{ "data_id": "33499", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3521", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3521", "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: CHEMBL3521 (TID: 12114), and it has 131 rows and 66 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 12:56:13", "update_comment": null, "last_update": "2016-07-15 12:56:13", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3506699\/data_53077.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-CHEMBL3521", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3521 (TID: 12114), and it has 131 rows and 66 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": 131, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "MeanKurtosisOfNumericAtts": 8.751216701830938, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 13.723949641107438, "Quartile1SkewnessOfNumericAtts": -1.4353825343445294, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.4132809566730137, "AutoCorrelation": 0.5876615384615386, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.490049660393722, "Dimensionality": 0.5190839694656488, "MeanSkewnessOfNumericAtts": 0.3676877246874281, "Quartile2MeansOfNumericAtts": 4.1988778625954195, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 9.703837669797139, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.8708158177924737, "MajorityClassSize": null, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.9878765145130957, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6847180617415913, "MaxKurtosisOfNumericAtts": 41.164581056154525, "MinMeansOfNumericAtts": -0.022946564885496186, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 104.5873893129771, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 13.88413212683862, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 12.679389312977102, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -4.851711075292405, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 4.427956469921797, "MinStdDevOfNumericAtts": 0.027745102671549875, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.5781261941914697, "MaxStdDevOfNumericAtts": 84.69560793065182, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.4015335592724445, "Quartile3StdDevOfNumericAtts": 9.485427832346529, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.9066870229007633, "StdvNominalAttDistinctValues": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "75", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "131", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATSC6e", "index": "1", "type": "numeric", "distinct": "116", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATSC5e", "index": "2", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "ATSC6s", "index": "3", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "591", "mean": "100", "stdev": "85" }, { "name": "CATS2D_08_DL", "index": "4", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "2", "stdev": "3" }, { "name": "GGI7", "index": "5", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC3s", "index": "6", "type": "numeric", "distinct": "117", "missing": "0", "min": "22", "max": "422", "mean": "78", "stdev": "52" }, { "name": "ATSC5s", "index": "7", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "423", "mean": "105", "stdev": "71" }, { "name": "ATSC1s", "index": "8", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "186", "mean": "22", "stdev": "22" }, { "name": "ATSC1e", "index": "9", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_C_A", "index": "10", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC8s", "index": "11", "type": "numeric", "distinct": "125", "missing": "0", "min": "0", "max": "353", "mean": "91", "stdev": "67" }, { "name": "Eig03_EA.ri.", "index": "12", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Mp", "index": "13", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS8s", "index": "14", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATSC1v", "index": "15", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "19", "mean": "7", "stdev": "4" }, { "name": "GATS1v", "index": "16", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCp", "index": "17", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "P_VSA_MR_5", "index": "18", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "124", "mean": "42", "stdev": "32" }, { "name": "H.047", "index": "19", "type": "numeric", "distinct": "29", "missing": "0", "min": "0", "max": "42", "mean": "13", "stdev": "9" }, { "name": "ATSC2v", "index": "20", "type": "numeric", "distinct": "113", "missing": "0", "min": "2", "max": "36", "mean": "13", "stdev": "7" }, { "name": "ATSC3v", "index": "21", "type": "numeric", "distinct": "114", "missing": "0", "min": "3", "max": "54", "mean": "19", "stdev": "12" }, { "name": "ATSC4m", "index": "22", "type": "numeric", "distinct": "117", "missing": "0", "min": "4", "max": "279", "mean": "48", "stdev": "34" }, { "name": "ATSC4v", "index": "23", "type": "numeric", "distinct": "117", "missing": "0", "min": "4", "max": "71", "mean": "22", "stdev": "17" }, { "name": "ATSC5m", "index": "24", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "233", "mean": "48", "stdev": "34" }, { "name": "ATSC5v", "index": "25", "type": "numeric", "distinct": "125", "missing": "0", "min": "3", "max": "77", "mean": "22", "stdev": "18" }, { "name": "ATSC6m", "index": "26", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "202", "mean": "44", "stdev": "32" }, { "name": "Eig03_AEA.ri.", "index": "27", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "GGI3", "index": "28", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "2" }, { "name": "H.046", "index": "29", "type": "numeric", "distinct": "15", "missing": "0", "min": "0", "max": "48", "mean": "9", "stdev": "16" }, { "name": "Mv", "index": "30", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nCsp3", "index": "31", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "34", "mean": "10", "stdev": "9" }, { "name": "SpMin3_Bh.s.", "index": "32", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1m", "index": "33", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GGI10", "index": "34", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "O.", "index": "35", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "50", "mean": "9", "stdev": "6" }, { "name": "SsCH3", "index": "36", "type": "numeric", "distinct": "71", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "6" }, { "name": "Eig02_AEA.bo.", "index": "37", "type": "numeric", "distinct": "89", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin1_Bh.e.", "index": "38", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC2s", "index": "39", "type": "numeric", "distinct": "117", "missing": "0", "min": "7", "max": "416", "mean": "65", "stdev": "51" }, { "name": "MPC07", "index": "40", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "C.001", "index": "41", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "NsCH3", "index": "42", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "3" }, { "name": "P_VSA_LogP_1", "index": "43", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "79", "mean": "16", "stdev": "22" }, { "name": "BIC0", "index": "44", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nH", "index": "45", "type": "numeric", "distinct": "43", "missing": "0", "min": "3", "max": "71", "mean": "28", "stdev": "15" }, { "name": "Eig04_AEA.ri.", "index": "46", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig04_EA", "index": "47", "type": "numeric", "distinct": "96", "missing": "0", "min": "-1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "48", "type": "numeric", "distinct": "104", "missing": "0", "min": "-1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "49", "type": "numeric", "distinct": "96", "missing": "0", "min": "-1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "MATS5p", "index": "50", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GGI8", "index": "51", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "52", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "PW3", "index": "53", "type": "numeric", "distinct": "64", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC7e", "index": "54", "type": "numeric", "distinct": "120", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "JGI2", "index": "55", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1p", "index": "56", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "AMW", "index": "57", "type": "numeric", "distinct": "106", "missing": "0", "min": "6", "max": "24", "mean": "8", "stdev": "2" }, { "name": "ATS3p", "index": "58", "type": "numeric", "distinct": "110", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS3v", "index": "59", "type": "numeric", "distinct": "112", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS4p", "index": "60", "type": "numeric", "distinct": "115", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS4v", "index": "61", "type": "numeric", "distinct": "115", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS5p", "index": "62", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS5v", "index": "63", "type": "numeric", "distinct": "120", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS6e", "index": "64", "type": "numeric", "distinct": "118", "missing": "0", "min": "0", "max": "6", "mean": "5", "stdev": "1" }, { "name": "ATS6i", "index": "65", "type": "numeric", "distinct": "122", "missing": "0", "min": "0", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ATSC3i", "index": "66", "type": "numeric", "distinct": "111", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" } ], "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 }