{ "data_id": "33926", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3594", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3594", "version": 9, "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: CHEMBL3594 (TID: 12952), and it has 1492 rows and 71 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": "2016-07-15 14:02:31", "update_comment": null, "last_update": "2016-07-15 14:02:31", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3517142\/data_53752.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-CHEMBL3594", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3594 (TID: 12952), and it has 1492 rows and 71 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": 1492, "NumberOfFeatures": 73, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 72, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 3.1845842405807767, "MinStdDevOfNumericAtts": 0.039765238918346525, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.45725072889412877, "MaxStdDevOfNumericAtts": 109.13357355072043, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.4438211766232019, "Quartile3StdDevOfNumericAtts": 1.4714114747718952, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.491119302949063, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 14.086898517405682, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.235168910113195, "Quartile1SkewnessOfNumericAtts": -3.3939663087905325, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4554223037761408, "AutoCorrelation": 0.16063179074446707, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 7.276332580439866, "Dimensionality": 0.048927613941018765, "MeanSkewnessOfNumericAtts": -1.3051253207917348, "Quartile2MeansOfNumericAtts": 4.486594839142091, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4.714060258073603, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -1.0035833480456167, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5680899191912636, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.7986801230318401, "MaxKurtosisOfNumericAtts": 52.5672246732905, "MinMeansOfNumericAtts": 0.13926675603217165, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 212.271754691689, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 25.888787019471543, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.63013698630137, "Quartile3MeansOfNumericAtts": 12.442408679624664, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -6.29744587278996, "PercentageOfSymbolicFeatures": 1.36986301369863, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "72", "type": "numeric", "distinct": "719", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1492", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_02_AP", "index": "1", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "N.069", "index": "2", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DD", "index": "3", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_DP", "index": "4", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_00_PP", "index": "5", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "NsNH2", "index": "6", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "7", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "2" }, { "name": "SM08_EA.bo.", "index": "8", "type": "numeric", "distinct": "842", "missing": "0", "min": "0", "max": "14", "mean": "12", "stdev": "1" }, { "name": "ATSC2s", "index": "9", "type": "numeric", "distinct": "1386", "missing": "0", "min": "1", "max": "319", "mean": "91", "stdev": "53" }, { "name": "SM06_EA.bo.", "index": "10", "type": "numeric", "distinct": "865", "missing": "0", "min": "0", "max": "11", "mean": "10", "stdev": "1" }, { "name": "SM08_AEA.bo.", "index": "11", "type": "numeric", "distinct": "842", "missing": "0", "min": "8", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM07_AEA.bo.", "index": "12", "type": "numeric", "distinct": "868", "missing": "0", "min": "7", "max": "13", "mean": "12", "stdev": "1" }, { "name": "SpMax3_Bh.e.", "index": "13", "type": "numeric", "distinct": "644", "missing": "0", "min": "0", "max": "4", "mean": "4", "stdev": "0" }, { "name": "ATS1m", "index": "14", "type": "numeric", "distinct": "813", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax3_Bh.p.", "index": "15", "type": "numeric", "distinct": "669", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM06_AEA.bo.", "index": "16", "type": "numeric", "distinct": "839", "missing": "0", "min": "6", "max": "12", "mean": "10", "stdev": "1" }, { "name": "SM07_EA", "index": "17", "type": "numeric", "distinct": "663", "missing": "0", "min": "0", "max": "12", "mean": "9", "stdev": "1" }, { "name": "SM08_EA", "index": "18", "type": "numeric", "distinct": "858", "missing": "0", "min": "0", "max": "13", "mean": "10", "stdev": "1" }, { "name": "SsNH2", "index": "19", "type": "numeric", "distinct": "640", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "ZM2Mad", "index": "20", "type": "numeric", "distinct": "1316", "missing": "0", "min": "0", "max": "922", "mean": "212", "stdev": "109" }, { "name": "MATS2s", "index": "21", "type": "numeric", "distinct": "534", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "BLI", "index": "22", "type": "numeric", "distinct": "529", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X1Av", "index": "23", "type": "numeric", "distinct": "247", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM05_EA", "index": "24", "type": "numeric", "distinct": "175", "missing": "0", "min": "0", "max": "9", "mean": "6", "stdev": "1" }, { "name": "SpMax3_Bh.v.", "index": "25", "type": "numeric", "distinct": "661", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax3_Bh.i.", "index": "26", "type": "numeric", "distinct": "628", "missing": "0", "min": "0", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM09_EA", "index": "27", "type": "numeric", "distinct": "846", "missing": "0", "min": "0", "max": "15", "mean": "11", "stdev": "1" }, { "name": "SM10_EA", "index": "28", "type": "numeric", "distinct": "867", "missing": "0", "min": "0", "max": "17", "mean": "12", "stdev": "1" }, { "name": "SpMax5_Bh.s.", "index": "29", "type": "numeric", "distinct": "598", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "1" }, { "name": "SM12_EA", "index": "30", "type": "numeric", "distinct": "916", "missing": "0", "min": "0", "max": "20", "mean": "15", "stdev": "1" }, { "name": "S.110", "index": "31", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "P_VSA_s_1", "index": "32", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "29", "mean": "6", "stdev": "4" }, { "name": "NddssS", "index": "33", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin3_Bh.v.", "index": "34", "type": "numeric", "distinct": "574", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eig03_EA.bo.", "index": "35", "type": "numeric", "distinct": "707", "missing": "0", "min": "-2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "SM13_AEA.ri.", "index": "36", "type": "numeric", "distinct": "707", "missing": "0", "min": "-2", "max": "5", "mean": "3", "stdev": "1" }, { "name": "MATS1m", "index": "37", "type": "numeric", "distinct": "402", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig03_AEA.bo.", "index": "38", "type": "numeric", "distinct": "693", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "P_VSA_MR_6", "index": "39", "type": "numeric", "distinct": "789", "missing": "0", "min": "0", "max": "256", "mean": "97", "stdev": "46" }, { "name": "GGI1", "index": "40", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "20", "mean": "7", "stdev": "3" }, { "name": "SpMin3_Bh.i.", "index": "41", "type": "numeric", "distinct": "613", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM03_EA", "index": "42", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax1_Bh.p.", "index": "43", "type": "numeric", "distinct": "365", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "0" }, { "name": "SpMax1_Bh.s.", "index": "44", "type": "numeric", "distinct": "128", "missing": "0", "min": "4", "max": "9", "mean": "8", "stdev": "1" }, { "name": "CATS2D_03_PL", "index": "45", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "piPC02", "index": "46", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "SM02_EA.bo.", "index": "47", "type": "numeric", "distinct": "336", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "X2Av", "index": "48", "type": "numeric", "distinct": "196", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nS", "index": "49", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "50", "type": "numeric", "distinct": "815", "missing": "0", "min": "0", "max": "22", "mean": "20", "stdev": "2" }, { "name": "SM14_EA.bo.", "index": "51", "type": "numeric", "distinct": "813", "missing": "0", "min": "0", "max": "24", "mean": "21", "stdev": "2" }, { "name": "SM15_EA.bo.", "index": "52", "type": "numeric", "distinct": "786", "missing": "0", "min": "0", "max": "26", "mean": "23", "stdev": "2" }, { "name": "GGI10", "index": "53", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM12_EA.bo.", "index": "54", "type": "numeric", "distinct": "831", "missing": "0", "min": "0", "max": "21", "mean": "18", "stdev": "2" }, { "name": "SM11_EA.bo.", "index": "55", "type": "numeric", "distinct": "813", "missing": "0", "min": "0", "max": "19", "mean": "17", "stdev": "2" }, { "name": "ATSC2e", "index": "56", "type": "numeric", "distinct": "736", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "0" }, { "name": "piPC01", "index": "57", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SCBO", "index": "58", "type": "numeric", "distinct": "135", "missing": "0", "min": "0", "max": "83", "mean": "34", "stdev": "14" }, { "name": "SM09_EA.bo.", "index": "59", "type": "numeric", "distinct": "822", "missing": "0", "min": "0", "max": "16", "mean": "14", "stdev": "2" }, { "name": "SpMax6_Bh.s.", "index": "60", "type": "numeric", "distinct": "682", "missing": "0", "min": "0", "max": "8", "mean": "5", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "61", "type": "numeric", "distinct": "857", "missing": "0", "min": "0", "max": "17", "mean": "15", "stdev": "1" }, { "name": "SM06_AEA.ed.", "index": "62", "type": "numeric", "distinct": "865", "missing": "0", "min": "0", "max": "15", "mean": "12", "stdev": "1" }, { "name": "SM07_AEA.ed.", "index": "63", "type": "numeric", "distinct": "866", "missing": "0", "min": "0", "max": "17", "mean": "14", "stdev": "1" }, { "name": "SM04_EA.ed.", "index": "64", "type": "numeric", "distinct": "908", "missing": "0", "min": "0", "max": "14", "mean": "11", "stdev": "1" }, { "name": "SpAD_EA.bo.", "index": "65", "type": "numeric", "distinct": "1210", "missing": "0", "min": "0", "max": "125", "mean": "50", "stdev": "21" }, { "name": "ATSC1s", "index": "66", "type": "numeric", "distinct": "1308", "missing": "0", "min": "1", "max": "132", "mean": "35", "stdev": "23" }, { "name": "SpMax7_Bh.s.", "index": "67", "type": "numeric", "distinct": "805", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "1" }, { "name": "AAC", "index": "68", "type": "numeric", "distinct": "593", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "IC0", "index": "69", "type": "numeric", "distinct": "593", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Eta_beta", "index": "70", "type": "numeric", "distinct": "230", "missing": "0", "min": "3", "max": "74", "mean": "31", "stdev": "13" }, { "name": "GGI9", "index": "71", "type": "numeric", "distinct": "381", "missing": "0", "min": "0", "max": "2", "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 }