{ "data_id": "33937", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3252", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3252", "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: CHEMBL3252 (TID: 10728), and it has 172 rows and 64 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 14:04:08", "update_comment": null, "last_update": "2016-07-15 14:04:08", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3517363\/data_52659.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-CHEMBL3252", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3252 (TID: 10728), and it has 172 rows and 64 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": 172, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.8127063934103267, "MinStdDevOfNumericAtts": 0.012548552516949427, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.47096460831152553, "MaxStdDevOfNumericAtts": 86.00006778116588, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6200959989186916, "Quartile3StdDevOfNumericAtts": 1.2062480209214077, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.6901395348837209, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.058334324956007946, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 22.353855277280864, "Quartile1SkewnessOfNumericAtts": -0.6307291489785463, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1993616032760704, "AutoCorrelation": -0.2516198830409359, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.18938278563527833, "Dimensionality": 0.38372093023255816, "MeanSkewnessOfNumericAtts": -0.009747662476745697, "Quartile2MeansOfNumericAtts": 1.1565872093023255, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 8.419315453127442, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.02028522663142682, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6254367386459803, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.30976541111157113, "MaxKurtosisOfNumericAtts": 3.469249912464797, "MinMeansOfNumericAtts": -0.13175581395348837, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 231.81516279069768, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.254096369623797, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 3.5969011627906964, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9071182499173516, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "127", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "172", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin7_Bh.m.", "index": "1", "type": "numeric", "distinct": "107", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS4i", "index": "2", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "3", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.s.", "index": "4", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "5", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS1p", "index": "6", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS4i", "index": "7", "type": "numeric", "distinct": "125", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.s.", "index": "8", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS4p", "index": "9", "type": "numeric", "distinct": "121", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS4p", "index": "10", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin8_Bh.e.", "index": "11", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "12", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "137", "mean": "58", "stdev": "36" }, { "name": "O.057", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.m.", "index": "14", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "O.060", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_DL", "index": "16", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "4" }, { "name": "SpMin7_Bh.e.", "index": "17", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_04_DA", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMin8_Bh.v.", "index": "19", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nArOH", "index": "20", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "JGI3", "index": "21", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nArOR", "index": "22", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.s.", "index": "23", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_L", "index": "24", "type": "numeric", "distinct": "131", "missing": "0", "min": "2", "max": "11", "mean": "6", "stdev": "2" }, { "name": "ATSC2m", "index": "25", "type": "numeric", "distinct": "115", "missing": "0", "min": "6", "max": "39", "mean": "19", "stdev": "6" }, { "name": "DBI", "index": "26", "type": "numeric", "distinct": "38", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "27", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "19", "mean": "4", "stdev": "4" }, { "name": "SpMin8_Bh.p.", "index": "28", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS3s", "index": "29", "type": "numeric", "distinct": "126", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig02_EA.dm.", "index": "30", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpAD_EA.dm.", "index": "31", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "19", "mean": "6", "stdev": "4" }, { "name": "MATS1e", "index": "32", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin6_Bh.m.", "index": "33", "type": "numeric", "distinct": "94", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS5e", "index": "34", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "35", "type": "numeric", "distinct": "122", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "36", "type": "numeric", "distinct": "98", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS1m", "index": "37", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax4_Bh.p.", "index": "38", "type": "numeric", "distinct": "106", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "39", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SssO", "index": "40", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "27", "mean": "5", "stdev": "5" }, { "name": "GATS4v", "index": "41", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IAC", "index": "42", "type": "numeric", "distinct": "104", "missing": "0", "min": "34", "max": "122", "mean": "69", "stdev": "19" }, { "name": "TIC0", "index": "43", "type": "numeric", "distinct": "104", "missing": "0", "min": "34", "max": "122", "mean": "69", "stdev": "19" }, { "name": "MATS1v", "index": "44", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS2i", "index": "45", "type": "numeric", "distinct": "107", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax4_Bh.v.", "index": "46", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC1i", "index": "47", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_AL", "index": "48", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "GATS2m", "index": "49", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "50", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS1s", "index": "51", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DECC", "index": "52", "type": "numeric", "distinct": "112", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "53", "type": "numeric", "distinct": "118", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "54", "type": "numeric", "distinct": "118", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_e_1", "index": "55", "type": "numeric", "distinct": "31", "missing": "0", "min": "47", "max": "471", "mean": "229", "stdev": "86" }, { "name": "P_VSA_m_1", "index": "56", "type": "numeric", "distinct": "31", "missing": "0", "min": "47", "max": "471", "mean": "229", "stdev": "86" }, { "name": "P_VSA_p_1", "index": "57", "type": "numeric", "distinct": "42", "missing": "0", "min": "71", "max": "471", "mean": "232", "stdev": "84" }, { "name": "P_VSA_s_2", "index": "58", "type": "numeric", "distinct": "33", "missing": "0", "min": "47", "max": "471", "mean": "229", "stdev": "86" }, { "name": "P_VSA_v_1", "index": "59", "type": "numeric", "distinct": "31", "missing": "0", "min": "47", "max": "471", "mean": "229", "stdev": "86" }, { "name": "SpMin6_Bh.p.", "index": "60", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS4s", "index": "61", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "62", "type": "numeric", "distinct": "117", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SM02_EA.dm.", "index": "63", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GATS1i", "index": "64", "type": "numeric", "distinct": "101", "missing": "0", "min": "1", "max": "2", "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 }