{ "data_id": "37080", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4552", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4552", "version": 12, "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: CHEMBL4552 (TID: 10841), and it has 801 rows and 66 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 23:25:00", "update_comment": null, "last_update": "2016-07-15 23:25:00", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3604239\/data_53142.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4552", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4552 (TID: 10841), and it has 801 rows and 66 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": 801, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08489388264669163, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.6269569299168496, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.19396539659172382, "Quartile2MeansOfNumericAtts": 5.890046192259676, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 3.113519518475649, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.2803375806215856, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8832532730205607, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.21999129931155015, "MaxKurtosisOfNumericAtts": 4.689572512179891, "MinMeansOfNumericAtts": 0.10486891385767803, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 171.17353308364545, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9856783443280004, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 10.216475655430711, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.193509486955067, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.5841573913344877, "MinStdDevOfNumericAtts": 0.07057166333623177, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.18250462961613695, "MaxStdDevOfNumericAtts": 68.9292724581884, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.3386403126750528, "Quartile3StdDevOfNumericAtts": 0.5414675341657668, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.160823970037453, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.6658894917417861, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 15.100788696964615, "Quartile1SkewnessOfNumericAtts": -0.601244051077099, "AutoCorrelation": -0.11637124999999912, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.18398937681364813 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "540", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "801", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GGI2", "index": "1", "type": "numeric", "distinct": "17", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM03_EA.ri.", "index": "2", "type": "numeric", "distinct": "265", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "3", "type": "numeric", "distinct": "377", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM07_AEA.ed.", "index": "4", "type": "numeric", "distinct": "422", "missing": "0", "min": "14", "max": "15", "mean": "14", "stdev": "0" }, { "name": "SM06_EA", "index": "5", "type": "numeric", "distinct": "384", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM04_AEA.ed.", "index": "6", "type": "numeric", "distinct": "375", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "GGI7", "index": "7", "type": "numeric", "distinct": "351", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "8", "type": "numeric", "distinct": "319", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SRW10", "index": "9", "type": "numeric", "distinct": "384", "missing": "0", "min": "10", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM05_EA", "index": "10", "type": "numeric", "distinct": "74", "missing": "0", "min": "6", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SM03_EA.ed.", "index": "11", "type": "numeric", "distinct": "210", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "SM06_AEA.ed.", "index": "12", "type": "numeric", "distinct": "397", "missing": "0", "min": "12", "max": "13", "mean": "13", "stdev": "0" }, { "name": "SM05_AEA.ed.", "index": "13", "type": "numeric", "distinct": "409", "missing": "0", "min": "10", "max": "11", "mean": "11", "stdev": "0" }, { "name": "SM02_EA.ed.", "index": "14", "type": "numeric", "distinct": "254", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "D.Dtr09", "index": "15", "type": "numeric", "distinct": "331", "missing": "0", "min": "0", "max": "414", "mean": "70", "stdev": "69" }, { "name": "Eig08_AEA.ed.", "index": "16", "type": "numeric", "distinct": "444", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "17", "type": "numeric", "distinct": "589", "missing": "0", "min": "75", "max": "194", "mean": "129", "stdev": "20" }, { "name": "MWC03", "index": "18", "type": "numeric", "distinct": "120", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ZM2", "index": "19", "type": "numeric", "distinct": "120", "missing": "0", "min": "99", "max": "258", "mean": "171", "stdev": "25" }, { "name": "SRW06", "index": "20", "type": "numeric", "distinct": "250", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "SM04_EA", "index": "21", "type": "numeric", "distinct": "149", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "22", "type": "numeric", "distinct": "356", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "23", "type": "numeric", "distinct": "364", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig08_EA.ri.", "index": "24", "type": "numeric", "distinct": "356", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nRCONR2", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM07_EA", "index": "26", "type": "numeric", "distinct": "278", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "SM02_AEA.ed.", "index": "27", "type": "numeric", "distinct": "126", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "28", "type": "numeric", "distinct": "225", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SRW08", "index": "29", "type": "numeric", "distinct": "355", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "Eig08_EA", "index": "30", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "31", "type": "numeric", "distinct": "321", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MWC04", "index": "32", "type": "numeric", "distinct": "235", "missing": "0", "min": "6", "max": "7", "mean": "7", "stdev": "0" }, { "name": "Ram", "index": "33", "type": "numeric", "distinct": "10", "missing": "0", "min": "5", "max": "14", "mean": "9", "stdev": "2" }, { "name": "SM03_EA", "index": "34", "type": "numeric", "distinct": "11", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC5i", "index": "35", "type": "numeric", "distinct": "564", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "36", "type": "numeric", "distinct": "338", "missing": "0", "min": "8", "max": "9", "mean": "9", "stdev": "0" }, { "name": "SM03_EA.bo.", "index": "37", "type": "numeric", "distinct": "66", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Eig08_AEA.ri.", "index": "38", "type": "numeric", "distinct": "362", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM02_EA.ri.", "index": "39", "type": "numeric", "distinct": "375", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "40", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "126", "mean": "46", "stdev": "21" }, { "name": "Sv", "index": "41", "type": "numeric", "distinct": "546", "missing": "0", "min": "17", "max": "46", "mean": "33", "stdev": "4" }, { "name": "X1Mad", "index": "42", "type": "numeric", "distinct": "683", "missing": "0", "min": "7", "max": "19", "mean": "13", "stdev": "2" }, { "name": "SpAD_AEA.ed.", "index": "43", "type": "numeric", "distinct": "587", "missing": "0", "min": "26", "max": "71", "mean": "47", "stdev": "7" }, { "name": "ATSC6i", "index": "44", "type": "numeric", "distinct": "602", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "45", "type": "numeric", "distinct": "380", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GGI3", "index": "46", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_EA", "index": "47", "type": "numeric", "distinct": "345", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "48", "type": "numeric", "distinct": "345", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eig14_AEA.ri.", "index": "49", "type": "numeric", "distinct": "526", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "BBI", "index": "50", "type": "numeric", "distinct": "40", "missing": "0", "min": "24", "max": "63", "mean": "42", "stdev": "6" }, { "name": "MPC02", "index": "51", "type": "numeric", "distinct": "40", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM02_EA", "index": "52", "type": "numeric", "distinct": "40", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM04_EA.ri.", "index": "53", "type": "numeric", "distinct": "435", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "GGI8", "index": "54", "type": "numeric", "distinct": "300", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Pol", "index": "55", "type": "numeric", "distinct": "38", "missing": "0", "min": "25", "max": "71", "mean": "45", "stdev": "7" }, { "name": "SpAD_AEA.ri.", "index": "56", "type": "numeric", "distinct": "749", "missing": "0", "min": "26", "max": "68", "mean": "45", "stdev": "6" }, { "name": "MPC03", "index": "57", "type": "numeric", "distinct": "48", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig03_AEA.ed.", "index": "58", "type": "numeric", "distinct": "296", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig06_EA.ri.", "index": "59", "type": "numeric", "distinct": "424", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.041", "index": "60", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpAD_EA", "index": "61", "type": "numeric", "distinct": "583", "missing": "0", "min": "26", "max": "68", "mean": "45", "stdev": "6" }, { "name": "P_VSA_e_5", "index": "62", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "118", "mean": "42", "stdev": "18" }, { "name": "Eig04_AEA.ri.", "index": "63", "type": "numeric", "distinct": "415", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X1Kup", "index": "64", "type": "numeric", "distinct": "649", "missing": "0", "min": "5", "max": "14", "mean": "9", "stdev": "1" }, { "name": "SRW04", "index": "65", "type": "numeric", "distinct": "87", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "66", "type": "numeric", "distinct": "379", "missing": "0", "min": "11", "max": "12", "mean": "12", "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 }