{ "data_id": "25957", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3788", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3788", "version": 7, "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: CHEMBL3788 (TID: 30003), and it has 778 rows and 69 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": "2016-07-14 18:08:17", "update_comment": null, "last_update": "2016-07-14 18:08:17", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3289484\/data_53532.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3788", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3788 (TID: 30003), and it has 778 rows and 69 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": 778, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.606422236503856, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 14.224564739058188, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 579.7418731178847, "Quartile1SkewnessOfNumericAtts": -1.2132231021469475, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.43674610882058623, "AutoCorrelation": 0.22720205920205958, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 3.5447547472658956, "Dimensionality": 0.09125964010282776, "MeanSkewnessOfNumericAtts": 0.8672899121954782, "Quartile2MeansOfNumericAtts": 3.1930790488431873, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 531.0518190116052, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4765372598894719, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.598437318093862, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7176616937336049, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 141.4663493680258, "MinMeansOfNumericAtts": -0.009722365038560466, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 17945.6323907455, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 7.087065737926038, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 19.261942159383032, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.910426693492626, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 8.881546654019267, "MinStdDevOfNumericAtts": 0.05799763194515682, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.504340525415029, "MaxStdDevOfNumericAtts": 17110.435211546337, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.5341357903442767, "Quartile3StdDevOfNumericAtts": 4.850529542088038 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "94", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "778", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eta_beta", "index": "1", "type": "numeric", "distinct": "153", "missing": "0", "min": "15", "max": "94", "mean": "37", "stdev": "9" }, { "name": "CATS2D_08_DD", "index": "2", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "P_VSA_e_3", "index": "3", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "472", "mean": "77", "stdev": "40" }, { "name": "Eig07_AEA.bo.", "index": "4", "type": "numeric", "distinct": "501", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eta_FL", "index": "5", "type": "numeric", "distinct": "697", "missing": "0", "min": "3", "max": "18", "mean": "7", "stdev": "2" }, { "name": "D.Dtr09", "index": "6", "type": "numeric", "distinct": "430", "missing": "0", "min": "0", "max": "439", "mean": "77", "stdev": "76" }, { "name": "TPSA.Tot.", "index": "7", "type": "numeric", "distinct": "510", "missing": "0", "min": "9", "max": "393", "mean": "95", "stdev": "36" }, { "name": "Eta_betaP", "index": "8", "type": "numeric", "distinct": "56", "missing": "0", "min": "8", "max": "48", "mean": "20", "stdev": "5" }, { "name": "DECC", "index": "9", "type": "numeric", "distinct": "534", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "10", "type": "numeric", "distinct": "728", "missing": "0", "min": "57", "max": "631", "mean": "194", "stdev": "55" }, { "name": "CATS2D_08_DP", "index": "11", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Eig07_EA.bo.", "index": "12", "type": "numeric", "distinct": "517", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Ui", "index": "13", "type": "numeric", "distinct": "30", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "14", "type": "numeric", "distinct": "414", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "X0sol", "index": "15", "type": "numeric", "distinct": "457", "missing": "0", "min": "8", "max": "61", "mean": "19", "stdev": "5" }, { "name": "SpMax3_Bh.v.", "index": "16", "type": "numeric", "distinct": "409", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "17", "type": "numeric", "distinct": "487", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "18", "type": "numeric", "distinct": "585", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "19", "type": "numeric", "distinct": "585", "missing": "0", "min": "-4", "max": "8", "mean": "3", "stdev": "2" }, { "name": "Eta_F", "index": "20", "type": "numeric", "distinct": "763", "missing": "0", "min": "6", "max": "92", "mean": "28", "stdev": "10" }, { "name": "SpMax2_Bh.i.", "index": "21", "type": "numeric", "distinct": "266", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig07_EA", "index": "22", "type": "numeric", "distinct": "481", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "23", "type": "numeric", "distinct": "481", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "24", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "3" }, { "name": "Vindex", "index": "25", "type": "numeric", "distinct": "218", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "UNIP", "index": "26", "type": "numeric", "distinct": "196", "missing": "0", "min": "19", "max": "782", "mean": "112", "stdev": "59" }, { "name": "H.050", "index": "27", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "nHDon", "index": "28", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "2" }, { "name": "Eig09_AEA.dm.", "index": "29", "type": "numeric", "distinct": "534", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SssNH", "index": "30", "type": "numeric", "distinct": "498", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "SMTIV", "index": "31", "type": "numeric", "distinct": "747", "missing": "0", "min": "1289", "max": "326954", "mean": "17946", "stdev": "17110" }, { "name": "SMTI", "index": "32", "type": "numeric", "distinct": "696", "missing": "0", "min": "637", "max": "168075", "mean": "10372", "stdev": "9507" }, { "name": "Eig09_AEA.ri.", "index": "33", "type": "numeric", "distinct": "527", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig09_EA.ri.", "index": "34", "type": "numeric", "distinct": "514", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Xindex", "index": "35", "type": "numeric", "distinct": "267", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig09_EA", "index": "36", "type": "numeric", "distinct": "473", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "37", "type": "numeric", "distinct": "473", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ZM2Mad", "index": "38", "type": "numeric", "distinct": "753", "missing": "0", "min": "79", "max": "698", "mean": "200", "stdev": "54" }, { "name": "MSD", "index": "39", "type": "numeric", "distinct": "657", "missing": "0", "min": "3", "max": "17", "mean": "6", "stdev": "2" }, { "name": "LPRS", "index": "40", "type": "numeric", "distinct": "706", "missing": "0", "min": "35", "max": "521", "mean": "137", "stdev": "48" }, { "name": "P_VSA_MR_6", "index": "41", "type": "numeric", "distinct": "660", "missing": "0", "min": "7", "max": "219", "mean": "103", "stdev": "38" }, { "name": "GMTI", "index": "42", "type": "numeric", "distinct": "693", "missing": "0", "min": "583", "max": "176048", "mean": "10908", "stdev": "10040" }, { "name": "nBM", "index": "43", "type": "numeric", "distinct": "29", "missing": "0", "min": "7", "max": "42", "mean": "20", "stdev": "5" }, { "name": "Uc", "index": "44", "type": "numeric", "distinct": "29", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "45", "type": "numeric", "distinct": "657", "missing": "0", "min": "0", "max": "59", "mean": "18", "stdev": "9" }, { "name": "X3sol", "index": "46", "type": "numeric", "distinct": "675", "missing": "0", "min": "4", "max": "32", "mean": "10", "stdev": "3" }, { "name": "Eig08_EA.ri.", "index": "47", "type": "numeric", "distinct": "525", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "Hy", "index": "48", "type": "numeric", "distinct": "407", "missing": "0", "min": "-1", "max": "15", "mean": "1", "stdev": "1" }, { "name": "Eig07_AEA.ri.", "index": "49", "type": "numeric", "distinct": "549", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax2_Bh.e.", "index": "50", "type": "numeric", "distinct": "270", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "51", "type": "numeric", "distinct": "486", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Yindex", "index": "52", "type": "numeric", "distinct": "410", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "53", "type": "numeric", "distinct": "528", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "0" }, { "name": "piPC01", "index": "54", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SCBO", "index": "55", "type": "numeric", "distinct": "96", "missing": "0", "min": "17", "max": "104", "mean": "41", "stdev": "10" }, { "name": "Eig15_AEA.dm.", "index": "56", "type": "numeric", "distinct": "557", "missing": "0", "min": "-2", "max": "3", "mean": "0", "stdev": "1" }, { "name": "CATS2D_05_DL", "index": "57", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "28", "mean": "3", "stdev": "3" }, { "name": "X0", "index": "58", "type": "numeric", "distinct": "349", "missing": "0", "min": "8", "max": "55", "mean": "19", "stdev": "5" }, { "name": "Eig08_AEA.dm.", "index": "59", "type": "numeric", "distinct": "519", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_AEA.bo.", "index": "60", "type": "numeric", "distinct": "496", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "61", "type": "numeric", "distinct": "389", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "N.069", "index": "62", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "63", "type": "numeric", "distinct": "525", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "IDE", "index": "64", "type": "numeric", "distinct": "545", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "65", "type": "numeric", "distinct": "667", "missing": "0", "min": "0", "max": "77", "mean": "23", "stdev": "14" }, { "name": "SpMax6_Bh.m.", "index": "66", "type": "numeric", "distinct": "496", "missing": "0", "min": "2", "max": "7", "mean": "3", "stdev": "0" }, { "name": "X4sol", "index": "67", "type": "numeric", "distinct": "677", "missing": "0", "min": "4", "max": "24", "mean": "9", "stdev": "2" }, { "name": "Eig08_EA", "index": "68", "type": "numeric", "distinct": "484", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "69", "type": "numeric", "distinct": "484", "missing": "0", "min": "-1", "max": "3", "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 }