{ "data_id": "39457", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4393", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4393", "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: CHEMBL4393 (TID: 11871), and it has 462 rows and 68 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 07:59:53", "update_comment": null, "last_update": "2016-07-16 07:59:53", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3674330\/data_53296.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4393", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4393 (TID: 11871), and it has 462 rows and 68 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": 462, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.15151515151515152, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.001173257664703, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.5732800227209853, "Quartile2MeansOfNumericAtts": 5.3818636363636365, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 19.6940105270714, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.4765466258218544, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1581577085153516, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.9264107330478516, "MaxKurtosisOfNumericAtts": 118.42031236937595, "MinMeansOfNumericAtts": 0.07493939393939393, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 700.1160606060606, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.0160489091727865, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 30.587908008658008, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.044892483494084, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 8.225552772655954, "MinStdDevOfNumericAtts": 0.04097078352654041, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.3143373427687821, "MaxStdDevOfNumericAtts": 192.35995835847766, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.1590026168013603, "Quartile3StdDevOfNumericAtts": 14.87965887421663, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 2.608225108225109, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 5.705498314696101, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 60.78901069703243, "Quartile1SkewnessOfNumericAtts": -0.663213192540441, "AutoCorrelation": 0.01448590021691961, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3379345303955915 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "274", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "462", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_i_3", "index": "1", "type": "numeric", "distinct": "312", "missing": "0", "min": "24", "max": "1407", "mean": "328", "stdev": "125" }, { "name": "ATSC2p", "index": "2", "type": "numeric", "distinct": "395", "missing": "0", "min": "2", "max": "25", "mean": "8", "stdev": "3" }, { "name": "ATSC3p", "index": "3", "type": "numeric", "distinct": "408", "missing": "0", "min": "3", "max": "34", "mean": "11", "stdev": "4" }, { "name": "ATS4s", "index": "4", "type": "numeric", "distinct": "365", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "0" }, { "name": "ATSC4p", "index": "5", "type": "numeric", "distinct": "429", "missing": "0", "min": "3", "max": "36", "mean": "11", "stdev": "4" }, { "name": "P_VSA_p_2", "index": "6", "type": "numeric", "distinct": "185", "missing": "0", "min": "53", "max": "527", "mean": "149", "stdev": "59" }, { "name": "ATS3s", "index": "7", "type": "numeric", "distinct": "351", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "8", "type": "numeric", "distinct": "195", "missing": "0", "min": "42", "max": "352", "mean": "115", "stdev": "40" }, { "name": "Uindex", "index": "9", "type": "numeric", "distinct": "331", "missing": "0", "min": "19", "max": "386", "mean": "51", "stdev": "22" }, { "name": "ATS7s", "index": "10", "type": "numeric", "distinct": "380", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SPI", "index": "11", "type": "numeric", "distinct": "332", "missing": "0", "min": "0", "max": "77", "mean": "16", "stdev": "6" }, { "name": "SpMax4_Bh.p.", "index": "12", "type": "numeric", "distinct": "294", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS8s", "index": "13", "type": "numeric", "distinct": "386", "missing": "0", "min": "2", "max": "8", "mean": "6", "stdev": "1" }, { "name": "ATS6s", "index": "14", "type": "numeric", "distinct": "370", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "MAXDP", "index": "15", "type": "numeric", "distinct": "374", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATS2s", "index": "16", "type": "numeric", "distinct": "356", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "17", "type": "numeric", "distinct": "275", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_s_1", "index": "18", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "SpMax8_Bh.m.", "index": "19", "type": "numeric", "distinct": "272", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig04_AEA.dm.", "index": "20", "type": "numeric", "distinct": "267", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "21", "type": "numeric", "distinct": "267", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "22", "type": "numeric", "distinct": "270", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "GGI1", "index": "23", "type": "numeric", "distinct": "24", "missing": "0", "min": "3", "max": "22", "mean": "7", "stdev": "2" }, { "name": "TPSA.NO.", "index": "24", "type": "numeric", "distinct": "185", "missing": "0", "min": "37", "max": "352", "mean": "102", "stdev": "37" }, { "name": "CATS2D_07_AN", "index": "25", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax8_Bh.s.", "index": "26", "type": "numeric", "distinct": "310", "missing": "0", "min": "2", "max": "7", "mean": "4", "stdev": "1" }, { "name": "CATS2D_09_NL", "index": "27", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "ATS5m", "index": "28", "type": "numeric", "distinct": "365", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Psi_i_s", "index": "29", "type": "numeric", "distinct": "332", "missing": "0", "min": "33", "max": "219", "mean": "75", "stdev": "21" }, { "name": "SAacc", "index": "30", "type": "numeric", "distinct": "206", "missing": "0", "min": "34", "max": "527", "mean": "151", "stdev": "62" }, { "name": "SpMin4_Bh.v.", "index": "31", "type": "numeric", "distinct": "290", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax5_Bh.s.", "index": "32", "type": "numeric", "distinct": "238", "missing": "0", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "ATSC4m", "index": "33", "type": "numeric", "distinct": "437", "missing": "0", "min": "7", "max": "141", "mean": "35", "stdev": "14" }, { "name": "SpMin4_Bh.p.", "index": "34", "type": "numeric", "distinct": "288", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS4m", "index": "35", "type": "numeric", "distinct": "379", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GGI2", "index": "36", "type": "numeric", "distinct": "35", "missing": "0", "min": "1", "max": "11", "mean": "4", "stdev": "1" }, { "name": "PHI", "index": "37", "type": "numeric", "distinct": "368", "missing": "0", "min": "2", "max": "32", "mean": "6", "stdev": "2" }, { "name": "P_VSA_s_6", "index": "38", "type": "numeric", "distinct": "188", "missing": "0", "min": "34", "max": "464", "mean": "134", "stdev": "54" }, { "name": "SpMax6_Bh.e.", "index": "39", "type": "numeric", "distinct": "260", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_MR_1", "index": "40", "type": "numeric", "distinct": "74", "missing": "0", "min": "24", "max": "789", "mean": "198", "stdev": "75" }, { "name": "SpMin3_Bh.i.", "index": "41", "type": "numeric", "distinct": "259", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ZM2Mad", "index": "42", "type": "numeric", "distinct": "412", "missing": "0", "min": "74", "max": "516", "mean": "226", "stdev": "65" }, { "name": "O.058", "index": "43", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "1" }, { "name": "ATS3m", "index": "44", "type": "numeric", "distinct": "348", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "45", "type": "numeric", "distinct": "284", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "P_VSA_v_2", "index": "46", "type": "numeric", "distinct": "210", "missing": "0", "min": "53", "max": "527", "mean": "154", "stdev": "59" }, { "name": "SaaO", "index": "47", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "3" }, { "name": "NdO", "index": "48", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "1" }, { "name": "GGI4", "index": "49", "type": "numeric", "distinct": "262", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SM05_EA", "index": "50", "type": "numeric", "distinct": "117", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "SpMax1_Bh.i.", "index": "51", "type": "numeric", "distinct": "190", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NaaO", "index": "52", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SsOH", "index": "53", "type": "numeric", "distinct": "230", "missing": "0", "min": "0", "max": "91", "mean": "8", "stdev": "9" }, { "name": "SpMin1_Bh.p.", "index": "54", "type": "numeric", "distinct": "118", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MATS1m", "index": "55", "type": "numeric", "distinct": "181", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ZM2MulPer", "index": "56", "type": "numeric", "distinct": "410", "missing": "0", "min": "199", "max": "1075", "mean": "480", "stdev": "130" }, { "name": "ZM2V", "index": "57", "type": "numeric", "distinct": "247", "missing": "0", "min": "186", "max": "999", "mean": "449", "stdev": "121" }, { "name": "ATSC8m", "index": "58", "type": "numeric", "distinct": "428", "missing": "0", "min": "1", "max": "190", "mean": "26", "stdev": "15" }, { "name": "ZM2Per", "index": "59", "type": "numeric", "distinct": "409", "missing": "0", "min": "286", "max": "1559", "mean": "700", "stdev": "192" }, { "name": "ZM1Kup", "index": "60", "type": "numeric", "distinct": "392", "missing": "0", "min": "229", "max": "1361", "mean": "517", "stdev": "157" }, { "name": "NddssS", "index": "61", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "S.110", "index": "62", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "ATSC3s", "index": "63", "type": "numeric", "distinct": "432", "missing": "0", "min": "13", "max": "313", "mean": "82", "stdev": "46" }, { "name": "Eig03_AEA.ri.", "index": "64", "type": "numeric", "distinct": "277", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP", "index": "65", "type": "numeric", "distinct": "48", "missing": "0", "min": "3", "max": "31", "mean": "19", "stdev": "5" }, { "name": "SpMin1_Bh.s.", "index": "66", "type": "numeric", "distinct": "189", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "67", "type": "numeric", "distinct": "266", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "CATS2D_03_NL", "index": "68", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "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 }