{ "data_id": "39297", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3942", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3942", "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: CHEMBL3942 (TID: 17073), and it has 391 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": "2016-07-16 07:24:59", "update_comment": null, "last_update": "2016-07-16 07:24:59", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3669702\/data_53116.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3942", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3942 (TID: 17073), and it has 391 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": 391, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.17391304347826086, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.5787551598641953, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.7397188333509308, "Quartile2MeansOfNumericAtts": 3.7289002557544766, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 25.968806853611753, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.908032150116949, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8468403228562609, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 3.00033442952002, "MaxKurtosisOfNumericAtts": 5.878104744675392, "MinMeansOfNumericAtts": -3.4543989769820973, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 285.214989769821, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.4246563466926854, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 7.113452685421994, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.3103507777728018, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.308192040141033, "MinStdDevOfNumericAtts": 0.04751732446525183, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.1716780819825292, "MaxStdDevOfNumericAtts": 149.83392017229346, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.40006787439261826, "Quartile3StdDevOfNumericAtts": 6.6091138285745705, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0253529411764706, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.6201244802552495, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 39.12679150284384, "Quartile1SkewnessOfNumericAtts": 0.41742115884945347, "AutoCorrelation": -0.3251974358974353, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.8063132101435455 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "271", "missing": "0", "target": "1", "min": "4", "max": "11", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "391", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_03_DL", "index": "1", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "26", "mean": "5", "stdev": "5" }, { "name": "GATS2p", "index": "2", "type": "numeric", "distinct": "254", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "3", "type": "numeric", "distinct": "104", "missing": "0", "min": "3", "max": "399", "mean": "87", "stdev": "80" }, { "name": "Hy", "index": "4", "type": "numeric", "distinct": "258", "missing": "0", "min": "-1", "max": "15", "mean": "2", "stdev": "3" }, { "name": "CATS2D_06_DA", "index": "5", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "20", "mean": "3", "stdev": "4" }, { "name": "GATS2i", "index": "6", "type": "numeric", "distinct": "243", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "7", "type": "numeric", "distinct": "259", "missing": "0", "min": "17", "max": "490", "mean": "118", "stdev": "96" }, { "name": "P_VSA_s_5", "index": "8", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "194", "mean": "45", "stdev": "46" }, { "name": "TPSA.Tot.", "index": "9", "type": "numeric", "distinct": "208", "missing": "0", "min": "15", "max": "562", "mean": "158", "stdev": "106" }, { "name": "GATS2v", "index": "10", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.050", "index": "11", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "22", "mean": "5", "stdev": "5" }, { "name": "nHDon", "index": "12", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "22", "mean": "5", "stdev": "5" }, { "name": "P_VSA_LogP_2", "index": "13", "type": "numeric", "distinct": "192", "missing": "0", "min": "5", "max": "435", "mean": "91", "stdev": "83" }, { "name": "CATS2D_02_DA", "index": "14", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "3", "stdev": "3" }, { "name": "CATS2D_06_DD", "index": "15", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "13", "mean": "2", "stdev": "2" }, { "name": "P_VSA_p_2", "index": "16", "type": "numeric", "distinct": "197", "missing": "0", "min": "21", "max": "769", "mean": "214", "stdev": "144" }, { "name": "MATS2i", "index": "17", "type": "numeric", "distinct": "236", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DLS_06", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_DA", "index": "19", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "3", "stdev": "4" }, { "name": "P_VSA_v_2", "index": "20", "type": "numeric", "distinct": "211", "missing": "0", "min": "21", "max": "769", "mean": "223", "stdev": "138" }, { "name": "nRCONHR", "index": "21", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "CATS2D_03_DD", "index": "22", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "2" }, { "name": "NssNH", "index": "23", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "SAdon", "index": "24", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "406", "mean": "84", "stdev": "85" }, { "name": "DLS_07", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SdssC", "index": "26", "type": "numeric", "distinct": "310", "missing": "0", "min": "-12", "max": "1", "mean": "-2", "stdev": "2" }, { "name": "CATS2D_09_DD", "index": "27", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "SssNH", "index": "28", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "23", "mean": "6", "stdev": "6" }, { "name": "CATS2D_04_DL", "index": "29", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "21", "mean": "5", "stdev": "5" }, { "name": "SdO", "index": "30", "type": "numeric", "distinct": "316", "missing": "0", "min": "0", "max": "204", "mean": "55", "stdev": "38" }, { "name": "CATS2D_09_DL", "index": "31", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "35", "mean": "6", "stdev": "6" }, { "name": "O.058", "index": "32", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "DLS_cons", "index": "33", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NdO", "index": "34", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "3" }, { "name": "SsssCH", "index": "35", "type": "numeric", "distinct": "289", "missing": "0", "min": "-16", "max": "2", "mean": "-3", "stdev": "3" }, { "name": "MATS2p", "index": "36", "type": "numeric", "distinct": "227", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1e", "index": "37", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_08_DD", "index": "38", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "CATS2D_06_DL", "index": "39", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "29", "mean": "6", "stdev": "6" }, { "name": "CATS2D_05_DA", "index": "40", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "3" }, { "name": "Eig03_EA.dm.", "index": "41", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "1" }, { "name": "SAacc", "index": "42", "type": "numeric", "distinct": "198", "missing": "0", "min": "21", "max": "769", "mean": "217", "stdev": "135" }, { "name": "Eig05_AEA.dm.", "index": "43", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_LogP_4", "index": "44", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "473", "mean": "133", "stdev": "84" }, { "name": "MATS2v", "index": "45", "type": "numeric", "distinct": "202", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nArCONR2", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_DL", "index": "47", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "6", "stdev": "6" }, { "name": "ATSC5s", "index": "48", "type": "numeric", "distinct": "329", "missing": "0", "min": "26", "max": "793", "mean": "245", "stdev": "150" }, { "name": "C.040", "index": "49", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "ATSC7s", "index": "50", "type": "numeric", "distinct": "332", "missing": "0", "min": "24", "max": "784", "mean": "203", "stdev": "119" }, { "name": "Eig05_EA.dm.", "index": "51", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "P_VSA_i_4", "index": "52", "type": "numeric", "distinct": "122", "missing": "0", "min": "3", "max": "399", "mean": "96", "stdev": "77" }, { "name": "CATS2D_08_DL", "index": "53", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "34", "mean": "6", "stdev": "7" }, { "name": "ATS7s", "index": "54", "type": "numeric", "distinct": "293", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "CATS2D_07_DL", "index": "55", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "25", "mean": "6", "stdev": "6" }, { "name": "nDB", "index": "56", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "16", "mean": "4", "stdev": "3" }, { "name": "nCconj", "index": "57", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS7v", "index": "58", "type": "numeric", "distinct": "189", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "59", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "4" }, { "name": "P_VSA_MR_2", "index": "60", "type": "numeric", "distinct": "174", "missing": "0", "min": "35", "max": "736", "mean": "249", "stdev": "132" }, { "name": "NdssC", "index": "61", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "14", "mean": "4", "stdev": "3" }, { "name": "P_VSA_m_2", "index": "62", "type": "numeric", "distinct": "307", "missing": "0", "min": "130", "max": "709", "mean": "285", "stdev": "100" }, { "name": "BLTA96", "index": "63", "type": "numeric", "distinct": "249", "missing": "0", "min": "-8", "max": "3", "mean": "-3", "stdev": "2" }, { "name": "BLTD48", "index": "64", "type": "numeric", "distinct": "250", "missing": "0", "min": "-8", "max": "3", "mean": "-3", "stdev": "2" }, { "name": "BLTF96", "index": "65", "type": "numeric", "distinct": "246", "missing": "0", "min": "-7", "max": "3", "mean": "-3", "stdev": "2" }, { "name": "MLOGP", "index": "66", "type": "numeric", "distinct": "293", "missing": "0", "min": "-5", "max": "7", "mean": "2", "stdev": "2" } ], "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 }