{ "data_id": "35591", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3593", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3593", "version": 10, "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: CHEMBL3593 (TID: 11231), and it has 126 rows and 62 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 18:27:21", "update_comment": null, "last_update": "2016-07-15 18:27:21", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3562334\/data_52453.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3593", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3593 (TID: 11231), and it has 126 rows and 62 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": 126, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.5079365079365079, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.6517784811919527, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.42414360010564334, "Quartile2MeansOfNumericAtts": 1.5983095238095237, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 11.049005695864496, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.43584130359341855, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0019749872938473, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.21954025671265928, "MaxKurtosisOfNumericAtts": 20.855968550058307, "MinMeansOfNumericAtts": -0.07509523809523809, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 349.0179523809524, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.0471314933433504, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MeansOfNumericAtts": 11.8015873015873, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.7434684997170888, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.6869724895913714, "MinStdDevOfNumericAtts": 0.008895185071729398, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.196571409162487, "MaxStdDevOfNumericAtts": 97.1360653107882, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.012769602246113898, "Quartile3StdDevOfNumericAtts": 3.06198400252941, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.5370714285714285, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.8839143161602387, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 38.39578546233308, "Quartile1SkewnessOfNumericAtts": -0.6418156456504116, "AutoCorrelation": -0.03998400000000015, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.08852535714213669 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "113", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "126", "missing": "0", "identifier": "1", "distr": [] }, { "name": "MATS3s", "index": "1", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3m", "index": "2", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "C.001", "index": "3", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "P_VSA_LogP_1", "index": "4", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "71", "mean": "17", "stdev": "18" }, { "name": "SpMin5_Bh.m.", "index": "5", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SsCH3", "index": "6", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "4" }, { "name": "nCp", "index": "7", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SpMin7_Bh.v.", "index": "8", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "NsCH3", "index": "9", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "BIC4", "index": "10", "type": "numeric", "distinct": "66", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "BIC5", "index": "11", "type": "numeric", "distinct": "64", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.039", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ON0V", "index": "13", "type": "numeric", "distinct": "90", "missing": "0", "min": "7", "max": "17", "mean": "11", "stdev": "2" }, { "name": "SpMin5_Bh.e.", "index": "14", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_5", "index": "15", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "94", "mean": "37", "stdev": "20" }, { "name": "SpMin7_Bh.p.", "index": "16", "type": "numeric", "distinct": "77", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig04_AEA.bo.", "index": "17", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GATS1e", "index": "18", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS3e", "index": "19", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin5_Bh.p.", "index": "20", "type": "numeric", "distinct": "82", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin5_Bh.v.", "index": "21", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_02_LL", "index": "22", "type": "numeric", "distinct": "23", "missing": "0", "min": "5", "max": "31", "mean": "14", "stdev": "6" }, { "name": "CATS2D_03_LL", "index": "23", "type": "numeric", "distinct": "25", "missing": "0", "min": "2", "max": "31", "mean": "12", "stdev": "6" }, { "name": "GATS3s", "index": "24", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_sh_p", "index": "25", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC1v", "index": "26", "type": "numeric", "distinct": "103", "missing": "0", "min": "5", "max": "13", "mean": "8", "stdev": "2" }, { "name": "X5A", "index": "27", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "H.047", "index": "28", "type": "numeric", "distinct": "19", "missing": "0", "min": "6", "max": "29", "mean": "18", "stdev": "5" }, { "name": "Yindex", "index": "29", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssN", "index": "30", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "1" }, { "name": "SpMin7_Bh.e.", "index": "31", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "32", "type": "numeric", "distinct": "71", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_C_A", "index": "33", "type": "numeric", "distinct": "103", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Vindex", "index": "34", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Xindex", "index": "35", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2v", "index": "36", "type": "numeric", "distinct": "105", "missing": "0", "min": "8", "max": "21", "mean": "13", "stdev": "3" }, { "name": "Eta_beta_A", "index": "37", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nH", "index": "38", "type": "numeric", "distinct": "24", "missing": "0", "min": "19", "max": "52", "mean": "30", "stdev": "8" }, { "name": "BIC1", "index": "39", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC1", "index": "40", "type": "numeric", "distinct": "94", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "1" }, { "name": "GNar", "index": "41", "type": "numeric", "distinct": "57", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "42", "type": "numeric", "distinct": "69", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X0A", "index": "43", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MCD", "index": "44", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X2A", "index": "45", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_AL", "index": "46", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "15", "mean": "7", "stdev": "3" }, { "name": "CATS2D_07_AL", "index": "47", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "4", "stdev": "2" }, { "name": "P_VSA_MR_1", "index": "48", "type": "numeric", "distinct": "35", "missing": "0", "min": "153", "max": "518", "mean": "293", "stdev": "68" }, { "name": "PW3", "index": "49", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "PW5", "index": "50", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SIC1", "index": "51", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_FL_A", "index": "52", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ON1V", "index": "53", "type": "numeric", "distinct": "93", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "P_VSA_e_1", "index": "54", "type": "numeric", "distinct": "28", "missing": "0", "min": "200", "max": "612", "mean": "347", "stdev": "94" }, { "name": "P_VSA_LogP_7", "index": "55", "type": "numeric", "distinct": "41", "missing": "0", "min": "177", "max": "621", "mean": "349", "stdev": "97" }, { "name": "P_VSA_m_1", "index": "56", "type": "numeric", "distinct": "28", "missing": "0", "min": "200", "max": "612", "mean": "347", "stdev": "94" }, { "name": "P_VSA_MR_6", "index": "57", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "165", "mean": "92", "stdev": "37" }, { "name": "P_VSA_v_1", "index": "58", "type": "numeric", "distinct": "28", "missing": "0", "min": "200", "max": "612", "mean": "347", "stdev": "94" }, { "name": "Xu", "index": "59", "type": "numeric", "distinct": "82", "missing": "0", "min": "18", "max": "32", "mean": "28", "stdev": "2" }, { "name": "TPSA.Tot.", "index": "60", "type": "numeric", "distinct": "60", "missing": "0", "min": "12", "max": "99", "mean": "42", "stdev": "20" }, { "name": "X5sol", "index": "61", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "9", "mean": "6", "stdev": "1" }, { "name": "P_VSA_s_2", "index": "62", "type": "numeric", "distinct": "35", "missing": "0", "min": "200", "max": "612", "mean": "348", "stdev": "94" } ], "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 }