{ "data_id": "33218", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3607", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3607", "version": 9, "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: CHEMBL3607 (TID: 11762), and it has 93 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 12:13:01", "update_comment": null, "last_update": "2016-07-15 12:13:01", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3500056\/data_52683.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3607", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3607 (TID: 11762), and it has 93 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": 93, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.7096774193548387, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.6909305111027697, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.37613090626200735, "Quartile2MeansOfNumericAtts": 1.602150537634409, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.1474861618439522, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.5344880240427001, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.715455830311262, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.949766832437378, "MaxKurtosisOfNumericAtts": 5.334546328582942, "MinMeansOfNumericAtts": -0.797741935483871, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 42.50511827956989, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.25692963945355896, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 4.795881720430108, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.66260660543194, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.6194472083015146, "MinStdDevOfNumericAtts": 0.06374701452368228, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9895354662089978, "MaxStdDevOfNumericAtts": 25.01349906326645, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.2488954769287415, "Quartile3StdDevOfNumericAtts": 2.2480842281984863, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.42527419354838714, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.36959832646942337, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 3.8085033912324238, "Quartile1SkewnessOfNumericAtts": -0.27563801480278965, "AutoCorrelation": -0.3751195652173917, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4928337239475179 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "58", "missing": "0", "target": "1", "min": "4", "max": "9", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "93", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_06_DL", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "CATS2D_06_NL", "index": "2", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "N.", "index": "3", "type": "numeric", "distinct": "51", "missing": "0", "min": "2", "max": "23", "mean": "7", "stdev": "5" }, { "name": "CATS2D_03_NL", "index": "4", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_05_NL", "index": "5", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "2" }, { "name": "GATS4e", "index": "6", "type": "numeric", "distinct": "75", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nCrt", "index": "7", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "nPyrrolidines", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_NL", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "2" }, { "name": "CATS2D_02_LL", "index": "10", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "30", "mean": "7", "stdev": "8" }, { "name": "CATS2D_04_LL", "index": "11", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "23", "mean": "4", "stdev": "6" }, { "name": "CATS2D_07_DL", "index": "12", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "GATS6s", "index": "13", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "BLTA96", "index": "14", "type": "numeric", "distinct": "73", "missing": "0", "min": "-5", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "BLTD48", "index": "15", "type": "numeric", "distinct": "73", "missing": "0", "min": "-5", "max": "3", "mean": "-1", "stdev": "2" }, { "name": "BLTF96", "index": "16", "type": "numeric", "distinct": "72", "missing": "0", "min": "-5", "max": "3", "mean": "-1", "stdev": "2" }, { "name": "MLOGP", "index": "17", "type": "numeric", "distinct": "73", "missing": "0", "min": "-5", "max": "4", "mean": "-1", "stdev": "2" }, { "name": "C.015", "index": "18", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NdCH2", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nR.Cp", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SdCH2", "index": "21", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "P_VSA_e_3", "index": "22", "type": "numeric", "distinct": "21", "missing": "0", "min": "18", "max": "106", "mean": "43", "stdev": "25" }, { "name": "SpDiam_EA.ri.", "index": "23", "type": "numeric", "distinct": "63", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "CATS2D_08_AL", "index": "24", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "C.003", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GATS4s", "index": "26", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NsssCH", "index": "27", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "ATSC5v", "index": "28", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "24", "mean": "9", "stdev": "5" }, { "name": "ATSC6v", "index": "29", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "24", "mean": "8", "stdev": "5" }, { "name": "CATS2D_03_LL", "index": "30", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "28", "mean": "6", "stdev": "8" }, { "name": "CATS2D_05_LL", "index": "31", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "21", "mean": "4", "stdev": "5" }, { "name": "CATS2D_08_DL", "index": "32", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "GATS2s", "index": "33", "type": "numeric", "distinct": "69", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "MATS4s", "index": "34", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Hy", "index": "35", "type": "numeric", "distinct": "63", "missing": "0", "min": "-1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpMin1_Bh.s.", "index": "36", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.017", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nR.Ct", "index": "38", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig01_EA.ri.", "index": "39", "type": "numeric", "distinct": "57", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "40", "type": "numeric", "distinct": "57", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ATS5e", "index": "41", "type": "numeric", "distinct": "85", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS5i", "index": "42", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATS6i", "index": "43", "type": "numeric", "distinct": "82", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "ATSC4v", "index": "44", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "23", "mean": "9", "stdev": "5" }, { "name": "CATS2D_01_LL", "index": "45", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "6" }, { "name": "MATS4e", "index": "46", "type": "numeric", "distinct": "78", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCt", "index": "47", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SssNH", "index": "48", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Hypertens.50", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_AL", "index": "50", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "ATSC3p", "index": "51", "type": "numeric", "distinct": "83", "missing": "0", "min": "2", "max": "16", "mean": "7", "stdev": "3" }, { "name": "ATSC4p", "index": "52", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "17", "mean": "7", "stdev": "4" }, { "name": "nN", "index": "53", "type": "numeric", "distinct": "6", "missing": "0", "min": "1", "max": "7", "mean": "2", "stdev": "1" }, { "name": "CATS2D_04_DA", "index": "54", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_NL", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "N.067", "index": "56", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nRNHR", "index": "57", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "58", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SsOH", "index": "59", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "27", "mean": "17", "stdev": "4" }, { "name": "ATSC5i", "index": "60", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM13_EA.ri.", "index": "61", "type": "numeric", "distinct": "84", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "62", "type": "numeric", "distinct": "80", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "63", "type": "numeric", "distinct": "83", "missing": "0", "min": "14", "max": "18", "mean": "17", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "64", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "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 }