{ "data_id": "31358", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3433", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3433", "version": 11, "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: CHEMBL3433 (TID: 20126), and it has 182 rows and 65 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 07:22:16", "update_comment": null, "last_update": "2016-07-15 07:22:16", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3446636\/data_52951.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3433", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3433 (TID: 20126), and it has 182 rows and 65 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": 182, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 13.794669257490048, "MinMeansOfNumericAtts": 0.023148351648351648, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.5311769434648175, "MaxMeansOfNumericAtts": 306.75999450549455, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 9.021137362637361, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.9120082417538653, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 0.8214654860499127, "MaxSkewnessOfNumericAtts": 2.253904487951527, "MinStdDevOfNumericAtts": 0.033607654935759804, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.696121511560255, "MaxStdDevOfNumericAtts": 502.52986041084887, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.14389655751085395, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.6277472527472536, "MeanKurtosisOfNumericAtts": 1.3267977191263605, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 16.09341341991342, "Quartile1SkewnessOfNumericAtts": -0.2205274703312792, "AutoCorrelation": -0.14429834254143659, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.24420231333592152, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.36813186813186816, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8882486122400883, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.2910899385003129, "Quartile2MeansOfNumericAtts": 5.113491758241758, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 15.361418708808063, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.34782671844758484, "Quartile2StdDevOfNumericAtts": 0.5355016241127062, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6460801337033983, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "119", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "182", "missing": "0", "identifier": "1", "distr": [] }, { "name": "RBF", "index": "1", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "2", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "1" }, { "name": "RCI", "index": "3", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RFD", "index": "4", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "D.Dtr05", "index": "5", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "1557", "mean": "178", "stdev": "293" }, { "name": "CATS2D_08_AA", "index": "6", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "3" }, { "name": "D.Dtr09", "index": "7", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "1956", "mean": "307", "stdev": "503" }, { "name": "Eig08_AEA.ed.", "index": "8", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GATS3p", "index": "9", "type": "numeric", "distinct": "114", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MWC06", "index": "10", "type": "numeric", "distinct": "117", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "MWC07", "index": "11", "type": "numeric", "distinct": "119", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "MWC08", "index": "12", "type": "numeric", "distinct": "120", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "GATS7i", "index": "13", "type": "numeric", "distinct": "124", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig05_EA.dm.", "index": "14", "type": "numeric", "distinct": "36", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig08_EA.dm.", "index": "15", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "16", "type": "numeric", "distinct": "96", "missing": "0", "min": "2", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "17", "type": "numeric", "distinct": "96", "missing": "0", "min": "2", "max": "9", "mean": "7", "stdev": "1" }, { "name": "CATS2D_05_AA", "index": "18", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "3" }, { "name": "MWC09", "index": "19", "type": "numeric", "distinct": "116", "missing": "0", "min": "11", "max": "12", "mean": "12", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "20", "type": "numeric", "distinct": "110", "missing": "0", "min": "2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "21", "type": "numeric", "distinct": "110", "missing": "0", "min": "2", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SM15_EA.dm.", "index": "22", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "5" }, { "name": "Eig05_EA.ed.", "index": "23", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "24", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "10", "mean": "8", "stdev": "1" }, { "name": "Eig09_EA.dm.", "index": "25", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "26", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "SM04_EA.dm.", "index": "27", "type": "numeric", "distinct": "101", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SM04_EA", "index": "28", "type": "numeric", "distinct": "101", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "MWC05", "index": "29", "type": "numeric", "distinct": "114", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "30", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA", "index": "31", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM03_AEA.dm.", "index": "32", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Qindex", "index": "33", "type": "numeric", "distinct": "32", "missing": "0", "min": "14", "max": "63", "mean": "35", "stdev": "8" }, { "name": "Eig03_AEA.ri.", "index": "34", "type": "numeric", "distinct": "73", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NNRS", "index": "35", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig05_AEA.dm.", "index": "36", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "NsssCH", "index": "37", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "GGI3", "index": "38", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SpMax3_Bh.s.", "index": "39", "type": "numeric", "distinct": "40", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "MPC05", "index": "40", "type": "numeric", "distinct": "83", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SRW06", "index": "41", "type": "numeric", "distinct": "111", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Eig10_AEA.ed.", "index": "42", "type": "numeric", "distinct": "102", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MWC10", "index": "43", "type": "numeric", "distinct": "115", "missing": "0", "min": "11", "max": "13", "mean": "13", "stdev": "0" }, { "name": "TWC", "index": "44", "type": "numeric", "distinct": "118", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "45", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "487", "mean": "149", "stdev": "108" }, { "name": "SpMax6_Bh.s.", "index": "46", "type": "numeric", "distinct": "65", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "Eig03_AEA.ed.", "index": "47", "type": "numeric", "distinct": "65", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig07_EA.dm.", "index": "48", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig03_EA.ed.", "index": "49", "type": "numeric", "distinct": "75", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "1" }, { "name": "SM12_AEA.dm.", "index": "50", "type": "numeric", "distinct": "75", "missing": "0", "min": "6", "max": "11", "mean": "9", "stdev": "1" }, { "name": "MPC06", "index": "51", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC07", "index": "52", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig11_AEA.ed.", "index": "53", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "MATS7i", "index": "54", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "55", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig09_AEA.ri.", "index": "56", "type": "numeric", "distinct": "123", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X2v", "index": "57", "type": "numeric", "distinct": "162", "missing": "0", "min": "6", "max": "29", "mean": "15", "stdev": "3" }, { "name": "SM02_EA.dm.", "index": "58", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Ram", "index": "59", "type": "numeric", "distinct": "26", "missing": "0", "min": "5", "max": "36", "mean": "18", "stdev": "5" }, { "name": "GGI10", "index": "60", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpAD_EA.dm.", "index": "61", "type": "numeric", "distinct": "103", "missing": "0", "min": "4", "max": "60", "mean": "21", "stdev": "10" }, { "name": "nDB", "index": "62", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "NdO", "index": "63", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "2" }, { "name": "O.058", "index": "64", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "13", "mean": "4", "stdev": "3" }, { "name": "SdO", "index": "65", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "184", "mean": "57", "stdev": "35" } ], "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 }