DEVELOPMENT... { "data_id": "30977", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3949", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3949", "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: CHEMBL3949 (TID: 17081), and it has 440 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": "unknown", "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 06:22:42", "update_comment": null, "last_update": "2016-07-15 06:22:42", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3434725\/data_52934.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3949", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3949 (TID: 17081), and it has 440 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": 440, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.50746268656717, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 2.914036778463153, "Quartile1MeansOfNumericAtts": 1.5030778409090908, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": 1.0657417475794437, "Quartile1StdDevOfNumericAtts": 0.276312728015464, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 7.219079078443234, "Quartile2MeansOfNumericAtts": 4.499915909090909, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 2.0431967901241386, "Quartile2StdDevOfNumericAtts": 0.5293520102991922, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 15.34182009041657, "Quartile3MeansOfNumericAtts": 20.536797727272727, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 3.5119704193317793, "Quartile3StdDevOfNumericAtts": 6.02190597216365, "AutoCorrelation": -0.05698861047836075, "MeanMeansOfNumericAtts": 29.083935847107437, "ClassEntropy": null, "Dimensionality": 0.15227272727272728, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 32.39472890940584, "MaxMeansOfNumericAtts": 669.3550454545455, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 5.6076721896424235, "MaxStdDevOfNumericAtts": 220.6016772038785, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 10.325731446911249, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 2.304600707852791, "MeanStdDevOfNumericAtts": 12.795674953162623, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.4177345442289015, "MinMeansOfNumericAtts": -0.04182954545454545, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0618177288468063, "MinStdDevOfNumericAtts": 0.03950370404215687, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "264", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "nR07", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRCOOH", "index": "34", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "D.Dtr07", "index": "48", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "204", "mean": "16", "stdev": "53" }, { "name": "ATSC6p", "index": "47", "type": "numeric", "distinct": "416", "missing": "0", "min": "6", "max": "50", "mean": "17", "stdev": "6" }, { "name": "CIC1", "index": "46", "type": "numeric", "distinct": "297", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "45", "type": "numeric", "distinct": "33", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS6e", "index": "44", "type": "numeric", "distinct": "333", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "ATS6i", "index": "43", "type": "numeric", "distinct": "350", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MATS3s", "index": "42", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8v", "index": "41", "type": "numeric", "distinct": "353", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpAD_AEA.ri.", "index": "40", "type": "numeric", "distinct": "405", "missing": "0", "min": "34", "max": "173", "mean": "63", "stdev": "18" }, { "name": "ATSC3s", "index": "39", "type": "numeric", "distinct": "422", "missing": "0", "min": "28", "max": "493", "mean": "84", "stdev": "72" }, { "name": "ATS2p", "index": "38", "type": "numeric", "distinct": "288", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nCconj", "index": "37", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATS2v", "index": "36", "type": "numeric", "distinct": "268", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "35", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Psi_i_1", "index": "33", "type": "numeric", "distinct": "382", "missing": "0", "min": "12", "max": "62", "mean": "23", "stdev": "7" }, { "name": "SpAD_EA", "index": "50", "type": "numeric", "distinct": "309", "missing": "0", "min": "34", "max": "173", "mean": "63", "stdev": "18" }, { "name": "ATSC5p", "index": "51", "type": "numeric", "distinct": "411", "missing": "0", "min": "7", "max": "44", "mean": "17", "stdev": "5" }, { "name": "SpAD_AEA.bo.", "index": "52", "type": "numeric", "distinct": "332", "missing": "0", "min": "35", "max": "176", "mean": "63", "stdev": "18" }, { "name": "SpAD_AEA.dm.", "index": "53", "type": "numeric", "distinct": "383", "missing": "0", "min": "35", "max": "183", "mean": "65", "stdev": "19" }, { "name": "Eta_alpha", "index": "54", "type": "numeric", "distinct": "178", "missing": "0", "min": "10", "max": "52", "mean": "18", "stdev": "5" }, { "name": "ATS3m", "index": "55", "type": "numeric", "distinct": "289", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SaaaC", "index": "56", "type": "numeric", "distinct": "164", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATS6m", "index": "57", "type": "numeric", "distinct": "314", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_05_DA", "index": "58", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "18", "mean": "2", "stdev": "3" }, { "name": "IC4", "index": "59", "type": "numeric", "distinct": "283", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "0" }, { "name": "Chi1_AEA.bo.", "index": "60", "type": "numeric", "distinct": "287", "missing": "0", "min": "11", "max": "57", "mean": "21", "stdev": "6" }, { "name": "Chi1_AEA.dm.", "index": "61", "type": "numeric", "distinct": "287", "missing": "0", "min": "11", "max": "57", "mean": "21", "stdev": "6" }, { "name": "Chi1_AEA.ed.", "index": "62", "type": "numeric", "distinct": "287", "missing": "0", "min": "11", "max": "57", "mean": "21", "stdev": "6" }, { "name": "Chi1_AEA.ri.", "index": "63", "type": "numeric", "distinct": "287", "missing": "0", "min": "11", "max": "57", "mean": "21", "stdev": "6" }, { "name": "Chi1_EA", "index": "64", "type": "numeric", "distinct": "287", "missing": "0", "min": "11", "max": "57", "mean": "21", "stdev": "6" }, { "name": "P_VSA_LogP_2", "index": "65", "type": "numeric", "distinct": "153", "missing": "0", "min": "0", "max": "249", "mean": "41", "stdev": "43" }, { "name": "GGI10", "index": "8", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC2i", "index": "16", "type": "numeric", "distinct": "305", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpMin8_Bh.e.", "index": "15", "type": "numeric", "distinct": "217", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_03_DD", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "ATSC3i", "index": "13", "type": "numeric", "distinct": "352", "missing": "0", "min": "1", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMin8_Bh.i.", "index": "12", "type": "numeric", "distinct": "234", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X3v", "index": "11", "type": "numeric", "distinct": "410", "missing": "0", "min": "4", "max": "19", "mean": "7", "stdev": "2" }, { "name": "ATSC1i", "index": "10", "type": "numeric", "distinct": "260", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "ATS5p", "index": "9", "type": "numeric", "distinct": "311", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS6p", "index": "17", "type": "numeric", "distinct": "326", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "7", "type": "numeric", "distinct": "31", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "nArCOOH", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS4v", "index": "5", "type": "numeric", "distinct": "295", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC4p", "index": "4", "type": "numeric", "distinct": "407", "missing": "0", "min": "7", "max": "42", "mean": "16", "stdev": "5" }, { "name": "CATS2D_02_AN", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "C.043", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ARR", "index": "1", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "440", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATS6v", "index": "18", "type": "numeric", "distinct": "316", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "VvdwMG", "index": "19", "type": "numeric", "distinct": "278", "missing": "0", "min": "141", "max": "816", "mean": "278", "stdev": "90" }, { "name": "Vx", "index": "20", "type": "numeric", "distinct": "278", "missing": "0", "min": "335", "max": "1983", "mean": "669", "stdev": "221" }, { "name": "ATS5v", "index": "21", "type": "numeric", "distinct": "307", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.e.", "index": "22", "type": "numeric", "distinct": "214", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS4m", "index": "23", "type": "numeric", "distinct": "288", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATSC5m", "index": "24", "type": "numeric", "distinct": "419", "missing": "0", "min": "15", "max": "168", "mean": "52", "stdev": "23" }, { "name": "ATS3p", "index": "25", "type": "numeric", "distinct": "295", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "26", "type": "numeric", "distinct": "317", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS5m", "index": "27", "type": "numeric", "distinct": "315", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS3v", "index": "28", "type": "numeric", "distinct": "296", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "TIE", "index": "29", "type": "numeric", "distinct": "422", "missing": "0", "min": "33", "max": "1330", "mean": "129", "stdev": "156" }, { "name": "ATSC6m", "index": "30", "type": "numeric", "distinct": "419", "missing": "0", "min": "14", "max": "180", "mean": "54", "stdev": "24" }, { "name": "X4v", "index": "31", "type": "numeric", "distinct": "400", "missing": "0", "min": "3", "max": "12", "mean": "5", "stdev": "1" }, { "name": "ATSC7p", "index": "32", "type": "numeric", "distinct": "411", "missing": "0", "min": "5", "max": "57", "mean": "18", "stdev": "7" } ], "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 }