{ "data_id": "38695", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3190", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3190", "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: CHEMBL3190 (TID: 12615), and it has 125 rows and 65 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 05:09:50", "update_comment": null, "last_update": "2016-07-16 05:09:50", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3649622\/data_52883.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3190", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3190 (TID: 12615), and it has 125 rows and 65 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": 125, "NumberOfFeatures": 67, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 66, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.805506225871788, "MinMeansOfNumericAtts": -0.141376, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.5879743519569776, "MaxMeansOfNumericAtts": 82.771792, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 5.82249, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.50746268656717, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5869471202191667, "PercentageOfSymbolicFeatures": 1.4925373134328357, "Quartile3SkewnessOfNumericAtts": 0.9170271923133261, "MaxSkewnessOfNumericAtts": 2.7436793285999643, "MinStdDevOfNumericAtts": 0.012674190182184953, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 1.1694970825096749, "MaxStdDevOfNumericAtts": 45.360158021979686, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9389846368909883, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.4403, "MeanKurtosisOfNumericAtts": 0.3962158194477536, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 7.027607757575757, "Quartile1SkewnessOfNumericAtts": -0.7381127333647689, "AutoCorrelation": 0.11737903225806423, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.2083383558668701, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.536, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.04923660355675974, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.15768992629295348, "Quartile2MeansOfNumericAtts": 1.570916, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.8987449720690814, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.1765555855065996, "Quartile2StdDevOfNumericAtts": 0.6023040730922546, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.586730579158647, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "66", "type": "numeric", "distinct": "96", "missing": "0", "target": "1", "min": "3", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "125", "missing": "0", "identifier": "1", "distr": [] }, { "name": "GATS4e", "index": "1", "type": "numeric", "distinct": "112", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS4s", "index": "2", "type": "numeric", "distinct": "113", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "CATS2D_08_NL", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MATS4e", "index": "4", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_09_AL", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "3", "stdev": "3" }, { "name": "ATSC1s", "index": "6", "type": "numeric", "distinct": "112", "missing": "0", "min": "7", "max": "63", "mean": "21", "stdev": "11" }, { "name": "StN", "index": "7", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "5" }, { "name": "ATSC4s", "index": "8", "type": "numeric", "distinct": "118", "missing": "0", "min": "20", "max": "243", "mean": "83", "stdev": "45" }, { "name": "ATSC4e", "index": "9", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GATS2i", "index": "10", "type": "numeric", "distinct": "98", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1e", "index": "11", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "12", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC3s", "index": "13", "type": "numeric", "distinct": "118", "missing": "0", "min": "16", "max": "262", "mean": "61", "stdev": "39" }, { "name": "StsC", "index": "14", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "nArCOOH", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI4", "index": "16", "type": "numeric", "distinct": "65", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "GATS2s", "index": "17", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_02_DA", "index": "18", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "1" }, { "name": "nArCN", "index": "19", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nCsp", "index": "20", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nTB", "index": "21", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NtN", "index": "22", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "NtsC", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "Eig01_EA.ri.", "index": "24", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax_EA.ri.", "index": "25", "type": "numeric", "distinct": "65", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "NaasC", "index": "26", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "3" }, { "name": "CATS2D_05_NL", "index": "27", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "GATS2v", "index": "28", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "PW5", "index": "29", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_NL", "index": "30", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_NL", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "P_VSA_LogP_5", "index": "32", "type": "numeric", "distinct": "56", "missing": "0", "min": "0", "max": "89", "mean": "26", "stdev": "22" }, { "name": "MATS4i", "index": "33", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "piPC08", "index": "34", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "2" }, { "name": "GATS3s", "index": "35", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMAD_AEA.bo.", "index": "36", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "BIC3", "index": "37", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "piPC06", "index": "38", "type": "numeric", "distinct": "86", "missing": "0", "min": "2", "max": "7", "mean": "5", "stdev": "1" }, { "name": "MATS1s", "index": "39", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MPC06", "index": "40", "type": "numeric", "distinct": "60", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MWC08", "index": "41", "type": "numeric", "distinct": "84", "missing": "0", "min": "8", "max": "11", "mean": "10", "stdev": "0" }, { "name": "Eig04_AEA.ed.", "index": "42", "type": "numeric", "distinct": "70", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig04_EA.ed.", "index": "43", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "8", "mean": "6", "stdev": "2" }, { "name": "SM13_AEA.dm.", "index": "44", "type": "numeric", "distinct": "79", "missing": "0", "min": "1", "max": "8", "mean": "6", "stdev": "2" }, { "name": "C.025", "index": "45", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "2" }, { "name": "piPC07", "index": "46", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "8", "mean": "6", "stdev": "1" }, { "name": "piPC09", "index": "47", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "2" }, { "name": "ATSC2s", "index": "48", "type": "numeric", "distinct": "118", "missing": "0", "min": "13", "max": "199", "mean": "58", "stdev": "27" }, { "name": "PW4", "index": "49", "type": "numeric", "distinct": "59", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM08_EA.ri.", "index": "50", "type": "numeric", "distinct": "116", "missing": "0", "min": "8", "max": "10", "mean": "10", "stdev": "1" }, { "name": "CATS2D_07_NL", "index": "51", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "MAXDN", "index": "52", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "7", "mean": "3", "stdev": "1" }, { "name": "SM15_EA.ri.", "index": "53", "type": "numeric", "distinct": "114", "missing": "0", "min": "14", "max": "19", "mean": "17", "stdev": "1" }, { "name": "SpDiam_EA.ri.", "index": "54", "type": "numeric", "distinct": "68", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "MWC07", "index": "55", "type": "numeric", "distinct": "81", "missing": "0", "min": "7", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SpMAD_AEA.dm.", "index": "56", "type": "numeric", "distinct": "92", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM11_EA.ri.", "index": "57", "type": "numeric", "distinct": "116", "missing": "0", "min": "11", "max": "14", "mean": "13", "stdev": "1" }, { "name": "SM12_EA.ri.", "index": "58", "type": "numeric", "distinct": "113", "missing": "0", "min": "12", "max": "15", "mean": "14", "stdev": "1" }, { "name": "SM13_EA.ri.", "index": "59", "type": "numeric", "distinct": "110", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "1" }, { "name": "SM14_EA.ri.", "index": "60", "type": "numeric", "distinct": "113", "missing": "0", "min": "14", "max": "17", "mean": "16", "stdev": "1" }, { "name": "GATS3e", "index": "61", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC3e", "index": "62", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig07_AEA.dm.", "index": "63", "type": "numeric", "distinct": "87", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM09_EA.ri.", "index": "64", "type": "numeric", "distinct": "112", "missing": "0", "min": "9", "max": "11", "mean": "11", "stdev": "1" }, { "name": "JGI3", "index": "65", "type": "numeric", "distinct": "35", "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 }