{ "data_id": "27954", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1792", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1792", "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: CHEMBL1792 (TID: 11265), and it has 740 rows and 67 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": "2016-07-14 22:47:36", "update_comment": null, "last_update": "2016-07-14 22:47:36", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3345110\/data_53206.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-CHEMBL1792", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1792 (TID: 11265), and it has 740 rows and 67 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": 740, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 6.6278803368318115, "MinStdDevOfNumericAtts": 0.028924682665638753, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6325255266604767, "MaxStdDevOfNumericAtts": 397029.67416096333, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.6506652887918908, "Quartile3StdDevOfNumericAtts": 26.46849885343518, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.502041891891892, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.7392221963474912, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 4588.8848987679, "Quartile1SkewnessOfNumericAtts": -0.829293425380476, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4089940905359616, "AutoCorrelation": 0.08229769959404522, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.10633467684800757, "Dimensionality": 0.09324324324324325, "MeanSkewnessOfNumericAtts": 0.05690378154827697, "Quartile2MeansOfNumericAtts": 6.180556081081081, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5880.071472137798, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.04147721720449633, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9116307536790962, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7722305140428896, "MaxKurtosisOfNumericAtts": 67.94810246231657, "MinMeansOfNumericAtts": 0.06096216216216219, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 305435.52297297405, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.676247169185015, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 58.87794864864865, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.6779864433906178, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "385", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "740", "missing": "0", "identifier": "1", "distr": [] }, { "name": "N.067", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "nRNHR", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "0" }, { "name": "MAXDP", "index": "3", "type": "numeric", "distinct": "530", "missing": "0", "min": "2", "max": "9", "mean": "7", "stdev": "2" }, { "name": "SsCH3", "index": "4", "type": "numeric", "distinct": "485", "missing": "0", "min": "0", "max": "11", "mean": "3", "stdev": "2" }, { "name": "ATSC4p", "index": "5", "type": "numeric", "distinct": "554", "missing": "0", "min": "7", "max": "80", "mean": "31", "stdev": "13" }, { "name": "SpMin8_Bh.p.", "index": "6", "type": "numeric", "distinct": "261", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "7", "type": "numeric", "distinct": "268", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin8_Bh.i.", "index": "8", "type": "numeric", "distinct": "256", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax8_Bh.e.", "index": "9", "type": "numeric", "distinct": "274", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin8_Bh.e.", "index": "10", "type": "numeric", "distinct": "259", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MPC08", "index": "11", "type": "numeric", "distinct": "269", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMin8_Bh.v.", "index": "12", "type": "numeric", "distinct": "258", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax8_Bh.v.", "index": "13", "type": "numeric", "distinct": "270", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MPC07", "index": "14", "type": "numeric", "distinct": "248", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "MPC10", "index": "15", "type": "numeric", "distinct": "297", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpMax8_Bh.p.", "index": "16", "type": "numeric", "distinct": "277", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Wap", "index": "17", "type": "numeric", "distinct": "484", "missing": "0", "min": "12652", "max": "4884940", "mean": "305436", "stdev": "397030" }, { "name": "NssCH2", "index": "18", "type": "numeric", "distinct": "27", "missing": "0", "min": "1", "max": "41", "mean": "10", "stdev": "5" }, { "name": "ATS1p", "index": "19", "type": "numeric", "distinct": "411", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "ATS2p", "index": "20", "type": "numeric", "distinct": "431", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "21", "type": "numeric", "distinct": "441", "missing": "0", "min": "5", "max": "153", "mean": "46", "stdev": "19" }, { "name": "Xt", "index": "22", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "23", "type": "numeric", "distinct": "177", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "24", "type": "numeric", "distinct": "148", "missing": "0", "min": "177", "max": "1905", "mean": "644", "stdev": "257" }, { "name": "ATSC8p", "index": "25", "type": "numeric", "distinct": "583", "missing": "0", "min": "8", "max": "125", "mean": "45", "stdev": "22" }, { "name": "P_VSA_LogP_4", "index": "26", "type": "numeric", "distinct": "152", "missing": "0", "min": "19", "max": "1033", "mean": "250", "stdev": "153" }, { "name": "SpMin7_Bh.m.", "index": "27", "type": "numeric", "distinct": "231", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "28", "type": "numeric", "distinct": "466", "missing": "0", "min": "3", "max": "136", "mean": "44", "stdev": "17" }, { "name": "MPC09", "index": "29", "type": "numeric", "distinct": "291", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC6p", "index": "30", "type": "numeric", "distinct": "564", "missing": "0", "min": "8", "max": "104", "mean": "36", "stdev": "16" }, { "name": "X1MulPer", "index": "31", "type": "numeric", "distinct": "517", "missing": "0", "min": "8", "max": "69", "mean": "23", "stdev": "9" }, { "name": "ATSC8v", "index": "32", "type": "numeric", "distinct": "582", "missing": "0", "min": "11", "max": "186", "mean": "60", "stdev": "30" }, { "name": "Sp", "index": "33", "type": "numeric", "distinct": "493", "missing": "0", "min": "31", "max": "266", "mean": "90", "stdev": "37" }, { "name": "ATSC1p", "index": "34", "type": "numeric", "distinct": "493", "missing": "0", "min": "4", "max": "36", "mean": "13", "stdev": "5" }, { "name": "ATS5p", "index": "35", "type": "numeric", "distinct": "457", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "TPC", "index": "36", "type": "numeric", "distinct": "422", "missing": "0", "min": "7", "max": "12", "mean": "9", "stdev": "1" }, { "name": "ISIZ", "index": "37", "type": "numeric", "distinct": "151", "missing": "0", "min": "247", "max": "3762", "mean": "996", "stdev": "492" }, { "name": "nAT", "index": "38", "type": "numeric", "distinct": "151", "missing": "0", "min": "45", "max": "430", "mean": "138", "stdev": "58" }, { "name": "ATS1v", "index": "39", "type": "numeric", "distinct": "407", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "nBT", "index": "40", "type": "numeric", "distinct": "153", "missing": "0", "min": "48", "max": "437", "mean": "143", "stdev": "59" }, { "name": "ATS1e", "index": "41", "type": "numeric", "distinct": "402", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS6p", "index": "42", "type": "numeric", "distinct": "457", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATS5e", "index": "43", "type": "numeric", "distinct": "422", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS5i", "index": "44", "type": "numeric", "distinct": "434", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS6e", "index": "45", "type": "numeric", "distinct": "435", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS6i", "index": "46", "type": "numeric", "distinct": "441", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "GGI1", "index": "47", "type": "numeric", "distinct": "52", "missing": "0", "min": "4", "max": "51", "mean": "15", "stdev": "7" }, { "name": "SpMax8_Bh.m.", "index": "48", "type": "numeric", "distinct": "297", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "49", "type": "numeric", "distinct": "219", "missing": "0", "min": "0", "max": "1573", "mean": "385", "stdev": "224" }, { "name": "ATS8i", "index": "50", "type": "numeric", "distinct": "449", "missing": "0", "min": "5", "max": "8", "mean": "6", "stdev": "1" }, { "name": "SpMaxA_AEA.dm.", "index": "51", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2m", "index": "52", "type": "numeric", "distinct": "528", "missing": "0", "min": "15", "max": "184", "mean": "57", "stdev": "24" }, { "name": "nH", "index": "53", "type": "numeric", "distinct": "93", "missing": "0", "min": "19", "max": "209", "mean": "65", "stdev": "27" }, { "name": "ATSC1v", "index": "54", "type": "numeric", "distinct": "497", "missing": "0", "min": "5", "max": "50", "mean": "16", "stdev": "7" }, { "name": "nOHp", "index": "55", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "0" }, { "name": "ATSC1m", "index": "56", "type": "numeric", "distinct": "502", "missing": "0", "min": "8", "max": "99", "mean": "31", "stdev": "14" }, { "name": "NaasC", "index": "57", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "14", "mean": "5", "stdev": "2" }, { "name": "SpMin4_Bh.p.", "index": "58", "type": "numeric", "distinct": "153", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC8m", "index": "59", "type": "numeric", "distinct": "586", "missing": "0", "min": "21", "max": "481", "mean": "146", "stdev": "78" }, { "name": "P_VSA_e_1", "index": "60", "type": "numeric", "distinct": "79", "missing": "0", "min": "200", "max": "1825", "mean": "613", "stdev": "235" }, { "name": "P_VSA_m_1", "index": "61", "type": "numeric", "distinct": "79", "missing": "0", "min": "200", "max": "1825", "mean": "613", "stdev": "235" }, { "name": "P_VSA_s_2", "index": "62", "type": "numeric", "distinct": "101", "missing": "0", "min": "200", "max": "1825", "mean": "613", "stdev": "235" }, { "name": "P_VSA_v_1", "index": "63", "type": "numeric", "distinct": "79", "missing": "0", "min": "200", "max": "1825", "mean": "613", "stdev": "235" }, { "name": "CIC0", "index": "64", "type": "numeric", "distinct": "420", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATSC5m", "index": "65", "type": "numeric", "distinct": "573", "missing": "0", "min": "20", "max": "350", "mean": "109", "stdev": "52" }, { "name": "SpMin7_Bh.p.", "index": "66", "type": "numeric", "distinct": "222", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_p_1", "index": "67", "type": "numeric", "distinct": "111", "missing": "0", "min": "200", "max": "1825", "mean": "616", "stdev": "233" } ], "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 }