{ "data_id": "32785", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2095152", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2095152", "version": 4, "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: CHEMBL2095152 (TID: 104737), and it has 271 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 11:06:20", "update_comment": null, "last_update": "2016-07-15 11:06:20", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3489545\/data_46998.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-CHEMBL2095152", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2095152 (TID: 104737), and it has 271 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, " ], "weight": 5 }, "qualities": { "NumberOfInstances": 271, "NumberOfFeatures": 53, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 52, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 16.46207763315425, "MinStdDevOfNumericAtts": 0, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 3.762548154644139, "MaxStdDevOfNumericAtts": 0.8782171911452283, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.949578086161929, "Quartile3StdDevOfNumericAtts": 0.49566840012402846, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.005535055350553509, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 30.822598045088665, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 0.3345156826568266, "Quartile1SkewnessOfNumericAtts": 0.22402699981541785, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.06074567392307881, "AutoCorrelation": 0.20507777777777772, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -1.042363459446618, "Dimensionality": 0.19557195571955718, "MeanSkewnessOfNumericAtts": 3.0784006703005486, "Quartile2MeansOfNumericAtts": 0.16420664206642072, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 0.30466379671113786, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6828404502669891, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -2.0144259568052525, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.3569522665918437, "MaxKurtosisOfNumericAtts": 270.9999999999995, "MinMeansOfNumericAtts": 0, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 5.664188191881919, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 12.247100926593806, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.11320754716981, "Quartile3MeansOfNumericAtts": 0.44095940959409596, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -0.38536755094623903, "PercentageOfSymbolicFeatures": 1.8867924528301887, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "52", "type": "numeric", "distinct": "177", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "271", "missing": "0", "identifier": "1", "distr": [] }, { "name": "FCFP4_1024b470", "index": "1", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b14", "index": "2", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b159", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b697", "index": "4", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b453", "index": "5", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b283", "index": "6", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b152", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b847", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b492", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b508", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b54", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b891", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b4", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b815", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b107", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "1" }, { "name": "FCFP4_1024b327", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b574", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b669", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b540", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b879", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b740", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b360", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b354", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b139", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "FCFP4_1024b600", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b651", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b300", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b143", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b201", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b410", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b466", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b586", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b983", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b923", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1", "index": "35", "type": "numeric", "distinct": "1", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "FCFP4_1024b10", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b100", "index": "37", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1000", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1001", "index": "39", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1002", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1003", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1004", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1005", "index": "43", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1006", "index": "44", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1007", "index": "45", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1008", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1009", "index": "47", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b101", "index": "48", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1010", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1011", "index": "50", "type": "numeric", "distinct": "1", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "FCFP4_1024b1012", "index": "51", "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 }