{ "data_id": "26468", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2069", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2069", "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: CHEMBL2069 (TID: 246), and it has 1135 rows and 68 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 19:19:11", "update_comment": null, "last_update": "2016-07-14 19:19:11", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3303845\/data_53391.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2069", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2069 (TID: 246), and it has 1135 rows and 68 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": 1135, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 3.6956555066079293, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.5076679196286924, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 78.46830369660985, "Quartile1SkewnessOfNumericAtts": -0.36571332647809873, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.23637690306693016, "AutoCorrelation": -0.12306878306878243, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.8977185845268196, "Dimensionality": 0.06167400881057269, "MeanSkewnessOfNumericAtts": 0.2521441228370223, "Quartile2MeansOfNumericAtts": 5.6431718061674, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 18.37485906027134, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.27090399584525926, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -0.7390909375742738, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5533893391950019, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 10.260393284432688, "MinMeansOfNumericAtts": 0.07534801762114537, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 665.4256651982379, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.1480900841829094, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 22.34465242290749, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.1776496734362998, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.3100580876726013, "MinStdDevOfNumericAtts": 0.007653516041343602, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6565370928853114, "MaxStdDevOfNumericAtts": 149.04246048256047, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.13105206151401738, "Quartile3StdDevOfNumericAtts": 8.733556970165676 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "582", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1135", "missing": "0", "identifier": "1", "distr": [] }, { "name": "D.Dtr07", "index": "1", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "176", "mean": "10", "stdev": "33" }, { "name": "nR07", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X5A", "index": "3", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig04_AEA.bo.", "index": "4", "type": "numeric", "distinct": "387", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "nCrs", "index": "5", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "SM06_AEA.bo.", "index": "6", "type": "numeric", "distinct": "546", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SM07_AEA.bo.", "index": "7", "type": "numeric", "distinct": "568", "missing": "0", "min": "11", "max": "13", "mean": "12", "stdev": "0" }, { "name": "SM04_EA.bo.", "index": "8", "type": "numeric", "distinct": "528", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "X4A", "index": "9", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS7m", "index": "10", "type": "numeric", "distinct": "645", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM05_AEA.bo.", "index": "11", "type": "numeric", "distinct": "499", "missing": "0", "min": "8", "max": "10", "mean": "9", "stdev": "0" }, { "name": "X3A", "index": "12", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig06_EA.bo.", "index": "13", "type": "numeric", "distinct": "460", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ZM2Per", "index": "14", "type": "numeric", "distinct": "968", "missing": "0", "min": "294", "max": "1510", "mean": "665", "stdev": "149" }, { "name": "Eig03_EA.bo.", "index": "15", "type": "numeric", "distinct": "422", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "16", "type": "numeric", "distinct": "422", "missing": "0", "min": "2", "max": "5", "mean": "3", "stdev": "0" }, { "name": "Chi1_EA.ed.", "index": "17", "type": "numeric", "distinct": "646", "missing": "0", "min": "3", "max": "13", "mean": "6", "stdev": "1" }, { "name": "ZM2MulPer", "index": "18", "type": "numeric", "distinct": "970", "missing": "0", "min": "204", "max": "1002", "mean": "458", "stdev": "100" }, { "name": "Chi0_EA.ed.", "index": "19", "type": "numeric", "distinct": "678", "missing": "0", "min": "7", "max": "27", "mean": "12", "stdev": "2" }, { "name": "ZM2V", "index": "20", "type": "numeric", "distinct": "331", "missing": "0", "min": "190", "max": "934", "mean": "429", "stdev": "93" }, { "name": "SpMax1_Bh.e.", "index": "21", "type": "numeric", "distinct": "251", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "IC4", "index": "22", "type": "numeric", "distinct": "484", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eig06_AEA.bo.", "index": "23", "type": "numeric", "distinct": "465", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ZM1Per", "index": "24", "type": "numeric", "distinct": "951", "missing": "0", "min": "317", "max": "1489", "mean": "647", "stdev": "135" }, { "name": "ATS6m", "index": "25", "type": "numeric", "distinct": "648", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "26", "type": "numeric", "distinct": "510", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM02_AEA.bo.", "index": "27", "type": "numeric", "distinct": "310", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM2Kup", "index": "28", "type": "numeric", "distinct": "923", "missing": "0", "min": "197", "max": "1004", "mean": "437", "stdev": "94" }, { "name": "SpAD_EA.bo.", "index": "29", "type": "numeric", "distinct": "804", "missing": "0", "min": "31", "max": "129", "mean": "63", "stdev": "13" }, { "name": "ATS5m", "index": "30", "type": "numeric", "distinct": "649", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM03_EA.ri.", "index": "31", "type": "numeric", "distinct": "382", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "32", "type": "numeric", "distinct": "103", "missing": "0", "min": "94", "max": "589", "mean": "279", "stdev": "79" }, { "name": "Eig04_AEA.ri.", "index": "33", "type": "numeric", "distinct": "435", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "34", "type": "numeric", "distinct": "307", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "35", "type": "numeric", "distinct": "437", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SssCH2", "index": "36", "type": "numeric", "distinct": "923", "missing": "0", "min": "-4", "max": "16", "mean": "4", "stdev": "4" }, { "name": "Eta_F", "index": "37", "type": "numeric", "distinct": "1020", "missing": "0", "min": "5", "max": "79", "mean": "29", "stdev": "9" }, { "name": "Eig01_AEA.ri.", "index": "38", "type": "numeric", "distinct": "335", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax_AEA.ri.", "index": "39", "type": "numeric", "distinct": "335", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nCsp3", "index": "40", "type": "numeric", "distinct": "23", "missing": "0", "min": "1", "max": "23", "mean": "8", "stdev": "4" }, { "name": "ZM1MulPer", "index": "41", "type": "numeric", "distinct": "960", "missing": "0", "min": "248", "max": "1154", "mean": "491", "stdev": "102" }, { "name": "CATS2D_07_NL", "index": "42", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "CATS2D_08_AL", "index": "43", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "3" }, { "name": "ATS8i", "index": "44", "type": "numeric", "distinct": "663", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CATS2D_08_DL", "index": "45", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "SpMax6_Bh.e.", "index": "46", "type": "numeric", "distinct": "467", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MWC03", "index": "47", "type": "numeric", "distinct": "155", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ZM2", "index": "48", "type": "numeric", "distinct": "155", "missing": "0", "min": "90", "max": "373", "mean": "182", "stdev": "37" }, { "name": "GGI4", "index": "49", "type": "numeric", "distinct": "461", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "ZM1Mad", "index": "50", "type": "numeric", "distinct": "828", "missing": "0", "min": "90", "max": "571", "mean": "202", "stdev": "48" }, { "name": "SpMax3_Bh.v.", "index": "51", "type": "numeric", "distinct": "310", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "52", "type": "numeric", "distinct": "725", "missing": "0", "min": "67", "max": "286", "mean": "139", "stdev": "29" }, { "name": "ZM1V", "index": "53", "type": "numeric", "distinct": "205", "missing": "0", "min": "232", "max": "1064", "mean": "454", "stdev": "93" }, { "name": "Eig01_EA.ed.", "index": "54", "type": "numeric", "distinct": "332", "missing": "0", "min": "8", "max": "19", "mean": "12", "stdev": "1" }, { "name": "SM10_AEA.dm.", "index": "55", "type": "numeric", "distinct": "332", "missing": "0", "min": "8", "max": "19", "mean": "12", "stdev": "1" }, { "name": "SpMax_EA.ed.", "index": "56", "type": "numeric", "distinct": "332", "missing": "0", "min": "8", "max": "19", "mean": "12", "stdev": "1" }, { "name": "SRW04", "index": "57", "type": "numeric", "distinct": "108", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "D.Dtr05", "index": "58", "type": "numeric", "distinct": "514", "missing": "0", "min": "0", "max": "694", "mean": "77", "stdev": "68" }, { "name": "CATS2D_07_AL", "index": "59", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "7", "stdev": "4" }, { "name": "NssCH2", "index": "60", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "6", "stdev": "3" }, { "name": "CATS2D_05_LL", "index": "61", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "35", "mean": "11", "stdev": "6" }, { "name": "CATS2D_02_LL", "index": "62", "type": "numeric", "distinct": "37", "missing": "0", "min": "2", "max": "40", "mean": "16", "stdev": "6" }, { "name": "piPC04", "index": "63", "type": "numeric", "distinct": "555", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Eta_beta", "index": "64", "type": "numeric", "distinct": "156", "missing": "0", "min": "14", "max": "82", "mean": "36", "stdev": "9" }, { "name": "BBI", "index": "65", "type": "numeric", "distinct": "53", "missing": "0", "min": "23", "max": "92", "mean": "46", "stdev": "9" }, { "name": "MPC02", "index": "66", "type": "numeric", "distinct": "53", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM02_EA", "index": "67", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "ZM1Kup", "index": "68", "type": "numeric", "distinct": "838", "missing": "0", "min": "246", "max": "1379", "mean": "499", "stdev": "115" } ], "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 }