DEVELOPMENT... { "data_id": "27934", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3959", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3959", "version": 7, "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: CHEMBL3959 (TID: 10170), and it has 233 rows and 66 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 22:44:59", "update_comment": null, "last_update": "2016-07-14 22:44:59", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3345002\/data_53103.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3959", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3959 (TID: 10170), and it has 233 rows and 66 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": 233, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "Quartile1MutualInformation": null, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 98.52941176470588, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 0.02058437077309172, "Quartile1MeansOfNumericAtts": 1.268068669527897, "StdvNominalAttDistinctValues": null, "Quartile1SkewnessOfNumericAtts": -0.11828843543504892, "Quartile1StdDevOfNumericAtts": 0.2559307041839405, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 0.7068520478269815, "Quartile2MeansOfNumericAtts": 2.8744935622317596, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.5176232992617518, "Quartile2StdDevOfNumericAtts": 0.860875166790807, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 2.122649952562296, "Quartile3MeansOfNumericAtts": 5.22968669527897, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 1.0244262400447397, "Quartile3StdDevOfNumericAtts": 1.9434718997225289, "AutoCorrelation": 0.10088362068965567, "MeanMeansOfNumericAtts": 28.96252021010826, "ClassEntropy": null, "Dimensionality": 0.2918454935622318, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 14.221673838843314, "MaxMeansOfNumericAtts": 709.4463519313302, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": null, "MaxSkewnessOfNumericAtts": 2.830004837981878, "MaxStdDevOfNumericAtts": 523.163806925441, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 1.716427968833205, "NumberOfBinaryFeatures": 0, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": null, "MeanSkewnessOfNumericAtts": 0.47236132763983535, "MeanStdDevOfNumericAtts": 13.797838475672577, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9586981943369461, "MinMeansOfNumericAtts": -0.027502145922746857, "MinMutualInformation": null, "MinNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.4533683174858476, "MinStdDevOfNumericAtts": 0.005747643667218934, "MinorityClassPercentage": null, "MinorityClassSize": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "191", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "ATSC3m", "index": "50", "type": "numeric", "distinct": "220", "missing": "0", "min": "7", "max": "52", "mean": "19", "stdev": "7" }, { "name": "TIC2", "index": "35", "type": "numeric", "distinct": "191", "missing": "0", "min": "63", "max": "339", "mean": "164", "stdev": "46" }, { "name": "TIC3", "index": "49", "type": "numeric", "distinct": "168", "missing": "0", "min": "78", "max": "369", "mean": "181", "stdev": "51" }, { "name": "H.052", "index": "48", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "2" }, { "name": "SIC3", "index": "47", "type": "numeric", "distinct": "115", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "TIC4", "index": "46", "type": "numeric", "distinct": "154", "missing": "0", "min": "84", "max": "374", "mean": "185", "stdev": "53" }, { "name": "IDE", "index": "45", "type": "numeric", "distinct": "185", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "GGI8", "index": "44", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2i", "index": "43", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "IC1", "index": "42", "type": "numeric", "distinct": "173", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MDDD", "index": "41", "type": "numeric", "distinct": "193", "missing": "0", "min": "4", "max": "52", "mean": "18", "stdev": "8" }, { "name": "GGI7", "index": "40", "type": "numeric", "distinct": "127", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS8m", "index": "39", "type": "numeric", "distinct": "208", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "ATS3i", "index": "38", "type": "numeric", "distinct": "186", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "RBN", "index": "37", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "11", "mean": "4", "stdev": "2" }, { "name": "SaaaC", "index": "36", "type": "numeric", "distinct": "147", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "LOC", "index": "34", "type": "numeric", "distinct": "136", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "AECC", "index": "51", "type": "numeric", "distinct": "171", "missing": "0", "min": "5", "max": "17", "mean": "9", "stdev": "2" }, { "name": "DBI", "index": "52", "type": "numeric", "distinct": "32", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "VAR", "index": "53", "type": "numeric", "distinct": "93", "missing": "0", "min": "16", "max": "228", "mean": "73", "stdev": "37" }, { "name": "SpMin3_Bh.s.", "index": "54", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CATS2D_02_DL", "index": "55", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "HVcpx", "index": "56", "type": "numeric", "distinct": "176", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "AMR", "index": "57", "type": "numeric", "distinct": "201", "missing": "0", "min": "46", "max": "151", "mean": "86", "stdev": "20" }, { "name": "TIC5", "index": "58", "type": "numeric", "distinct": "153", "missing": "0", "min": "86", "max": "374", "mean": "187", "stdev": "53" }, { "name": "SpMax6_Bh.m.", "index": "59", "type": "numeric", "distinct": "186", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "X0v", "index": "60", "type": "numeric", "distinct": "194", "missing": "0", "min": "6", "max": "21", "mean": "13", "stdev": "3" }, { "name": "ATS8s", "index": "61", "type": "numeric", "distinct": "209", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATSC3i", "index": "62", "type": "numeric", "distinct": "192", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1i", "index": "63", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CENT", "index": "64", "type": "numeric", "distinct": "179", "missing": "0", "min": "82", "max": "2915", "mean": "709", "stdev": "523" }, { "name": "X1v", "index": "65", "type": "numeric", "distinct": "207", "missing": "0", "min": "4", "max": "13", "mean": "7", "stdev": "2" }, { "name": "Eig04_EA", "index": "66", "type": "numeric", "distinct": "158", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "CATS2D_07_DL", "index": "8", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "GGI9", "index": "16", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "JGI9", "index": "15", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_2", "index": "14", "type": "numeric", "distinct": "52", "missing": "0", "min": "0", "max": "66", "mean": "17", "stdev": "16" }, { "name": "Hy", "index": "13", "type": "numeric", "distinct": "134", "missing": "0", "min": "-1", "max": "4", "mean": "0", "stdev": "1" }, { "name": "CATS2D_04_DL", "index": "12", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "CATS2D_05_DL", "index": "11", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "SpMax3_Bh.e.", "index": "10", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC4", "index": "9", "type": "numeric", "distinct": "141", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_03_DL", "index": "17", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "2" }, { "name": "ATS7m", "index": "7", "type": "numeric", "distinct": "210", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "IC3", "index": "6", "type": "numeric", "distinct": "151", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_06_DL", "index": "5", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "IC2", "index": "4", "type": "numeric", "distinct": "179", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.006", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "NssCH2", "index": "2", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "SssCH2", "index": "1", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "2" }, { "name": "SpMin4_Bh.e.", "index": "25", "type": "numeric", "distinct": "172", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SssNH", "index": "33", "type": "numeric", "distinct": "130", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "2" }, { "name": "NssNH", "index": "32", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax4_Bh.m.", "index": "31", "type": "numeric", "distinct": "172", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.m.", "index": "30", "type": "numeric", "distinct": "173", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "29", "type": "numeric", "distinct": "194", "missing": "0", "min": "3", "max": "9", "mean": "5", "stdev": "1" }, { "name": "BIC3", "index": "28", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "27", "type": "numeric", "distinct": "161", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "DECC", "index": "26", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "233", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin1_Bh.s.", "index": "24", "type": "numeric", "distinct": "130", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ICR", "index": "23", "type": "numeric", "distinct": "142", "missing": "0", "min": "2", "max": "4", "mean": "2", "stdev": "0" }, { "name": "SAdon", "index": "22", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "256", "mean": "28", "stdev": "30" }, { "name": "nHDon", "index": "21", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "H.050", "index": "20", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "TIC1", "index": "19", "type": "numeric", "distinct": "188", "missing": "0", "min": "47", "max": "264", "mean": "132", "stdev": "35" }, { "name": "RBF", "index": "18", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "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 }