{ "data_id": "34838", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4361", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4361", "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: CHEMBL4361 (TID: 100468), and it has 1457 rows and 71 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 16:25:34", "update_comment": null, "last_update": "2016-07-15 16:25:34", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3540342\/data_53727.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4361", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4361 (TID: 100468), and it has 1457 rows and 71 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": 1457, "NumberOfFeatures": 73, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 72, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 3.751141915697609, "Dimensionality": 0.050102951269732326, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 6.252683939601922, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.29406886489090434, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.6148647051483973, "Quartile2SkewnessOfNumericAtts": -0.467695623489751, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6225200329065661, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": 0.19364364451189964, "MinMeansOfNumericAtts": 0.04392587508579248, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 452.9659400955138, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 9.123569712323011, "MaxMeansOfNumericAtts": 52.363264241592304, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.63013698630137, "Quartile3MeansOfNumericAtts": 10.59404615648593, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -2.404879902659007, "PercentageOfSymbolicFeatures": 1.36986301369863, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.07288129616415899, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.37892393249814893, "MaxSkewnessOfNumericAtts": 18.94466652212131, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 2.24703120548865, "Quartile3StdDevOfNumericAtts": 1.1053789773940308, "MaxStdDevOfNumericAtts": 96.36917526239854, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 4.364953328757721, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 14.149650479828612, "Quartile1SkewnessOfNumericAtts": -1.0200926634393057, "MeanMeansOfNumericAtts": 8.155474033401969, "Quartile1StdDevOfNumericAtts": 0.3874328108598946, "AutoCorrelation": 0.45670329670329657, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "72", "type": "numeric", "distinct": "870", "missing": "0", "target": "1", "min": "3", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1457", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMax1_Bh.p.", "index": "1", "type": "numeric", "distinct": "344", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.v.", "index": "2", "type": "numeric", "distinct": "327", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MPC07", "index": "3", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpMin2_Bh.s.", "index": "4", "type": "numeric", "distinct": "471", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "D.Dtr12", "index": "5", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "692", "mean": "9", "stdev": "43" }, { "name": "SM13_EA.ri.", "index": "6", "type": "numeric", "distinct": "1123", "missing": "0", "min": "10", "max": "18", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "7", "type": "numeric", "distinct": "1124", "missing": "0", "min": "11", "max": "20", "mean": "16", "stdev": "1" }, { "name": "MWC10", "index": "8", "type": "numeric", "distinct": "924", "missing": "0", "min": "8", "max": "14", "mean": "12", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "9", "type": "numeric", "distinct": "387", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nR12", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "0" }, { "name": "TWC", "index": "11", "type": "numeric", "distinct": "896", "missing": "0", "min": "9", "max": "14", "mean": "13", "stdev": "0" }, { "name": "ALOGP2", "index": "12", "type": "numeric", "distinct": "1346", "missing": "0", "min": "0", "max": "132", "mean": "18", "stdev": "17" }, { "name": "C.025", "index": "13", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "2" }, { "name": "SM12_EA.ri.", "index": "14", "type": "numeric", "distinct": "1105", "missing": "0", "min": "10", "max": "17", "mean": "14", "stdev": "1" }, { "name": "ALOGP", "index": "15", "type": "numeric", "distinct": "1211", "missing": "0", "min": "-11", "max": "12", "mean": "4", "stdev": "2" }, { "name": "piPC06", "index": "16", "type": "numeric", "distinct": "981", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "Eig01_EA.ri.", "index": "17", "type": "numeric", "distinct": "595", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "18", "type": "numeric", "distinct": "604", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "19", "type": "numeric", "distinct": "595", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "20", "type": "numeric", "distinct": "298", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "21", "type": "numeric", "distinct": "1104", "missing": "0", "min": "9", "max": "16", "mean": "13", "stdev": "1" }, { "name": "D.Dtr11", "index": "22", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "328", "mean": "5", "stdev": "24" }, { "name": "SM10_EA.ri.", "index": "23", "type": "numeric", "distinct": "1081", "missing": "0", "min": "8", "max": "14", "mean": "12", "stdev": "1" }, { "name": "CATS2D_04_LL", "index": "24", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "46", "mean": "6", "stdev": "6" }, { "name": "TPC", "index": "25", "type": "numeric", "distinct": "1026", "missing": "0", "min": "3", "max": "12", "mean": "7", "stdev": "1" }, { "name": "SM09_EA.ri.", "index": "26", "type": "numeric", "distinct": "1038", "missing": "0", "min": "7", "max": "13", "mean": "11", "stdev": "1" }, { "name": "nCIR", "index": "27", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "148", "mean": "5", "stdev": "6" }, { "name": "SM08_EA.ri.", "index": "28", "type": "numeric", "distinct": "984", "missing": "0", "min": "7", "max": "12", "mean": "10", "stdev": "1" }, { "name": "piPC05", "index": "29", "type": "numeric", "distinct": "933", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "D.Dtr10", "index": "30", "type": "numeric", "distinct": "450", "missing": "0", "min": "0", "max": "1246", "mean": "52", "stdev": "96" }, { "name": "MPC10", "index": "31", "type": "numeric", "distinct": "381", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "1" }, { "name": "MPC05", "index": "32", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "0" }, { "name": "CATS2D_03_LL", "index": "33", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "49", "mean": "9", "stdev": "7" }, { "name": "Rbrid", "index": "34", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "piPC10", "index": "35", "type": "numeric", "distinct": "1127", "missing": "0", "min": "0", "max": "11", "mean": "7", "stdev": "1" }, { "name": "piPC04", "index": "36", "type": "numeric", "distinct": "849", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "0" }, { "name": "MWC07", "index": "37", "type": "numeric", "distinct": "851", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "0" }, { "name": "MPC09", "index": "38", "type": "numeric", "distinct": "362", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "1" }, { "name": "MWC08", "index": "39", "type": "numeric", "distinct": "859", "missing": "0", "min": "7", "max": "12", "mean": "10", "stdev": "0" }, { "name": "MPC08", "index": "40", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "nR11", "index": "41", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "piPC09", "index": "42", "type": "numeric", "distinct": "1118", "missing": "0", "min": "0", "max": "11", "mean": "7", "stdev": "1" }, { "name": "CATS2D_02_LL", "index": "43", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "44", "mean": "11", "stdev": "7" }, { "name": "Eig05_EA.ed.", "index": "44", "type": "numeric", "distinct": "1147", "missing": "0", "min": "-4", "max": "11", "mean": "6", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "45", "type": "numeric", "distinct": "1147", "missing": "0", "min": "-4", "max": "11", "mean": "6", "stdev": "1" }, { "name": "SRW10", "index": "46", "type": "numeric", "distinct": "859", "missing": "0", "min": "7", "max": "12", "mean": "10", "stdev": "0" }, { "name": "SM05_EA.ri.", "index": "47", "type": "numeric", "distinct": "913", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "0" }, { "name": "piPC07", "index": "48", "type": "numeric", "distinct": "1042", "missing": "0", "min": "0", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM06_EA.ri.", "index": "49", "type": "numeric", "distinct": "900", "missing": "0", "min": "5", "max": "10", "mean": "8", "stdev": "0" }, { "name": "SM07_EA.ri.", "index": "50", "type": "numeric", "distinct": "984", "missing": "0", "min": "5", "max": "10", "mean": "9", "stdev": "1" }, { "name": "MWC06", "index": "51", "type": "numeric", "distinct": "823", "missing": "0", "min": "6", "max": "10", "mean": "8", "stdev": "0" }, { "name": "MPC06", "index": "52", "type": "numeric", "distinct": "240", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "piID", "index": "53", "type": "numeric", "distinct": "1244", "missing": "0", "min": "4", "max": "19", "mean": "11", "stdev": "2" }, { "name": "Eig05_AEA.ed.", "index": "54", "type": "numeric", "distinct": "908", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpMax1_Bh.e.", "index": "55", "type": "numeric", "distinct": "303", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "56", "type": "numeric", "distinct": "690", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "57", "type": "numeric", "distinct": "690", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "58", "type": "numeric", "distinct": "702", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "59", "type": "numeric", "distinct": "690", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "60", "type": "numeric", "distinct": "594", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "61", "type": "numeric", "distinct": "594", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "H.046", "index": "62", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "37", "mean": "2", "stdev": "4" }, { "name": "SM11_EA.bo.", "index": "63", "type": "numeric", "distinct": "1078", "missing": "0", "min": "11", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "64", "type": "numeric", "distinct": "1046", "missing": "0", "min": "10", "max": "17", "mean": "15", "stdev": "1" }, { "name": "piPC08", "index": "65", "type": "numeric", "distinct": "1088", "missing": "0", "min": "0", "max": "10", "mean": "7", "stdev": "1" }, { "name": "SpMin1_Bh.i.", "index": "66", "type": "numeric", "distinct": "309", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_EA.ri.", "index": "67", "type": "numeric", "distinct": "1149", "missing": "0", "min": "12", "max": "21", "mean": "17", "stdev": "1" }, { "name": "TRS", "index": "68", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "59", "mean": "21", "stdev": "7" }, { "name": "SM12_EA.bo.", "index": "69", "type": "numeric", "distinct": "1106", "missing": "0", "min": "12", "max": "21", "mean": "18", "stdev": "1" }, { "name": "CATS2D_01_LL", "index": "70", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "43", "mean": "9", "stdev": "5" }, { "name": "SM09_EA.bo.", "index": "71", "type": "numeric", "distinct": "1057", "missing": "0", "min": "9", "max": "16", "mean": "14", "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 }