{ "data_id": "33517", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2407", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2407", "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: CHEMBL2407 (TID: 11199), and it has 104 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 12:59:03", "update_comment": null, "last_update": "2016-07-15 12:59:03", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3507253\/data_52640.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2407", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2407 (TID: 11199), and it has 104 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": 104, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 2.8720299940272613, "MinStdDevOfNumericAtts": 0.10998849827844467, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.678639556778208, "MaxStdDevOfNumericAtts": 52.1276018020226, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7960028159212804, "Quartile3StdDevOfNumericAtts": 1.4907414114450384, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.660110576923077, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.8488765493548837, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 11.160225739644972, "Quartile1SkewnessOfNumericAtts": -0.2816098501831558, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3122369887973935, "AutoCorrelation": -0.37761165048543693, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.3423551292967342, "Dimensionality": 0.6346153846153846, "MeanSkewnessOfNumericAtts": 0.2016870905265393, "Quartile2MeansOfNumericAtts": 5.465057692307692, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.8923267780390782, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.03758521420180225, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3223311824349153, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4562693083681779, "MaxKurtosisOfNumericAtts": 15.201961849609534, "MinMeansOfNumericAtts": 0.07757692307692308, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 121.96477884615383, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.0273366739578247, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 11.536091346153846, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.048728279215342, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "76", "missing": "0", "target": "1", "min": "3", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "104", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig01_AEA.bo.", "index": "1", "type": "numeric", "distinct": "62", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "SpMax_AEA.bo.", "index": "2", "type": "numeric", "distinct": "62", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "3", "type": "numeric", "distinct": "50", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "4", "type": "numeric", "distinct": "50", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpDiam_AEA.bo.", "index": "5", "type": "numeric", "distinct": "65", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "6", "type": "numeric", "distinct": "61", "missing": "0", "min": "14", "max": "27", "mean": "21", "stdev": "3" }, { "name": "Eta_FL", "index": "7", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "13", "mean": "7", "stdev": "2" }, { "name": "CATS2D_06_AA", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "3", "stdev": "2" }, { "name": "SpMax6_Bh.s.", "index": "9", "type": "numeric", "distinct": "69", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "10", "type": "numeric", "distinct": "58", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "piPC03", "index": "11", "type": "numeric", "distinct": "78", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpDiam_EA", "index": "12", "type": "numeric", "distinct": "53", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_03_AL", "index": "13", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "5" }, { "name": "Eig01_EA", "index": "14", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "15", "type": "numeric", "distinct": "54", "missing": "0", "min": "9", "max": "17", "mean": "13", "stdev": "2" }, { "name": "SM09_AEA.bo.", "index": "16", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM10_AEA.dm.", "index": "17", "type": "numeric", "distinct": "54", "missing": "0", "min": "9", "max": "17", "mean": "13", "stdev": "2" }, { "name": "SpMax_EA", "index": "18", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ed.", "index": "19", "type": "numeric", "distinct": "54", "missing": "0", "min": "9", "max": "17", "mean": "13", "stdev": "2" }, { "name": "X5", "index": "20", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "16", "mean": "7", "stdev": "3" }, { "name": "Eig01_EA.ri.", "index": "21", "type": "numeric", "distinct": "56", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "22", "type": "numeric", "distinct": "56", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X3sol", "index": "23", "type": "numeric", "distinct": "90", "missing": "0", "min": "4", "max": "28", "mean": "13", "stdev": "4" }, { "name": "Eig01_AEA.ri.", "index": "24", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "25", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_beta", "index": "26", "type": "numeric", "distinct": "63", "missing": "0", "min": "13", "max": "79", "mean": "39", "stdev": "12" }, { "name": "piPC02", "index": "27", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA.bo.", "index": "28", "type": "numeric", "distinct": "63", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM10_EA.bo.", "index": "29", "type": "numeric", "distinct": "83", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM04_EA.bo.", "index": "30", "type": "numeric", "distinct": "83", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "piPC05", "index": "31", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "6", "mean": "6", "stdev": "0" }, { "name": "MATS2m", "index": "32", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Xindex", "index": "33", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "piPC04", "index": "34", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig02_AEA.dm.", "index": "35", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SM11_EA.bo.", "index": "36", "type": "numeric", "distinct": "84", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "37", "type": "numeric", "distinct": "81", "missing": "0", "min": "16", "max": "20", "mean": "17", "stdev": "1" }, { "name": "MPC05", "index": "38", "type": "numeric", "distinct": "62", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM13_EA.bo.", "index": "39", "type": "numeric", "distinct": "81", "missing": "0", "min": "17", "max": "21", "mean": "19", "stdev": "1" }, { "name": "SM14_EA.bo.", "index": "40", "type": "numeric", "distinct": "84", "missing": "0", "min": "18", "max": "23", "mean": "20", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "41", "type": "numeric", "distinct": "81", "missing": "0", "min": "19", "max": "24", "mean": "21", "stdev": "2" }, { "name": "SpDiam_AEA.ri.", "index": "42", "type": "numeric", "distinct": "77", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "nHAcc", "index": "43", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "24", "mean": "8", "stdev": "4" }, { "name": "P_VSA_LogP_4", "index": "44", "type": "numeric", "distinct": "34", "missing": "0", "min": "36", "max": "406", "mean": "122", "stdev": "52" }, { "name": "TPSA.NO.", "index": "45", "type": "numeric", "distinct": "39", "missing": "0", "min": "30", "max": "374", "mean": "105", "stdev": "48" }, { "name": "piPC06", "index": "46", "type": "numeric", "distinct": "86", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig13_AEA.dm.", "index": "47", "type": "numeric", "distinct": "67", "missing": "0", "min": "-2", "max": "4", "mean": "1", "stdev": "1" }, { "name": "DLS_cons", "index": "48", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "49", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS2m", "index": "50", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM09_EA.bo.", "index": "51", "type": "numeric", "distinct": "83", "missing": "0", "min": "12", "max": "15", "mean": "13", "stdev": "1" }, { "name": "ATS1p", "index": "52", "type": "numeric", "distinct": "85", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Sp", "index": "53", "type": "numeric", "distinct": "87", "missing": "0", "min": "14", "max": "102", "mean": "43", "stdev": "16" }, { "name": "SpMax5_Bh.p.", "index": "54", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "55", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Ui", "index": "56", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig01_AEA.ed.", "index": "57", "type": "numeric", "distinct": "46", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax_AEA.ed.", "index": "58", "type": "numeric", "distinct": "46", "missing": "0", "min": "6", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "59", "type": "numeric", "distinct": "88", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "piPC07", "index": "60", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "7", "mean": "6", "stdev": "1" }, { "name": "X5sol", "index": "61", "type": "numeric", "distinct": "90", "missing": "0", "min": "3", "max": "18", "mean": "8", "stdev": "3" }, { "name": "ATS6s", "index": "62", "type": "numeric", "distinct": "99", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SM07_EA.bo.", "index": "63", "type": "numeric", "distinct": "81", "missing": "0", "min": "9", "max": "12", "mean": "10", "stdev": "1" }, { "name": "Eig02_AEA.bo.", "index": "64", "type": "numeric", "distinct": "55", "missing": "0", "min": "4", "max": "5", "mean": "4", "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 }