DEVELOPMENT... { "data_id": "27018", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2971", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2971", "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: CHEMBL2971 (TID: 10938), and it has 1862 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": "unknown", "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 20:35:49", "update_comment": null, "last_update": "2016-07-14 20:35:49", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3318869\/data_53722.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2971", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2971 (TID: 10938), and it has 1862 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": 1862, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.61111111111111, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.010945684818607582, "Quartile1MeansOfNumericAtts": 1.0763372717508057, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -1.0047494044706577, "Quartile1StdDevOfNumericAtts": 0.1821061758352732, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.185670904592873, "Quartile2MeansOfNumericAtts": 2.52868850698174, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.24721480977888283, "Quartile2StdDevOfNumericAtts": 0.4724170698807179, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 2.967559970369033, "Quartile3MeansOfNumericAtts": 7.4334049409237375, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 0.6707844731877614, "Quartile3StdDevOfNumericAtts": 2.6360362225345666, "AutoCorrelation": 0.2425566899516368, "MeanMeansOfNumericAtts": 20.71632157607298, "ClassEntropy": null, "Dimensionality": 0.03866809881847476, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 21.418615707985136, "MaxMeansOfNumericAtts": 264.1121858216971, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 4.4172187641375, "MaxStdDevOfNumericAtts": 89.3031052664452, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 2.461208240237495, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 0.028034115803373585, "MeanStdDevOfNumericAtts": 7.381992941750304, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8976303270625356, "MinMeansOfNumericAtts": -0.09690708915145002, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.160144394356338, "MinStdDevOfNumericAtts": 0.01297444987013814, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "572", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "nBM", "index": "53", "type": "numeric", "distinct": "32", "missing": "0", "min": "2", "max": "35", "mean": "19", "stdev": "5" }, { "name": "piPC10", "index": "37", "type": "numeric", "distinct": "1138", "missing": "0", "min": "0", "max": "10", "mean": "8", "stdev": "1" }, { "name": "SpMax3_Bh.v.", "index": "52", "type": "numeric", "distinct": "597", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC5", "index": "51", "type": "numeric", "distinct": "790", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC6v", "index": "50", "type": "numeric", "distinct": "1739", "missing": "0", "min": "0", "max": "35", "mean": "11", "stdev": "5" }, { "name": "SpMin3_Bh.s.", "index": "49", "type": "numeric", "distinct": "591", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.047", "index": "48", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "36", "mean": "12", "stdev": "6" }, { "name": "Mp", "index": "47", "type": "numeric", "distinct": "180", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "46", "type": "numeric", "distinct": "684", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DLS_04", "index": "45", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1m", "index": "44", "type": "numeric", "distinct": "221", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nCsp3", "index": "43", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "3" }, { "name": "nN", "index": "42", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "20", "mean": "5", "stdev": "2" }, { "name": "SpMin3_Bh.m.", "index": "41", "type": "numeric", "distinct": "510", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nAT", "index": "40", "type": "numeric", "distinct": "72", "missing": "0", "min": "15", "max": "104", "mean": "47", "stdev": "13" }, { "name": "ISIZ", "index": "39", "type": "numeric", "distinct": "72", "missing": "0", "min": "59", "max": "697", "mean": "264", "stdev": "89" }, { "name": "piPC03", "index": "38", "type": "numeric", "distinct": "706", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "nHet", "index": "36", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "22", "mean": "7", "stdev": "2" }, { "name": "ATS4i", "index": "62", "type": "numeric", "distinct": "1019", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "NaaN", "index": "70", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "N.075", "index": "69", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "SpMin7_Bh.p.", "index": "68", "type": "numeric", "distinct": "700", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig08_AEA.dm.", "index": "67", "type": "numeric", "distinct": "959", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ATSC2m", "index": "66", "type": "numeric", "distinct": "1641", "missing": "0", "min": "1", "max": "72", "mean": "17", "stdev": "7" }, { "name": "piPC07", "index": "65", "type": "numeric", "distinct": "1037", "missing": "0", "min": "2", "max": "9", "mean": "7", "stdev": "1" }, { "name": "Mv", "index": "64", "type": "numeric", "distinct": "184", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_3", "index": "63", "type": "numeric", "distinct": "460", "missing": "0", "min": "0", "max": "469", "mean": "76", "stdev": "32" }, { "name": "Uc", "index": "54", "type": "numeric", "distinct": "32", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig03_EA.ri.", "index": "61", "type": "numeric", "distinct": "723", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "P_VSA_i_4", "index": "60", "type": "numeric", "distinct": "621", "missing": "0", "min": "0", "max": "469", "mean": "81", "stdev": "35" }, { "name": "D.Dtr09", "index": "59", "type": "numeric", "distinct": "895", "missing": "0", "min": "0", "max": "439", "mean": "72", "stdev": "74" }, { "name": "SpMin8_Bh.m.", "index": "58", "type": "numeric", "distinct": "691", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig03_AEA.ri.", "index": "57", "type": "numeric", "distinct": "733", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NRS", "index": "56", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "SpMax3_Bh.p.", "index": "55", "type": "numeric", "distinct": "611", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MATS1v", "index": "9", "type": "numeric", "distinct": "210", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "17", "type": "numeric", "distinct": "605", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "P_VSA_m_2", "index": "16", "type": "numeric", "distinct": "1644", "missing": "0", "min": "40", "max": "620", "mean": "194", "stdev": "48" }, { "name": "SpMin3_Bh.e.", "index": "15", "type": "numeric", "distinct": "546", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "TIC2", "index": "14", "type": "numeric", "distinct": "1567", "missing": "0", "min": "51", "max": "469", "mean": "215", "stdev": "68" }, { "name": "ATSC1i", "index": "13", "type": "numeric", "distinct": "720", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_betaS_A", "index": "12", "type": "numeric", "distinct": "147", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1p", "index": "11", "type": "numeric", "distinct": "619", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IC2", "index": "10", "type": "numeric", "distinct": "911", "missing": "0", "min": "2", "max": "5", "mean": "5", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "18", "type": "numeric", "distinct": "1419", "missing": "0", "min": "0", "max": "54", "mean": "19", "stdev": "8" }, { "name": "MATS1i", "index": "8", "type": "numeric", "distinct": "572", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "7", "type": "numeric", "distinct": "1488", "missing": "0", "min": "0", "max": "81", "mean": "27", "stdev": "14" }, { "name": "n124.Triazines", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_AA", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "2" }, { "name": "C.032", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "MATS1p", "index": "3", "type": "numeric", "distinct": "364", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SaaN", "index": "2", "type": "numeric", "distinct": "1397", "missing": "0", "min": "0", "max": "26", "mean": "8", "stdev": "5" }, { "name": "nArNHR", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Mi", "index": "27", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "IC3", "index": "35", "type": "numeric", "distinct": "848", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SssCH2", "index": "34", "type": "numeric", "distinct": "1094", "missing": "0", "min": "-1", "max": "22", "mean": "2", "stdev": "2" }, { "name": "C.006", "index": "33", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "GATS1v", "index": "32", "type": "numeric", "distinct": "459", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MPC08", "index": "31", "type": "numeric", "distinct": "283", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "NssCH2", "index": "30", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "3" }, { "name": "SpMin3_Bh.v.", "index": "29", "type": "numeric", "distinct": "475", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "C.", "index": "28", "type": "numeric", "distinct": "165", "missing": "0", "min": "25", "max": "59", "mean": "43", "stdev": "4" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1862", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SsssN", "index": "26", "type": "numeric", "distinct": "585", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "2" }, { "name": "SpMaxA_AEA.dm.", "index": "25", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin4_Bh.e.", "index": "24", "type": "numeric", "distinct": "676", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "23", "type": "numeric", "distinct": "572", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nCIC", "index": "22", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "4", "stdev": "1" }, { "name": "SpMin4_Bh.p.", "index": "21", "type": "numeric", "distinct": "595", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "TIC3", "index": "20", "type": "numeric", "distinct": "1262", "missing": "0", "min": "51", "max": "511", "mean": "236", "stdev": "76" }, { "name": "N.073", "index": "19", "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 }