{ "data_id": "33541", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5498", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5498", "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: CHEMBL5498 (TID: 100872), and it has 533 rows and 102 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent FCFP 1024-bit Molecular Fingerprints which were generated from SMILES strings. Feature selection was applied to this dataset. The fingerprints were obtained using the Pipeline Pilot program, Dassault Syst\u00e8mes BIOVIA. Generating Fingerprints do not usually require missing value imputation as all bits are generated.", "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 13:02:41", "update_comment": null, "last_update": "2016-07-15 13:02:41", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3507679\/data_47271.arff", "kaggle_url": null, "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 1, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5498", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5498 (TID: 100872), and it has 533 rows and 102 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent FCFP 1024-bit Molecular Fingerprints which were generated from SMILES strings. Feature selection was applied to this dataset. The fingerprints were obtained using the Pipeline Pilot program, D " ], "weight": 5 }, "qualities": { "NumberOfInstances": 533, "NumberOfFeatures": 104, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 103, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 23.08679276123034, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 8.00001492965142, "MaxStdDevOfNumericAtts": 1.3125848940569218, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.0844071558907826, "Quartile3StdDevOfNumericAtts": 0.34412872485716756, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.003752345215759823, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 73.69814960992817, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 0.19322011329896718, "Quartile1SkewnessOfNumericAtts": 1.6048157756971213, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.061198790308952124, "AutoCorrelation": -0.12832142857142803, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 9.580879292179045, "Dimensionality": 0.1951219512195122, "MeanSkewnessOfNumericAtts": 5.866332032797199, "Quartile2MeansOfNumericAtts": 0.030018761726078785, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.20865319980269756, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 3.2349654470320743, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.9938420430581074, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.1600767565468856, "MaxKurtosisOfNumericAtts": 532.9999999999983, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 6.580846153846154, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 62.23374892513198, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 99.03846153846155, "Quartile3MeansOfNumericAtts": 0.1594746716697938, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.397784922371, "PercentageOfSymbolicFeatures": 0.9615384615384616, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "103", "type": "numeric", "distinct": "398", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "533", "missing": "0", "identifier": "1", "distr": [] }, { "name": "FCFP4_1024b79", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b363", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b264", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b925", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b103", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b804", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b17", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b492", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b122", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b301", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b603", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b234", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b399", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b859", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b614", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b785", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b25", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b697", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b128", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b461", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b152", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b144", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b837", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b954", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b136", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b674", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b944", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b930", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b971", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b793", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b170", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b444", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b981", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b942", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b562", "index": "35", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b255", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b524", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b504", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b986", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b171", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b48", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b408", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b780", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b431", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b303", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b762", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b585", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b821", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1", "index": "49", "type": "numeric", "distinct": "1", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b10", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b100", "index": "51", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1000", "index": "52", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1001", "index": "53", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1002", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1003", "index": "55", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1004", "index": "56", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1005", "index": "57", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1006", "index": "58", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1007", "index": "59", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1008", "index": "60", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1009", "index": "61", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b101", "index": "62", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1010", "index": "63", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1011", "index": "64", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1012", "index": "65", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1013", "index": "66", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1014", "index": "67", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1015", "index": "68", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1016", "index": "69", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1017", "index": "70", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1018", "index": "71", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1019", "index": "72", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b102", "index": "73", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1020", "index": "74", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1021", "index": "75", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1022", "index": "76", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1023", "index": "77", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1024", "index": "78", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b104", "index": "79", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b105", "index": "80", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b106", "index": "81", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b107", "index": "82", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b108", "index": "83", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b109", "index": "84", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b11", "index": "85", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b110", "index": "86", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b111", "index": "87", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b112", "index": "88", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b113", "index": "89", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b114", "index": "90", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b115", "index": "91", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b116", "index": "92", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b117", "index": "93", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b118", "index": "94", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b119", "index": "95", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b12", "index": "96", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b120", "index": "97", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b121", "index": "98", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b123", "index": "99", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b124", "index": "100", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b125", "index": "101", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b126", "index": "102", "type": "numeric", "distinct": "1", "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 }