{ "data_id": "33801", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3991", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3991", "version": 8, "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: CHEMBL3991 (TID: 12000), and it has 366 rows and 68 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 13:43:30", "update_comment": null, "last_update": "2016-07-15 13:43:30", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3514253\/data_53421.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-CHEMBL3991", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3991 (TID: 12000), and it has 366 rows and 68 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": 366, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.322036309114311, "MinStdDevOfNumericAtts": 0.1028501108909354, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.1728164329898156, "MaxStdDevOfNumericAtts": 241.7941426221292, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 3.464311249734402, "Quartile3StdDevOfNumericAtts": 3.539030046070505, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1025286885245902, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 6.539532708769403, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 15.707418230775323, "Quartile1SkewnessOfNumericAtts": 0.684910695215838, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.5433392502274208, "AutoCorrelation": -0.025421917808218703, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 5.017673298505942, "Dimensionality": 0.1912568306010929, "MeanSkewnessOfNumericAtts": 1.816984808679685, "Quartile2MeansOfNumericAtts": 2.1234180327868852, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 14.713197980833181, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.5719149120893965, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.5920469523378262, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9318414391406294, "MaxKurtosisOfNumericAtts": 17.09823622123168, "MinMeansOfNumericAtts": 0.0990546448087432, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 185.81523224043715, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 11.408550588772101, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 4.84936475409836, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.6455097449615652, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "220", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "366", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_02_DD", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SsOH", "index": "2", "type": "numeric", "distinct": "137", "missing": "0", "min": "0", "max": "61", "mean": "10", "stdev": "14" }, { "name": "O.057", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "NsOH", "index": "4", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "P_VSA_LogP_4", "index": "5", "type": "numeric", "distinct": "138", "missing": "0", "min": "20", "max": "950", "mean": "155", "stdev": "167" }, { "name": "Chi1_EA.dm.", "index": "6", "type": "numeric", "distinct": "318", "missing": "0", "min": "2", "max": "115", "mean": "32", "stdev": "18" }, { "name": "SdNH", "index": "7", "type": "numeric", "distinct": "173", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "4" }, { "name": "P_VSA_e_5", "index": "8", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "845", "mean": "136", "stdev": "153" }, { "name": "P_VSA_m_3", "index": "9", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "845", "mean": "142", "stdev": "152" }, { "name": "nN", "index": "10", "type": "numeric", "distinct": "11", "missing": "0", "min": "2", "max": "29", "mean": "6", "stdev": "5" }, { "name": "HVcpx", "index": "11", "type": "numeric", "distinct": "236", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "12", "type": "numeric", "distinct": "262", "missing": "0", "min": "7", "max": "37", "mean": "14", "stdev": "4" }, { "name": "GATS1s", "index": "13", "type": "numeric", "distinct": "223", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "14", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "26", "mean": "6", "stdev": "5" }, { "name": "Chi0_EA.dm.", "index": "15", "type": "numeric", "distinct": "306", "missing": "0", "min": "4", "max": "122", "mean": "29", "stdev": "19" }, { "name": "ICR", "index": "16", "type": "numeric", "distinct": "223", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDE", "index": "17", "type": "numeric", "distinct": "236", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "NdNH", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.040", "index": "19", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "25", "mean": "3", "stdev": "4" }, { "name": "Eig09_EA.ri.", "index": "20", "type": "numeric", "distinct": "250", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_09_AN", "index": "21", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_02_DP", "index": "22", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.dm.", "index": "23", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "DECC", "index": "24", "type": "numeric", "distinct": "241", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig10_EA.ri.", "index": "25", "type": "numeric", "distinct": "241", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "26", "type": "numeric", "distinct": "210", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig11_AEA.ri.", "index": "27", "type": "numeric", "distinct": "213", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "Eig11_EA", "index": "28", "type": "numeric", "distinct": "186", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig11_EA.ri.", "index": "29", "type": "numeric", "distinct": "215", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Eig12_AEA.bo.", "index": "30", "type": "numeric", "distinct": "169", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig12_AEA.dm.", "index": "31", "type": "numeric", "distinct": "236", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig12_AEA.ri.", "index": "32", "type": "numeric", "distinct": "200", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig12_EA", "index": "33", "type": "numeric", "distinct": "171", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig12_EA.ed.", "index": "34", "type": "numeric", "distinct": "219", "missing": "0", "min": "-3", "max": "9", "mean": "3", "stdev": "2" }, { "name": "Eig12_EA.ri.", "index": "35", "type": "numeric", "distinct": "192", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GGI4", "index": "36", "type": "numeric", "distinct": "224", "missing": "0", "min": "1", "max": "12", "mean": "3", "stdev": "2" }, { "name": "MSD", "index": "37", "type": "numeric", "distinct": "277", "missing": "0", "min": "4", "max": "21", "mean": "8", "stdev": "2" }, { "name": "SM05_AEA.dm.", "index": "38", "type": "numeric", "distinct": "186", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM06_AEA.dm.", "index": "39", "type": "numeric", "distinct": "171", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM07_AEA.ri.", "index": "40", "type": "numeric", "distinct": "219", "missing": "0", "min": "-3", "max": "9", "mean": "3", "stdev": "2" }, { "name": "CATS2D_06_DA", "index": "41", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "29", "mean": "3", "stdev": "6" }, { "name": "CATS2D_07_PL", "index": "42", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Eig15_AEA.dm.", "index": "43", "type": "numeric", "distinct": "201", "missing": "0", "min": "-2", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_DD", "index": "44", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "4" }, { "name": "CATS2D_08_AN", "index": "45", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "46", "type": "numeric", "distinct": "253", "missing": "0", "min": "23", "max": "353", "mean": "137", "stdev": "54" }, { "name": "GGI5", "index": "47", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "CATS2D_08_PL", "index": "48", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "IDDE", "index": "49", "type": "numeric", "distinct": "204", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SssNH", "index": "50", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "45", "mean": "7", "stdev": "9" }, { "name": "CATS2D_05_DD", "index": "51", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_AP", "index": "52", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig10_EA.dm.", "index": "53", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig11_AEA.ed.", "index": "54", "type": "numeric", "distinct": "208", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig11_EA.ed.", "index": "55", "type": "numeric", "distinct": "222", "missing": "0", "min": "-2", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SM06_AEA.ri.", "index": "56", "type": "numeric", "distinct": "222", "missing": "0", "min": "-2", "max": "9", "mean": "3", "stdev": "2" }, { "name": "SPI", "index": "57", "type": "numeric", "distinct": "285", "missing": "0", "min": "7", "max": "150", "mean": "27", "stdev": "25" }, { "name": "Eig13_EA.ed.", "index": "58", "type": "numeric", "distinct": "214", "missing": "0", "min": "-3", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SM08_AEA.ri.", "index": "59", "type": "numeric", "distinct": "214", "missing": "0", "min": "-3", "max": "9", "mean": "2", "stdev": "2" }, { "name": "GATS8i", "index": "60", "type": "numeric", "distinct": "220", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "N.066", "index": "61", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nRNH2", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_DD", "index": "63", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "Eig14_AEA.bo.", "index": "64", "type": "numeric", "distinct": "199", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eta_F_A", "index": "65", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig07_EA.dm.", "index": "66", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC2s", "index": "67", "type": "numeric", "distinct": "357", "missing": "0", "min": "9", "max": "551", "mean": "86", "stdev": "86" }, { "name": "ATSC6s", "index": "68", "type": "numeric", "distinct": "358", "missing": "0", "min": "16", "max": "1340", "mean": "186", "stdev": "242" } ], "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 }