{ "data_id": "39379", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2756", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2756", "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: CHEMBL2756 (TID: 12232), and it has 269 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": "2016-07-16 07:43:09", "update_comment": null, "last_update": "2016-07-16 07:43:09", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3672372\/data_52702.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2756", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2756 (TID: 12232), and it has 269 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": 269, "NumberOfFeatures": 66, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 65, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.24535315985130113, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.991713189542979, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.6859886605636656, "Quartile2MeansOfNumericAtts": 2.202728624535316, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.3493621356406305, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.43225770218530973, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3440438200812312, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.634210742199967, "MaxKurtosisOfNumericAtts": 63.06193839521525, "MinMeansOfNumericAtts": -0.19894423791821556, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 283.7646356877323, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 4.049517291877088, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.48484848484848, "Quartile3MeansOfNumericAtts": 3.815626394052045, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3268325224928037, "PercentageOfSymbolicFeatures": 1.5151515151515151, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 6.4118409519465445, "MinStdDevOfNumericAtts": 0.03877465888813817, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.608784894095808, "MaxStdDevOfNumericAtts": 129.9616101898669, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.5746421875875198, "Quartile3StdDevOfNumericAtts": 2.1559642329289406, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.546468401486989, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 3.982758582935842, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 17.42508813268516, "Quartile1SkewnessOfNumericAtts": -0.6912634783394906, "AutoCorrelation": -0.1513283582089556, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3315576562186169 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "65", "type": "numeric", "distinct": "189", "missing": "0", "target": "1", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "269", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig06_EA", "index": "1", "type": "numeric", "distinct": "132", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SM14_AEA.bo.", "index": "2", "type": "numeric", "distinct": "132", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "DBI", "index": "3", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "nR.Cs", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "MATS5e", "index": "5", "type": "numeric", "distinct": "187", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_AEA.ri.", "index": "6", "type": "numeric", "distinct": "174", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig04_AEA.dm.", "index": "7", "type": "numeric", "distinct": "205", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nN", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Eig06_EA.ed.", "index": "9", "type": "numeric", "distinct": "153", "missing": "0", "min": "-2", "max": "11", "mean": "3", "stdev": "2" }, { "name": "SM15_AEA.dm.", "index": "10", "type": "numeric", "distinct": "153", "missing": "0", "min": "-2", "max": "11", "mean": "3", "stdev": "2" }, { "name": "MATS3e", "index": "11", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AL", "index": "12", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "17", "mean": "1", "stdev": "2" }, { "name": "SssO", "index": "13", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "24", "mean": "3", "stdev": "5" }, { "name": "nR05", "index": "14", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MCD", "index": "15", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS2i", "index": "16", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "IC3", "index": "17", "type": "numeric", "distinct": "169", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "MATS2e", "index": "18", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SRW05", "index": "19", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SRW07", "index": "20", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "SRW09", "index": "21", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "3" }, { "name": "N.", "index": "22", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "21", "mean": "6", "stdev": "3" }, { "name": "P_VSA_e_3", "index": "23", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "69", "mean": "24", "stdev": "17" }, { "name": "SpMin3_Bh.i.", "index": "24", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_05_AL", "index": "25", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "32", "mean": "4", "stdev": "4" }, { "name": "SsssN", "index": "26", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "Eig15_AEA.ri.", "index": "27", "type": "numeric", "distinct": "135", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "28", "type": "numeric", "distinct": "208", "missing": "0", "min": "35", "max": "242", "mean": "121", "stdev": "35" }, { "name": "Eig06_EA.ri.", "index": "29", "type": "numeric", "distinct": "179", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GGI10", "index": "30", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "31", "type": "numeric", "distinct": "157", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC2", "index": "32", "type": "numeric", "distinct": "192", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "VvdwZAZ", "index": "33", "type": "numeric", "distinct": "178", "missing": "0", "min": "109", "max": "754", "mean": "250", "stdev": "73" }, { "name": "SpMax6_Bh.m.", "index": "34", "type": "numeric", "distinct": "166", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin3_Bh.e.", "index": "35", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "N.068", "index": "36", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "nRNR2", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "C.043", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "39", "type": "numeric", "distinct": "153", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "O.060", "index": "40", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ZM1MulPer", "index": "41", "type": "numeric", "distinct": "227", "missing": "0", "min": "71", "max": "862", "mean": "284", "stdev": "130" }, { "name": "ICR", "index": "42", "type": "numeric", "distinct": "122", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CATS2D_09_LL", "index": "43", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "4" }, { "name": "Mv", "index": "44", "type": "numeric", "distinct": "109", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.m.", "index": "45", "type": "numeric", "distinct": "163", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NssO", "index": "46", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Psi_i_0", "index": "47", "type": "numeric", "distinct": "208", "missing": "0", "min": "6", "max": "43", "mean": "14", "stdev": "4" }, { "name": "Eig05_AEA.dm.", "index": "48", "type": "numeric", "distinct": "185", "missing": "0", "min": "-1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "ZM1V", "index": "49", "type": "numeric", "distinct": "125", "missing": "0", "min": "66", "max": "808", "mean": "266", "stdev": "121" }, { "name": "Chi1_EA.bo.", "index": "50", "type": "numeric", "distinct": "194", "missing": "0", "min": "3", "max": "29", "mean": "8", "stdev": "3" }, { "name": "CATS2D_09_AA", "index": "51", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "ATS1v", "index": "52", "type": "numeric", "distinct": "180", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Psi_i_1", "index": "53", "type": "numeric", "distinct": "230", "missing": "0", "min": "4", "max": "39", "mean": "11", "stdev": "4" }, { "name": "P_VSA_p_2", "index": "54", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "250", "mean": "50", "stdev": "40" }, { "name": "SpMax8_Bh.m.", "index": "55", "type": "numeric", "distinct": "166", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_AA", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "nRCOOR", "index": "57", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "N.075", "index": "58", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NaaN", "index": "59", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SaaN", "index": "60", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "GGI1", "index": "61", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "17", "mean": "4", "stdev": "2" }, { "name": "MATS5m", "index": "62", "type": "numeric", "distinct": "185", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig05_AEA.bo.", "index": "63", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig07_AEA.bo.", "index": "64", "type": "numeric", "distinct": "146", "missing": "0", "min": "-1", "max": "4", "mean": "2", "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 }