{ "data_id": "32722", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1871", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1871", "version": 8, "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: CHEMBL1871 (TID: 56), and it has 1631 rows and 70 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 10:56:41", "update_comment": null, "last_update": "2016-07-15 10:56:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3488016\/data_53637.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1871", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1871 (TID: 56), and it has 1631 rows and 70 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": 1631, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 13.660941435441556, "MinStdDevOfNumericAtts": 0.0059841754107606004, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.661763932974934, "MaxStdDevOfNumericAtts": 109.26903483279303, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.16008899564101897, "Quartile3StdDevOfNumericAtts": 1.780185873600387, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.7299006744328633, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 4.85814898968074, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 15.372504123453165, "Quartile1SkewnessOfNumericAtts": -0.1951514726967076, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.13229407006503768, "AutoCorrelation": 0.061014723926381034, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.22793066357722136, "Dimensionality": 0.04414469650521153, "MeanSkewnessOfNumericAtts": 0.5073149715609512, "Quartile2MeansOfNumericAtts": 3.336963212752912, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.351304278634252, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.18925244208770614, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.3551812150366387, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.23443789812238516, "MaxKurtosisOfNumericAtts": 281.17571291219195, "MinMeansOfNumericAtts": 0.0243868792152054, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 140.65578540772532, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.3629542840555984, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 5.049049662783579, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.0164649557833747, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "909", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1631", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CIC2", "index": "1", "type": "numeric", "distinct": "771", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "SpMAD_AEA.bo.", "index": "2", "type": "numeric", "distinct": "223", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "BIC2", "index": "3", "type": "numeric", "distinct": "256", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaasN", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "5", "type": "numeric", "distinct": "604", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SIC2", "index": "6", "type": "numeric", "distinct": "279", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax2_Bh.p.", "index": "7", "type": "numeric", "distinct": "421", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "8", "type": "numeric", "distinct": "603", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "C.034", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "N.073", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "11", "type": "numeric", "distinct": "545", "missing": "0", "min": "3", "max": "11", "mean": "4", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "12", "type": "numeric", "distinct": "537", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax3_Bh.e.", "index": "13", "type": "numeric", "distinct": "525", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NaasC", "index": "14", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "2" }, { "name": "SpMAD_EA.ed.", "index": "15", "type": "numeric", "distinct": "771", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MATS2i", "index": "16", "type": "numeric", "distinct": "517", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin3_Bh.p.", "index": "17", "type": "numeric", "distinct": "463", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SaaCH", "index": "18", "type": "numeric", "distinct": "1279", "missing": "0", "min": "0", "max": "32", "mean": "8", "stdev": "6" }, { "name": "JGI4", "index": "19", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nAB", "index": "20", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "28", "mean": "10", "stdev": "6" }, { "name": "PW2", "index": "21", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_B_A", "index": "22", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC4s", "index": "23", "type": "numeric", "distinct": "1490", "missing": "0", "min": "12", "max": "579", "mean": "115", "stdev": "83" }, { "name": "P_VSA_s_4", "index": "24", "type": "numeric", "distinct": "555", "missing": "0", "min": "0", "max": "218", "mean": "73", "stdev": "32" }, { "name": "JGI6", "index": "25", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_betaS_A", "index": "26", "type": "numeric", "distinct": "135", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "27", "type": "numeric", "distinct": "1231", "missing": "0", "min": "37", "max": "297", "mean": "123", "stdev": "40" }, { "name": "P_VSA_v_3", "index": "28", "type": "numeric", "distinct": "1231", "missing": "0", "min": "37", "max": "297", "mean": "123", "stdev": "40" }, { "name": "SpMaxA_EA.dm.", "index": "29", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "JGT", "index": "30", "type": "numeric", "distinct": "368", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_2", "index": "31", "type": "numeric", "distinct": "1227", "missing": "0", "min": "10", "max": "297", "mean": "115", "stdev": "38" }, { "name": "BIC3", "index": "32", "type": "numeric", "distinct": "167", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nBnz", "index": "33", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin2_Bh.m.", "index": "34", "type": "numeric", "distinct": "292", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMAD_AEA.ri.", "index": "35", "type": "numeric", "distinct": "193", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SaasC", "index": "36", "type": "numeric", "distinct": "1242", "missing": "0", "min": "-6", "max": "11", "mean": "1", "stdev": "3" }, { "name": "Eta_betaP_A", "index": "37", "type": "numeric", "distinct": "359", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaaCH", "index": "38", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "SpMAD_EA", "index": "39", "type": "numeric", "distinct": "181", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC4e", "index": "40", "type": "numeric", "distinct": "936", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS2i", "index": "41", "type": "numeric", "distinct": "563", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_09_LL", "index": "42", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "32", "mean": "4", "stdev": "5" }, { "name": "P_VSA_LogP_3", "index": "43", "type": "numeric", "distinct": "145", "missing": "0", "min": "0", "max": "232", "mean": "67", "stdev": "35" }, { "name": "Eta_beta", "index": "44", "type": "numeric", "distinct": "170", "missing": "0", "min": "6", "max": "96", "mean": "31", "stdev": "8" }, { "name": "SaaaC", "index": "45", "type": "numeric", "distinct": "262", "missing": "0", "min": "-1", "max": "5", "mean": "0", "stdev": "1" }, { "name": "BIC1", "index": "46", "type": "numeric", "distinct": "329", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA", "index": "47", "type": "numeric", "distinct": "434", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM09_AEA.bo.", "index": "48", "type": "numeric", "distinct": "434", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpDiam_EA", "index": "49", "type": "numeric", "distinct": "434", "missing": "0", "min": "5", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax_EA", "index": "50", "type": "numeric", "distinct": "434", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SIC1", "index": "51", "type": "numeric", "distinct": "351", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5s", "index": "52", "type": "numeric", "distinct": "1491", "missing": "0", "min": "12", "max": "691", "mean": "141", "stdev": "109" }, { "name": "CIC1", "index": "53", "type": "numeric", "distinct": "897", "missing": "0", "min": "1", "max": "5", "mean": "2", "stdev": "1" }, { "name": "SpDiam_EA.ed.", "index": "54", "type": "numeric", "distinct": "701", "missing": "0", "min": "15", "max": "31", "mean": "21", "stdev": "2" }, { "name": "ATSC8s", "index": "55", "type": "numeric", "distinct": "1480", "missing": "0", "min": "0", "max": "662", "mean": "113", "stdev": "88" }, { "name": "RFD", "index": "56", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig01_AEA.ri.", "index": "57", "type": "numeric", "distinct": "497", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "58", "type": "numeric", "distinct": "497", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "RCI", "index": "59", "type": "numeric", "distinct": "55", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS3s", "index": "60", "type": "numeric", "distinct": "667", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.ed.", "index": "61", "type": "numeric", "distinct": "611", "missing": "0", "min": "9", "max": "20", "mean": "13", "stdev": "2" }, { "name": "SM10_AEA.dm.", "index": "62", "type": "numeric", "distinct": "611", "missing": "0", "min": "9", "max": "20", "mean": "13", "stdev": "2" }, { "name": "SpMax_EA.ed.", "index": "63", "type": "numeric", "distinct": "611", "missing": "0", "min": "9", "max": "20", "mean": "13", "stdev": "2" }, { "name": "C.024", "index": "64", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "Eig03_EA.bo.", "index": "65", "type": "numeric", "distinct": "692", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "66", "type": "numeric", "distinct": "692", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IC1", "index": "67", "type": "numeric", "distinct": "787", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "68", "type": "numeric", "distinct": "553", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GATS6s", "index": "69", "type": "numeric", "distinct": "821", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2m", "index": "70", "type": "numeric", "distinct": "522", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" } ], "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 }