{ "data_id": "35634", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5704", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5704", "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: CHEMBL5704 (TID: 101509), and it has 126 rows and 60 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 18:34:44", "update_comment": null, "last_update": "2016-07-15 18:34:44", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3563891\/data_51996.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5704", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5704 (TID: 101509), and it has 126 rows and 60 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": 126, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.49206349206349204, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.8342596032214682, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.0912492473979434, "Quartile2MeansOfNumericAtts": 2.673484126984127, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.41724533929078567, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.09585905738927332, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.602586676239744, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.26413285497901434, "MaxKurtosisOfNumericAtts": 4.019368771478556, "MinMeansOfNumericAtts": -0.02552380952380952, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 18.913650793650795, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.37013925576567996, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 5.311857142857143, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.8922425789896391, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 0.8582827317654298, "MinStdDevOfNumericAtts": 0.007941472415552684, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.4268437741245903, "MaxStdDevOfNumericAtts": 2.4320171888490294, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.177722441889002, "Quartile3StdDevOfNumericAtts": 0.463216296916921, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0736507936507937, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": -0.6707282501551723, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4.217638433515483, "Quartile1SkewnessOfNumericAtts": -0.20358555762191594, "AutoCorrelation": 0.1727040000000004, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1986006208559587 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "96", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "126", "missing": "0", "identifier": "1", "distr": [] }, { "name": "IC2", "index": "1", "type": "numeric", "distinct": "97", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MATS7s", "index": "2", "type": "numeric", "distinct": "109", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS5i", "index": "3", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BIC2", "index": "4", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS5v", "index": "5", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.ri.", "index": "6", "type": "numeric", "distinct": "83", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "JGI4", "index": "7", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "8", "type": "numeric", "distinct": "69", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig05_EA.bo.", "index": "9", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "10", "type": "numeric", "distinct": "65", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.ri.", "index": "11", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig08_AEA.bo.", "index": "12", "type": "numeric", "distinct": "72", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MATS2m", "index": "13", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC2", "index": "14", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC2", "index": "15", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS5p", "index": "16", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS8e", "index": "17", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig06_EA", "index": "18", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "19", "type": "numeric", "distinct": "78", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "GATS8s", "index": "20", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS6s", "index": "21", "type": "numeric", "distinct": "116", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig09_EA", "index": "22", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig10_AEA.dm.", "index": "23", "type": "numeric", "distinct": "72", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig13_AEA.ed.", "index": "24", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM03_AEA.dm.", "index": "25", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1s", "index": "26", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM09_EA.ri.", "index": "27", "type": "numeric", "distinct": "104", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SM10_EA.ri.", "index": "28", "type": "numeric", "distinct": "103", "missing": "0", "min": "12", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SM11_EA.ri.", "index": "29", "type": "numeric", "distinct": "106", "missing": "0", "min": "13", "max": "15", "mean": "14", "stdev": "1" }, { "name": "Eig08_AEA.ri.", "index": "30", "type": "numeric", "distinct": "112", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA", "index": "31", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "32", "type": "numeric", "distinct": "102", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "33", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "34", "type": "numeric", "distinct": "57", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS7i", "index": "35", "type": "numeric", "distinct": "107", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS7e", "index": "36", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2i", "index": "37", "type": "numeric", "distinct": "91", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "GATS5p", "index": "38", "type": "numeric", "distinct": "100", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM12_EA.ri.", "index": "39", "type": "numeric", "distinct": "101", "missing": "0", "min": "14", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "40", "type": "numeric", "distinct": "103", "missing": "0", "min": "15", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "41", "type": "numeric", "distinct": "100", "missing": "0", "min": "16", "max": "19", "mean": "18", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "42", "type": "numeric", "distinct": "101", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM03_EA.ri.", "index": "43", "type": "numeric", "distinct": "64", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ON0", "index": "44", "type": "numeric", "distinct": "46", "missing": "0", "min": "13", "max": "24", "mean": "17", "stdev": "2" }, { "name": "ATSC5i", "index": "45", "type": "numeric", "distinct": "117", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "DBI", "index": "46", "type": "numeric", "distinct": "23", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "47", "type": "numeric", "distinct": "80", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.ri.", "index": "48", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "49", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SM04_AEA.ri.", "index": "50", "type": "numeric", "distinct": "81", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "Eig06_EA.ed.", "index": "51", "type": "numeric", "distinct": "71", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM15_AEA.dm.", "index": "52", "type": "numeric", "distinct": "71", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "ATS2s", "index": "53", "type": "numeric", "distinct": "100", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS3s", "index": "54", "type": "numeric", "distinct": "107", "missing": "0", "min": "6", "max": "6", "mean": "6", "stdev": "0" }, { "name": "Eig03_EA", "index": "55", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM11_AEA.bo.", "index": "56", "type": "numeric", "distinct": "60", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin1_Bh.i.", "index": "57", "type": "numeric", "distinct": "59", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "58", "type": "numeric", "distinct": "75", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS8i", "index": "59", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig11_AEA.dm.", "index": "60", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "2", "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 }