{ "data_id": "34831", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4077", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4077", "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: CHEMBL4077 (TID: 12708), and it has 469 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 16:24:17", "update_comment": null, "last_update": "2016-07-15 16:24:17", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3540025\/data_53138.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4077", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4077 (TID: 12708), and it has 469 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": 469, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile2KurtosisOfNumericAtts": 1.4605951722419115, "Dimensionality": 0.14498933901918976, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 2.3965884861407245, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.2931875049881778, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 810.9281543102524, "Quartile2SkewnessOfNumericAtts": 0.9881244259231848, "MajorityClassSize": null, "MinAttributeEntropy": null, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7209555672806032, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.57342166510514, "MinMeansOfNumericAtts": -0.09017910447761193, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 130.20331483707574, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 8.828224781710277, "MaxMeansOfNumericAtts": 16686.30703624733, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 13.279317697228137, "MaxMutualInformation": null, "MinSkewnessOfNumericAtts": -3.524737255208266, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinStdDevOfNumericAtts": 0.05102481705608147, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.9981540402642357, "MaxSkewnessOfNumericAtts": 10.057590013108674, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.7376362195127437, "Quartile3StdDevOfNumericAtts": 10.656518531076566, "MaxStdDevOfNumericAtts": 51371.26748563578, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.46942430703624727, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 6.59017044706863, "Quartile1SkewnessOfNumericAtts": 0.48048919244252286, "MeanMeansOfNumericAtts": 313.774350857652, "Quartile1StdDevOfNumericAtts": 0.4573991610887041, "AutoCorrelation": -0.11540811965812008, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "311", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "469", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr09", "index": "1", "type": "numeric", "distinct": "291", "missing": "0", "min": "0", "max": "2134", "mean": "217", "stdev": "192" }, { "name": "nBM", "index": "2", "type": "numeric", "distinct": "51", "missing": "0", "min": "7", "max": "91", "mean": "28", "stdev": "12" }, { "name": "Uc", "index": "3", "type": "numeric", "distinct": "51", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "CATS2D_06_AL", "index": "4", "type": "numeric", "distinct": "37", "missing": "0", "min": "2", "max": "59", "mean": "13", "stdev": "9" }, { "name": "P_VSA_LogP_7", "index": "5", "type": "numeric", "distinct": "96", "missing": "0", "min": "200", "max": "3488", "mean": "482", "stdev": "303" }, { "name": "DLS_01", "index": "6", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DLS_03", "index": "7", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "DLS_06", "index": "8", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "DLS_cons", "index": "9", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "DLS_07", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_1", "index": "11", "type": "numeric", "distinct": "69", "missing": "0", "min": "200", "max": "2896", "mean": "490", "stdev": "270" }, { "name": "P_VSA_m_1", "index": "12", "type": "numeric", "distinct": "69", "missing": "0", "min": "200", "max": "2896", "mean": "490", "stdev": "270" }, { "name": "P_VSA_s_2", "index": "13", "type": "numeric", "distinct": "72", "missing": "0", "min": "200", "max": "2896", "mean": "490", "stdev": "270" }, { "name": "P_VSA_v_1", "index": "14", "type": "numeric", "distinct": "69", "missing": "0", "min": "200", "max": "2896", "mean": "490", "stdev": "270" }, { "name": "CATS2D_06_DP", "index": "15", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_AP", "index": "16", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "2" }, { "name": "CATS2D_08_DP", "index": "17", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "S3K", "index": "18", "type": "numeric", "distinct": "363", "missing": "0", "min": "3", "max": "118", "mean": "14", "stdev": "11" }, { "name": "CATS2D_02_AP", "index": "19", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "Eig12_EA.dm.", "index": "20", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig13_EA.dm.", "index": "21", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "H.049", "index": "22", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "DLS_04", "index": "23", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_07_DP", "index": "24", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "nImidazoles", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_AL", "index": "26", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "55", "mean": "13", "stdev": "9" }, { "name": "Eig10_EA.dm.", "index": "27", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "P_VSA_MR_5", "index": "28", "type": "numeric", "distinct": "248", "missing": "0", "min": "26", "max": "1585", "mean": "220", "stdev": "170" }, { "name": "N.075", "index": "29", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "NaaN", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "VAR", "index": "31", "type": "numeric", "distinct": "219", "missing": "0", "min": "71", "max": "5678", "mean": "436", "stdev": "549" }, { "name": "Eig14_EA.dm.", "index": "32", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "33", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "CATS2D_00_DP", "index": "34", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "CATS2D_00_PP", "index": "35", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "NsNH2", "index": "36", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "14", "mean": "2", "stdev": "2" }, { "name": "Eig15_EA.dm.", "index": "37", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SssNH", "index": "38", "type": "numeric", "distinct": "261", "missing": "0", "min": "0", "max": "104", "mean": "10", "stdev": "12" }, { "name": "P_VSA_LogP_5", "index": "39", "type": "numeric", "distinct": "148", "missing": "0", "min": "6", "max": "125", "mean": "48", "stdev": "20" }, { "name": "SRW09", "index": "40", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "8", "mean": "7", "stdev": "2" }, { "name": "C.028", "index": "41", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "CATS2D_08_DL", "index": "42", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "64", "mean": "12", "stdev": "11" }, { "name": "SpMax7_Bh.m.", "index": "43", "type": "numeric", "distinct": "292", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "C.042", "index": "44", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nRCONH2", "index": "45", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_m_2", "index": "46", "type": "numeric", "distinct": "360", "missing": "0", "min": "141", "max": "2093", "mean": "395", "stdev": "237" }, { "name": "SpMaxA_EA.ed.", "index": "47", "type": "numeric", "distinct": "174", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "48", "type": "numeric", "distinct": "313", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MATS1e", "index": "49", "type": "numeric", "distinct": "146", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "50", "type": "numeric", "distinct": "109", "missing": "0", "min": "12", "max": "1327", "mean": "192", "stdev": "154" }, { "name": "IC1", "index": "51", "type": "numeric", "distinct": "310", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SRW07", "index": "52", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "SpMAD_EA.dm.", "index": "53", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "54", "type": "numeric", "distinct": "117", "missing": "0", "min": "12", "max": "1327", "mean": "192", "stdev": "154" }, { "name": "ATS1s", "index": "55", "type": "numeric", "distinct": "338", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "N.073", "index": "56", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NaaNH", "index": "57", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "AECC", "index": "58", "type": "numeric", "distinct": "351", "missing": "0", "min": "8", "max": "52", "mean": "16", "stdev": "6" }, { "name": "AAC", "index": "59", "type": "numeric", "distinct": "228", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "60", "type": "numeric", "distinct": "228", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CENT", "index": "61", "type": "numeric", "distinct": "359", "missing": "0", "min": "645", "max": "799434", "mean": "16686", "stdev": "51371" }, { "name": "HNar", "index": "62", "type": "numeric", "distinct": "140", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS7m", "index": "63", "type": "numeric", "distinct": "380", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "MATS5s", "index": "64", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CIC1", "index": "65", "type": "numeric", "distinct": "336", "missing": "0", "min": "2", "max": "6", "mean": "3", "stdev": "1" }, { "name": "ATS3s", "index": "66", "type": "numeric", "distinct": "365", "missing": "0", "min": "6", "max": "9", "mean": "7", "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 }