{ "data_id": "34872", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3807", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3807", "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: CHEMBL3807 (TID: 10258), and it has 434 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 16:31:02", "update_comment": null, "last_update": "2016-07-15 16:31:02", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3541462\/data_53305.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3807", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3807 (TID: 10258), and it has 434 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": 434, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.9589460201622111, "Dimensionality": 0.16129032258064516, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 5.743232718894009, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.14218673934564782, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 752.8802618943073, "Quartile2SkewnessOfNumericAtts": 0.04915948774738539, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.8454087128914898, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4026128174001298, "MinMeansOfNumericAtts": 0.22119815668202714, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 97.7052524679914, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.0971767824892162, "MaxMeansOfNumericAtts": 71579.86405529956, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 56.452535714285716, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -7.535222525928515, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.1608727465937923, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5930142344595908, "MaxSkewnessOfNumericAtts": 3.1167359833838995, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.07901353684827428, "Quartile3StdDevOfNumericAtts": 27.343058556998713, "MaxStdDevOfNumericAtts": 49881.34606914392, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.5653294930875576, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 4.5193366344823, "Quartile1SkewnessOfNumericAtts": -1.1688712020835779, "MeanMeansOfNumericAtts": 1128.373319742203, "Quartile1StdDevOfNumericAtts": 0.7011660827701214, "AutoCorrelation": 0.37056120092378775, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "312", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "434", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SM07_EA.bo.", "index": "1", "type": "numeric", "distinct": "313", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "TPSA.Tot.", "index": "2", "type": "numeric", "distinct": "189", "missing": "0", "min": "17", "max": "444", "mean": "124", "stdev": "50" }, { "name": "SM08_EA.bo.", "index": "3", "type": "numeric", "distinct": "326", "missing": "0", "min": "10", "max": "14", "mean": "12", "stdev": "1" }, { "name": "ATS1m", "index": "4", "type": "numeric", "distinct": "304", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "5", "type": "numeric", "distinct": "177", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATSC3s", "index": "6", "type": "numeric", "distinct": "409", "missing": "0", "min": "19", "max": "605", "mean": "114", "stdev": "95" }, { "name": "TPSA.NO.", "index": "7", "type": "numeric", "distinct": "165", "missing": "0", "min": "17", "max": "444", "mean": "109", "stdev": "47" }, { "name": "ATSC3e", "index": "8", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMax3_Bh.m.", "index": "9", "type": "numeric", "distinct": "229", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "0" }, { "name": "ATSC2s", "index": "10", "type": "numeric", "distinct": "404", "missing": "0", "min": "10", "max": "431", "mean": "98", "stdev": "74" }, { "name": "ZM1Mad", "index": "11", "type": "numeric", "distinct": "345", "missing": "0", "min": "83", "max": "571", "mean": "254", "stdev": "73" }, { "name": "ZM2V", "index": "12", "type": "numeric", "distinct": "273", "missing": "0", "min": "105", "max": "1182", "mean": "531", "stdev": "156" }, { "name": "nHet", "index": "13", "type": "numeric", "distinct": "21", "missing": "0", "min": "1", "max": "26", "mean": "9", "stdev": "4" }, { "name": "SM04_EA.bo.", "index": "14", "type": "numeric", "distinct": "299", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "MW", "index": "15", "type": "numeric", "distinct": "349", "missing": "0", "min": "118", "max": "941", "mean": "529", "stdev": "131" }, { "name": "ZM2Per", "index": "16", "type": "numeric", "distinct": "398", "missing": "0", "min": "163", "max": "1867", "mean": "835", "stdev": "248" }, { "name": "X2sol", "index": "17", "type": "numeric", "distinct": "350", "missing": "0", "min": "6", "max": "30", "mean": "17", "stdev": "4" }, { "name": "Eig15_EA", "index": "18", "type": "numeric", "distinct": "264", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SM09_AEA.dm.", "index": "19", "type": "numeric", "distinct": "264", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ZM2MulPer", "index": "20", "type": "numeric", "distinct": "398", "missing": "0", "min": "117", "max": "1264", "mean": "568", "stdev": "167" }, { "name": "ATS2m", "index": "21", "type": "numeric", "distinct": "299", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "22", "type": "numeric", "distinct": "234", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ZM1Per", "index": "23", "type": "numeric", "distinct": "394", "missing": "0", "min": "183", "max": "1844", "mean": "795", "stdev": "245" }, { "name": "Eig14_EA.ed.", "index": "24", "type": "numeric", "distinct": "282", "missing": "0", "min": "-7", "max": "5", "mean": "2", "stdev": "2" }, { "name": "SM09_AEA.ri.", "index": "25", "type": "numeric", "distinct": "282", "missing": "0", "min": "-7", "max": "5", "mean": "2", "stdev": "2" }, { "name": "Eig15_AEA.ri.", "index": "26", "type": "numeric", "distinct": "296", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig15_EA.ed.", "index": "27", "type": "numeric", "distinct": "272", "missing": "0", "min": "-7", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SM10_AEA.ri.", "index": "28", "type": "numeric", "distinct": "272", "missing": "0", "min": "-7", "max": "5", "mean": "1", "stdev": "2" }, { "name": "SpMax2_Bh.m.", "index": "29", "type": "numeric", "distinct": "197", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "0" }, { "name": "P_VSA_s_5", "index": "30", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "276", "mean": "21", "stdev": "26" }, { "name": "ZM2Kup", "index": "31", "type": "numeric", "distinct": "378", "missing": "0", "min": "60", "max": "1282", "mean": "542", "stdev": "160" }, { "name": "P_VSA_e_3", "index": "32", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "276", "mean": "32", "stdev": "29" }, { "name": "Psi_i_s", "index": "33", "type": "numeric", "distinct": "317", "missing": "0", "min": "26", "max": "216", "mean": "92", "stdev": "26" }, { "name": "ATSC2e", "index": "34", "type": "numeric", "distinct": "301", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ZM1MulPer", "index": "35", "type": "numeric", "distinct": "396", "missing": "0", "min": "159", "max": "1433", "mean": "602", "stdev": "193" }, { "name": "ZM1V", "index": "36", "type": "numeric", "distinct": "214", "missing": "0", "min": "136", "max": "1310", "mean": "555", "stdev": "176" }, { "name": "X1sol", "index": "37", "type": "numeric", "distinct": "323", "missing": "0", "min": "4", "max": "31", "mean": "18", "stdev": "4" }, { "name": "P_VSA_i_4", "index": "38", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "161", "mean": "37", "stdev": "32" }, { "name": "SpMax5_Bh.s.", "index": "39", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMax8_Bh.m.", "index": "40", "type": "numeric", "distinct": "296", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "41", "type": "numeric", "distinct": "121", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Psi_e_0", "index": "42", "type": "numeric", "distinct": "411", "missing": "0", "min": "3", "max": "26", "mean": "14", "stdev": "4" }, { "name": "Eig13_EA.ed.", "index": "43", "type": "numeric", "distinct": "271", "missing": "0", "min": "-6", "max": "7", "mean": "2", "stdev": "2" }, { "name": "SM08_AEA.ri.", "index": "44", "type": "numeric", "distinct": "271", "missing": "0", "min": "-6", "max": "7", "mean": "2", "stdev": "2" }, { "name": "ATSC1s", "index": "45", "type": "numeric", "distinct": "383", "missing": "0", "min": "5", "max": "199", "mean": "33", "stdev": "28" }, { "name": "Eig15_EA.ri.", "index": "46", "type": "numeric", "distinct": "299", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig14_EA.bo.", "index": "47", "type": "numeric", "distinct": "278", "missing": "0", "min": "-3", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig13_AEA.bo.", "index": "48", "type": "numeric", "distinct": "260", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ATS5m", "index": "49", "type": "numeric", "distinct": "358", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "50", "type": "numeric", "distinct": "271", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "nHAcc", "index": "51", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "26", "mean": "8", "stdev": "3" }, { "name": "Eig12_EA.bo.", "index": "52", "type": "numeric", "distinct": "274", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X0", "index": "53", "type": "numeric", "distinct": "276", "missing": "0", "min": "5", "max": "49", "mean": "26", "stdev": "7" }, { "name": "ON0", "index": "54", "type": "numeric", "distinct": "161", "missing": "0", "min": "4", "max": "39", "mean": "20", "stdev": "5" }, { "name": "IDDM", "index": "55", "type": "numeric", "distinct": "253", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "nN", "index": "56", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "nSO2N", "index": "57", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "58", "type": "numeric", "distinct": "376", "missing": "0", "min": "7", "max": "139", "mean": "76", "stdev": "20" }, { "name": "Eig13_EA", "index": "59", "type": "numeric", "distinct": "252", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM07_AEA.dm.", "index": "60", "type": "numeric", "distinct": "252", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Dz", "index": "61", "type": "numeric", "distinct": "197", "missing": "0", "min": "13", "max": "160", "mean": "81", "stdev": "21" }, { "name": "Eta_alpha", "index": "62", "type": "numeric", "distinct": "270", "missing": "0", "min": "3", "max": "29", "mean": "18", "stdev": "4" }, { "name": "GMTIV", "index": "63", "type": "numeric", "distinct": "408", "missing": "0", "min": "435", "max": "359530", "mean": "71580", "stdev": "49881" }, { "name": "SpMax4_Bh.s.", "index": "64", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig12_AEA.bo.", "index": "65", "type": "numeric", "distinct": "268", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_AEA.ri.", "index": "66", "type": "numeric", "distinct": "272", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig14_EA", "index": "67", "type": "numeric", "distinct": "262", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig14_EA.ri.", "index": "68", "type": "numeric", "distinct": "282", "missing": "0", "min": "-2", "max": "2", "mean": "1", "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 }