{ "data_id": "34309", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1908", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1908", "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: CHEMBL1908 (TID: 76), and it has 454 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 15:01:33", "update_comment": null, "last_update": "2016-07-15 15:01:33", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3525766\/data_52666.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1908", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1908 (TID: 76), and it has 454 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": 454, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "MaxMeansOfNumericAtts": 37.72605066079295, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9505002562760958, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 4.815280837004405, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1836240330170067, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 5.062707319205976, "MinStdDevOfNumericAtts": 0.014660012085016773, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.7401177358556157, "MaxStdDevOfNumericAtts": 34.146931824260136, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.29785540259514653, "Quartile3StdDevOfNumericAtts": 1.5050689007269709, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.48127753303964743, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.4614806694746985, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 5.069184615384615, "Quartile1SkewnessOfNumericAtts": -0.11563236030485696, "AutoCorrelation": 0.22821192052980108, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.11277366077840625, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.14537444933920704, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.26137246899120736, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5096783978956579, "Quartile2MeansOfNumericAtts": 1.5066299559471366, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.275586868191824, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3762859339346109, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8422325984875072, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5070757038809962, "MaxKurtosisOfNumericAtts": 23.755189900321444, "MinMeansOfNumericAtts": -0.12750881057268723, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "373", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "454", "missing": "0", "identifier": "1", "distr": [] }, { "name": "nImidazoles", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "C.042", "index": "2", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "N.073", "index": "3", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "D.Dtr05", "index": "4", "type": "numeric", "distinct": "194", "missing": "0", "min": "0", "max": "230", "mean": "38", "stdev": "34" }, { "name": "C.027", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nPyridines", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "MATS1i", "index": "7", "type": "numeric", "distinct": "226", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_6", "index": "8", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "67", "mean": "8", "stdev": "10" }, { "name": "SRW05", "index": "9", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SaasN", "index": "10", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.006", "index": "11", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "NaasN", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "H.048", "index": "13", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "N.", "index": "14", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "18", "mean": "6", "stdev": "3" }, { "name": "CATS2D_02_AA", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "C.033", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "GATS1i", "index": "17", "type": "numeric", "distinct": "263", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nN", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "6", "mean": "2", "stdev": "1" }, { "name": "Chi1_EA.dm.", "index": "19", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "39", "mean": "15", "stdev": "8" }, { "name": "nR05", "index": "20", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "21", "type": "numeric", "distinct": "35", "missing": "0", "min": "17", "max": "97", "mean": "29", "stdev": "17" }, { "name": "Eta_betaS_A", "index": "22", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_04_LL", "index": "23", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "35", "mean": "10", "stdev": "8" }, { "name": "GATS4v", "index": "24", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "25", "type": "numeric", "distinct": "179", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS1v", "index": "26", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "27", "type": "numeric", "distinct": "261", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SRW07", "index": "28", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SRW09", "index": "29", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "3" }, { "name": "P_VSA_i_4", "index": "30", "type": "numeric", "distinct": "51", "missing": "0", "min": "17", "max": "110", "mean": "30", "stdev": "17" }, { "name": "SpMin4_Bh.i.", "index": "31", "type": "numeric", "distinct": "263", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS4p", "index": "32", "type": "numeric", "distinct": "276", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_LL", "index": "33", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "43", "mean": "13", "stdev": "8" }, { "name": "IC1", "index": "34", "type": "numeric", "distinct": "275", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "35", "type": "numeric", "distinct": "157", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SssCH2", "index": "36", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "GATS3i", "index": "37", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS3v", "index": "38", "type": "numeric", "distinct": "246", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "39", "type": "numeric", "distinct": "165", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS3i", "index": "40", "type": "numeric", "distinct": "243", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS4i", "index": "41", "type": "numeric", "distinct": "259", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_01_LL", "index": "42", "type": "numeric", "distinct": "25", "missing": "0", "min": "1", "max": "25", "mean": "11", "stdev": "5" }, { "name": "SpMin2_Bh.p.", "index": "43", "type": "numeric", "distinct": "180", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "44", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "37", "mean": "14", "stdev": "7" }, { "name": "CATS2D_04_AL", "index": "45", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "5", "stdev": "3" }, { "name": "SpMin1_Bh.p.", "index": "46", "type": "numeric", "distinct": "151", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax2_Bh.i.", "index": "47", "type": "numeric", "distinct": "162", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NssCH2", "index": "48", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "MATS4p", "index": "49", "type": "numeric", "distinct": "273", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaNH", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaaNH", "index": "51", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMin1_Bh.m.", "index": "52", "type": "numeric", "distinct": "182", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS4v", "index": "53", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.p.", "index": "54", "type": "numeric", "distinct": "257", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpDiam_EA.ri.", "index": "55", "type": "numeric", "distinct": "277", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "56", "type": "numeric", "distinct": "200", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS3m", "index": "57", "type": "numeric", "distinct": "242", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS3v", "index": "58", "type": "numeric", "distinct": "245", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_04_AA", "index": "59", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "SM12_EA.ed.", "index": "60", "type": "numeric", "distinct": "264", "missing": "0", "min": "24", "max": "34", "mean": "29", "stdev": "2" }, { "name": "PW4", "index": "61", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM10_EA.ed.", "index": "62", "type": "numeric", "distinct": "262", "missing": "0", "min": "20", "max": "29", "mean": "24", "stdev": "1" }, { "name": "SM11_EA.ed.", "index": "63", "type": "numeric", "distinct": "266", "missing": "0", "min": "22", "max": "31", "mean": "26", "stdev": "2" }, { "name": "GATS3p", "index": "64", "type": "numeric", "distinct": "256", "missing": "0", "min": "1", "max": "1", "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 }