numeric", "distinct": "306", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig11_EA.bo.", "index": "51", "type": "numeric", "distinct": "316", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "52", "type": "numeric", "distinct": "321", "missing": "0", "min": "-1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax7_Bh.v.", "index": "53", "type": "numeric", "distinct": "332", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MPC05", "index": "54", "type": "numeric", "distinct": "152", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig12_AEA.ed.", "index": "55", "type": "numeric", "distinct": "281", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "Eig10_EA.bo.", "index": "56", "type": "numeric", "distinct": "305", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig05_AEA.bo.", "index": "57", "type": "numeric", "distinct": "359", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "SpMin2_Bh.e.", "index": "58", "type": "numeric", "distinct": "271", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "59", "type": "numeric", "distinct": "375", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "60", "type": "numeric", "distinct": "333", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "ATS2v", "index": "61", "type": "numeric", "distinct": "418", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "X2", "index": "62", "type": "numeric", "distinct": "412", "missing": "0", "min": "3", "max": "70", "mean": "11", "stdev": "7" }, { "name": "Eig04_AEA.dm.", "index": "63", "type": "numeric", "distinct": "360", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "D.Dtr06", "index": "64", "type": "numeric", "distinct": "413", "missing": "0", "min": "0", "max": "2724", "mean": "218", "stdev": "223" }, { "name": "SpAD_AEA.dm.", "index": "65", "type": "numeric", "distinct": "515", "missing": "0", "min": "6", "max": "265", "mean": "44", "stdev": "27" }, { "name": "Eig13_AEA.ed.", "index": "66", "type": "numeric", "distinct": "300", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "MWC05", "index": "67", "type": "numeric", "distinct": "350", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "68", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "58", "mean": "9", "stdev": "6" }, { "name": "Eig11_AEA.ed.", "index": "69", "type": "numeric", "distinct": "282", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" } ], "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 }