{ "data_id": "34981", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5038", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5038", "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: CHEMBL5038 (TID: 20162), and it has 156 rows and 51 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 16:48:37", "update_comment": null, "last_update": "2016-07-15 16:48:37", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3544537\/data_46782.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-CHEMBL5038", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5038 (TID: 20162), and it has 156 rows and 51 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, Das " ], "weight": 5 }, "qualities": { "NumberOfInstances": 156, "NumberOfFeatures": 53, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 52, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 4.439699925314733, "MinStdDevOfNumericAtts": 0.2076892442257913, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 2.736208260924877, "MaxStdDevOfNumericAtts": 1.246767808254841, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.4637412897422741, "Quartile3StdDevOfNumericAtts": 0.47059963860070847, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.09775641025641021, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.7139017780458325, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 0.4149956854043393, "Quartile1SkewnessOfNumericAtts": 0.10369901432198242, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.28673456021756305, "AutoCorrelation": 0.38627096774193537, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.5351589258291314, "Dimensionality": 0.33974358974358976, "MeanSkewnessOfNumericAtts": 1.299919432937096, "Quartile2MeansOfNumericAtts": 0.22756410256410264, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.39595591193258123, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.3124198930068678, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.0234258775280463, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.4002392638617386, "MaxKurtosisOfNumericAtts": 17.94079926052182, "MinMeansOfNumericAtts": 0.0448717948717949, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 6.028493589743589, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 6.485682621319949, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.11320754716981, "Quartile3MeansOfNumericAtts": 0.4839743589743589, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.0444656953735216, "PercentageOfSymbolicFeatures": 1.8867924528301887, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "52", "type": "numeric", "distinct": "37", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "156", "missing": "0", "identifier": "1", "distr": [] }, { "name": "FCFP4_1024b983", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b553", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b787", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b692", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b300", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b351", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b84", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b899", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b385", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b38", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b817", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1002", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b153", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b318", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b723", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b319", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b57", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b472", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b206", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b804", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b985", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b247", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b137", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b937", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b904", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b256", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b376", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b632", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b482", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b65", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b521", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b281", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b942", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b412", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b600", "index": "35", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b769", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b643", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b152", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b133", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b437", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b187", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b614", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b680", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b327", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b273", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b33", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b10", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b574", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b253", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b370", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b352", "index": "51", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "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 }