{ "data_id": "40367", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5785", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5785", "version": 12, "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: CHEMBL5785 (TID: 101333), and it has 168 rows and 67 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": "2016-07-16 11:12:43", "update_comment": null, "last_update": "2016-07-16 11:12:43", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3694166\/data_53195.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5785", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5785 (TID: 101333), and it has 168 rows and 67 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": 168, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.4107142857142857, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.3646468846316844, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.04245155805210326, "Quartile2MeansOfNumericAtts": 4.178092261904762, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.527332715217398, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.34469799901231535, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9843492055957634, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5966294975424802, "MaxKurtosisOfNumericAtts": 7.4754149082008325, "MinMeansOfNumericAtts": 0.10682142857142853, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 395.51232142857145, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.6857112430807002, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 15.562755952380952, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.147942729237706, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.6905940844332241, "MinStdDevOfNumericAtts": 0.016923328839941843, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6032453825824, "MaxStdDevOfNumericAtts": 91.02712491026509, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.08680753102411864, "Quartile3StdDevOfNumericAtts": 3.596222398418444, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.781982142857143, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.9485598071565186, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 24.555604779411766, "Quartile1SkewnessOfNumericAtts": -0.5545390471582438, "AutoCorrelation": 0.3848862275449101, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.26454832041555554 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "59", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "168", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GGI8", "index": "1", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI4", "index": "2", "type": "numeric", "distinct": "149", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "ATS8s", "index": "3", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "PHI", "index": "4", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "2" }, { "name": "Eig07_AEA.dm.", "index": "5", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "TIE", "index": "6", "type": "numeric", "distinct": "166", "missing": "0", "min": "12", "max": "123", "mean": "49", "stdev": "22" }, { "name": "SpMax6_Bh.m.", "index": "7", "type": "numeric", "distinct": "144", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "8", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "9", "type": "numeric", "distinct": "143", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax7_Bh.m.", "index": "10", "type": "numeric", "distinct": "145", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS7m", "index": "11", "type": "numeric", "distinct": "156", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MW", "index": "12", "type": "numeric", "distinct": "159", "missing": "0", "min": "185", "max": "642", "mean": "396", "stdev": "91" }, { "name": "Eig08_AEA.dm.", "index": "13", "type": "numeric", "distinct": "144", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "X2v", "index": "14", "type": "numeric", "distinct": "162", "missing": "0", "min": "3", "max": "14", "mean": "7", "stdev": "2" }, { "name": "Eig11_AEA.dm.", "index": "15", "type": "numeric", "distinct": "137", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "ATS8m", "index": "16", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS8i", "index": "17", "type": "numeric", "distinct": "158", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SpMaxA_EA.ed.", "index": "18", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig02_AEA.bo.", "index": "19", "type": "numeric", "distinct": "141", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "XMOD", "index": "20", "type": "numeric", "distinct": "165", "missing": "0", "min": "43", "max": "143", "mean": "89", "stdev": "20" }, { "name": "GGI9", "index": "21", "type": "numeric", "distinct": "128", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SAacc", "index": "22", "type": "numeric", "distinct": "141", "missing": "0", "min": "37", "max": "233", "mean": "108", "stdev": "41" }, { "name": "Eig09_AEA.dm.", "index": "23", "type": "numeric", "distinct": "150", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS8e", "index": "24", "type": "numeric", "distinct": "158", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATS7v", "index": "25", "type": "numeric", "distinct": "157", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "P_VSA_s_3", "index": "26", "type": "numeric", "distinct": "161", "missing": "0", "min": "10", "max": "89", "mean": "37", "stdev": "16" }, { "name": "MAXDP", "index": "27", "type": "numeric", "distinct": "164", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "2" }, { "name": "ATS7s", "index": "28", "type": "numeric", "distinct": "159", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATSC2p", "index": "29", "type": "numeric", "distinct": "161", "missing": "0", "min": "1", "max": "14", "mean": "7", "stdev": "2" }, { "name": "ATS6m", "index": "30", "type": "numeric", "distinct": "160", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC3s", "index": "31", "type": "numeric", "distinct": "166", "missing": "0", "min": "13", "max": "161", "mean": "45", "stdev": "26" }, { "name": "Eig10_AEA.dm.", "index": "32", "type": "numeric", "distinct": "140", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATS1m", "index": "33", "type": "numeric", "distinct": "148", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS2m", "index": "34", "type": "numeric", "distinct": "150", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig07_AEA.ri.", "index": "35", "type": "numeric", "distinct": "144", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "PW3", "index": "36", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_C", "index": "37", "type": "numeric", "distinct": "166", "missing": "0", "min": "6", "max": "50", "mean": "23", "stdev": "9" }, { "name": "SaaNH", "index": "38", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "Chi1_EA.ri.", "index": "39", "type": "numeric", "distinct": "165", "missing": "0", "min": "8", "max": "27", "mean": "16", "stdev": "4" }, { "name": "SpMin8_Bh.p.", "index": "40", "type": "numeric", "distinct": "132", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_alpha", "index": "41", "type": "numeric", "distinct": "153", "missing": "0", "min": "7", "max": "21", "mean": "13", "stdev": "3" }, { "name": "Eig15_AEA.dm.", "index": "42", "type": "numeric", "distinct": "144", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpAD_EA.ri.", "index": "43", "type": "numeric", "distinct": "165", "missing": "0", "min": "18", "max": "80", "mean": "45", "stdev": "11" }, { "name": "S1K", "index": "44", "type": "numeric", "distinct": "153", "missing": "0", "min": "8", "max": "32", "mean": "19", "stdev": "5" }, { "name": "SpMaxA_EA.bo.", "index": "45", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "VvdwZAZ", "index": "46", "type": "numeric", "distinct": "161", "missing": "0", "min": "134", "max": "567", "mean": "333", "stdev": "85" }, { "name": "X0sol", "index": "47", "type": "numeric", "distinct": "136", "missing": "0", "min": "10", "max": "32", "mean": "20", "stdev": "4" }, { "name": "GGI7", "index": "48", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "Dz", "index": "49", "type": "numeric", "distinct": "114", "missing": "0", "min": "31", "max": "103", "mean": "62", "stdev": "14" }, { "name": "Eig06_AEA.dm.", "index": "50", "type": "numeric", "distinct": "158", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMin8_Bh.v.", "index": "51", "type": "numeric", "distinct": "124", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig14_AEA.dm.", "index": "52", "type": "numeric", "distinct": "143", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Chi1_AEA.bo.", "index": "53", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.dm.", "index": "54", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.ed.", "index": "55", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "Chi1_AEA.ri.", "index": "56", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "Chi1_EA", "index": "57", "type": "numeric", "distinct": "159", "missing": "0", "min": "7", "max": "26", "mean": "16", "stdev": "4" }, { "name": "SpMax8_Bh.m.", "index": "58", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS3m", "index": "59", "type": "numeric", "distinct": "150", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "CID", "index": "60", "type": "numeric", "distinct": "137", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "BBI", "index": "61", "type": "numeric", "distinct": "45", "missing": "0", "min": "21", "max": "83", "mean": "45", "stdev": "11" }, { "name": "MPC02", "index": "62", "type": "numeric", "distinct": "45", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MWC02", "index": "63", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM02_EA", "index": "64", "type": "numeric", "distinct": "45", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SRW04", "index": "65", "type": "numeric", "distinct": "86", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM1", "index": "66", "type": "numeric", "distinct": "66", "missing": "0", "min": "72", "max": "270", "mean": "153", "stdev": "37" }, { "name": "Eig12_AEA.dm.", "index": "67", "type": "numeric", "distinct": "136", "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 }