{ "data_id": "35381", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3308", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3308", "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: CHEMBL3308 (TID: 12013), and it has 200 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 17:53:34", "update_comment": null, "last_update": "2016-07-15 17:53:34", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3556426\/data_52809.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3308", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3308 (TID: 12013), and it has 200 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": 200, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": -0.6897840882905786, "Dimensionality": 0.335, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 3.7683125, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.14273634843793037, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1.4570709232850492, "Quartile2SkewnessOfNumericAtts": -0.3574542839630863, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.42241452979860084, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8493949648771972, "MinMeansOfNumericAtts": -0.029900000000000003, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 40.63879024684283, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.3606789762409577, "MaxMeansOfNumericAtts": 37.49972, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MeansOfNumericAtts": 5.74512375, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -3.2549261266400316, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.009802055983697384, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5534822899436047, "MaxSkewnessOfNumericAtts": 3.927910384247391, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.4416623234201362, "Quartile3StdDevOfNumericAtts": 1.4321728339037139, "MaxStdDevOfNumericAtts": 22.278205616191045, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.6108875, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 2.4143570125169918, "Quartile1SkewnessOfNumericAtts": -0.44054312025856424, "MeanMeansOfNumericAtts": 6.617649318181819, "Quartile1StdDevOfNumericAtts": 0.23070587504199913, "AutoCorrelation": 0.18037688442211047, "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": "139", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "200", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig04_AEA.dm.", "index": "1", "type": "numeric", "distinct": "106", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_03_AA", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SpMAD_EA.dm.", "index": "3", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.dm.", "index": "4", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_06_AA", "index": "5", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "4", "stdev": "2" }, { "name": "C.040", "index": "6", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "11", "mean": "2", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "7", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "NdssC", "index": "8", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "1" }, { "name": "Eig02_EA.dm.", "index": "9", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "P_VSA_s_5", "index": "10", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "126", "mean": "28", "stdev": "22" }, { "name": "SpAD_EA.dm.", "index": "11", "type": "numeric", "distinct": "72", "missing": "0", "min": "3", "max": "55", "mean": "14", "stdev": "8" }, { "name": "X1A", "index": "12", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM04_EA.dm.", "index": "13", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "Eig01_EA.dm.", "index": "14", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SM06_EA.dm.", "index": "15", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "2" }, { "name": "SM08_EA.dm.", "index": "16", "type": "numeric", "distinct": "57", "missing": "0", "min": "1", "max": "14", "mean": "6", "stdev": "3" }, { "name": "SpMax_EA.dm.", "index": "17", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.dm.", "index": "18", "type": "numeric", "distinct": "27", "missing": "0", "min": "2", "max": "8", "mean": "4", "stdev": "1" }, { "name": "Eig03_AEA.dm.", "index": "19", "type": "numeric", "distinct": "92", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_EA.dm.", "index": "20", "type": "numeric", "distinct": "57", "missing": "0", "min": "2", "max": "17", "mean": "8", "stdev": "4" }, { "name": "SM12_EA.dm.", "index": "21", "type": "numeric", "distinct": "55", "missing": "0", "min": "2", "max": "20", "mean": "9", "stdev": "5" }, { "name": "SM14_EA.dm.", "index": "22", "type": "numeric", "distinct": "55", "missing": "0", "min": "2", "max": "24", "mean": "10", "stdev": "5" }, { "name": "LOC", "index": "23", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_05_AA", "index": "24", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "2" }, { "name": "SpMax2_Bh.s.", "index": "25", "type": "numeric", "distinct": "30", "missing": "0", "min": "5", "max": "8", "mean": "8", "stdev": "0" }, { "name": "GNar", "index": "26", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.039", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArCO", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS5s", "index": "29", "type": "numeric", "distinct": "159", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MCD", "index": "30", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Yindex", "index": "31", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "32", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_EA", "index": "33", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "34", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "35", "type": "numeric", "distinct": "67", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "36", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_EA", "index": "37", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0A", "index": "38", "type": "numeric", "distinct": "47", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "39", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "40", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "41", "type": "numeric", "distinct": "66", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "42", "type": "numeric", "distinct": "66", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig01_AEA.bo.", "index": "43", "type": "numeric", "distinct": "71", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "44", "type": "numeric", "distinct": "71", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "GATS8s", "index": "45", "type": "numeric", "distinct": "170", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "ARR", "index": "46", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "47", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "48", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig02_AEA.ed.", "index": "49", "type": "numeric", "distinct": "60", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Eig02_AEA.ri.", "index": "50", "type": "numeric", "distinct": "78", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig02_EA", "index": "51", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.bo.", "index": "52", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "53", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM15_AEA.ed.", "index": "54", "type": "numeric", "distinct": "112", "missing": "0", "min": "27", "max": "31", "mean": "30", "stdev": "1" }, { "name": "SsF", "index": "55", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "40", "mean": "5", "stdev": "9" }, { "name": "Vindex", "index": "56", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Xindex", "index": "57", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "58", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.ed.", "index": "59", "type": "numeric", "distinct": "102", "missing": "0", "min": "26", "max": "32", "mean": "30", "stdev": "2" }, { "name": "SM13_EA.ed.", "index": "60", "type": "numeric", "distinct": "98", "missing": "0", "min": "28", "max": "35", "mean": "33", "stdev": "2" }, { "name": "SM14_EA.ed.", "index": "61", "type": "numeric", "distinct": "100", "missing": "0", "min": "30", "max": "37", "mean": "35", "stdev": "2" }, { "name": "SM15_EA.ed.", "index": "62", "type": "numeric", "distinct": "95", "missing": "0", "min": "32", "max": "40", "mean": "37", "stdev": "2" }, { "name": "SM15_EA.bo.", "index": "63", "type": "numeric", "distinct": "125", "missing": "0", "min": "19", "max": "24", "mean": "23", "stdev": "1" }, { "name": "HNar", "index": "64", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM08_EA.ed.", "index": "65", "type": "numeric", "distinct": "112", "missing": "0", "min": "18", "max": "22", "mean": "20", "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 }