{ "data_id": "35314", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3486", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3486", "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: CHEMBL3486 (TID: 100588), and it has 119 rows and 63 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 17:42:44", "update_comment": null, "last_update": "2016-07-15 17:42:44", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3554539\/data_52516.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3486", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3486 (TID: 100588), and it has 119 rows and 63 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": 119, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 0.9816065097908857, "Dimensionality": 0.5462184873949579, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.379386554621849, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.0873660732021342, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.87587410768942, "Quartile2SkewnessOfNumericAtts": -0.37735283232528677, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7195041713984154, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8417883711354017, "MinMeansOfNumericAtts": -0.37310924369747894, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 13.325712434093289, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.0939649759751537, "MaxMeansOfNumericAtts": 84.88756302521008, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 11.905283613445379, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -1.7573112790443828, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.10101163979684757, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9121716482181363, "MaxSkewnessOfNumericAtts": 2.7879981142857835, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9931657766443928, "Quartile3StdDevOfNumericAtts": 1.6998883770662463, "MaxStdDevOfNumericAtts": 54.636716414772174, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.8151260504201677, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 1.6467399027441603, "Quartile1SkewnessOfNumericAtts": -0.7069617976216968, "MeanMeansOfNumericAtts": 10.684268644957983, "Quartile1StdDevOfNumericAtts": 0.48671828488870716, "AutoCorrelation": 0.2209915254237288, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "84", "missing": "0", "target": "1", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "119", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SdssC", "index": "1", "type": "numeric", "distinct": "45", "missing": "0", "min": "-3", "max": "1", "mean": "0", "stdev": "1" }, { "name": "SAdon", "index": "2", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "85", "mean": "29", "stdev": "19" }, { "name": "C.044", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_5", "index": "4", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "201", "mean": "30", "stdev": "41" }, { "name": "O.057", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "NsOH", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SsOH", "index": "7", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "5" }, { "name": "nArNHR", "index": "8", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_AA", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "O.", "index": "10", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "4" }, { "name": "P_VSA_p_2", "index": "11", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "237", "mean": "85", "stdev": "29" }, { "name": "C.030", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.035", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_AA", "index": "14", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "N.075", "index": "15", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "NaaN", "index": "16", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nPyrimidines", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nTriazoles", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SaaN", "index": "19", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "17", "mean": "8", "stdev": "6" }, { "name": "SRW09", "index": "20", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "3" }, { "name": "nO", "index": "21", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "piPC06", "index": "22", "type": "numeric", "distinct": "103", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SssNH", "index": "23", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "PHI", "index": "24", "type": "numeric", "distinct": "99", "missing": "0", "min": "2", "max": "13", "mean": "4", "stdev": "2" }, { "name": "SpMAD_EA.bo.", "index": "25", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "26", "type": "numeric", "distinct": "94", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "27", "type": "numeric", "distinct": "92", "missing": "0", "min": "16", "max": "20", "mean": "18", "stdev": "1" }, { "name": "N.073", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "piPC07", "index": "29", "type": "numeric", "distinct": "101", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "30", "type": "numeric", "distinct": "26", "missing": "0", "min": "30", "max": "217", "mean": "77", "stdev": "23" }, { "name": "P_VSA_MR_7", "index": "31", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "134", "mean": "48", "stdev": "27" }, { "name": "SM10_EA.bo.", "index": "32", "type": "numeric", "distinct": "96", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "0" }, { "name": "CATS2D_03_DA", "index": "33", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "S2K", "index": "34", "type": "numeric", "distinct": "94", "missing": "0", "min": "3", "max": "16", "mean": "6", "stdev": "2" }, { "name": "nR05", "index": "35", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_03_AA", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM06_EA.bo.", "index": "37", "type": "numeric", "distinct": "100", "missing": "0", "min": "9", "max": "10", "mean": "10", "stdev": "0" }, { "name": "PCD", "index": "38", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "39", "type": "numeric", "distinct": "96", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "0" }, { "name": "SM08_EA.bo.", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "11", "max": "14", "mean": "12", "stdev": "0" }, { "name": "SdO", "index": "41", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "63", "mean": "6", "stdev": "9" }, { "name": "P_VSA_MR_2", "index": "42", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "272", "mean": "56", "stdev": "55" }, { "name": "P_VSA_m_3", "index": "43", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "201", "mean": "39", "stdev": "43" }, { "name": "Eig01_EA.bo.", "index": "44", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM11_AEA.ri.", "index": "45", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_EA.bo.", "index": "46", "type": "numeric", "distinct": "60", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax_EA.bo.", "index": "47", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.040", "index": "48", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "H.051", "index": "49", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM05_EA.bo.", "index": "50", "type": "numeric", "distinct": "85", "missing": "0", "min": "6", "max": "9", "mean": "8", "stdev": "0" }, { "name": "piPC05", "index": "51", "type": "numeric", "distinct": "95", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "52", "type": "numeric", "distinct": "93", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "53", "type": "numeric", "distinct": "89", "missing": "0", "min": "5", "max": "46", "mean": "21", "stdev": "6" }, { "name": "NdssC", "index": "54", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "55", "type": "numeric", "distinct": "91", "missing": "0", "min": "17", "max": "22", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "56", "type": "numeric", "distinct": "91", "missing": "0", "min": "18", "max": "23", "mean": "21", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "57", "type": "numeric", "distinct": "92", "missing": "0", "min": "19", "max": "25", "mean": "22", "stdev": "1" }, { "name": "N.", "index": "58", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "21", "mean": "10", "stdev": "6" }, { "name": "NdO", "index": "59", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "O.058", "index": "60", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "CATS2D_07_DL", "index": "61", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "piID", "index": "62", "type": "numeric", "distinct": "100", "missing": "0", "min": "7", "max": "14", "mean": "10", "stdev": "1" }, { "name": "piPC04", "index": "63", "type": "numeric", "distinct": "93", "missing": "0", "min": "4", "max": "6", "mean": "5", "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 }