{ "data_id": "33103", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1293222", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1293222", "version": 11, "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: CHEMBL1293222 (TID: 103655), and it has 346 rows and 67 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 11:55:19", "update_comment": null, "last_update": "2016-07-15 11:55:19", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3497093\/data_53246.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-CHEMBL1293222", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1293222 (TID: 103655), and it has 346 rows and 67 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": 346, "NumberOfFeatures": 69, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 68, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 3.3885026143227783, "MinStdDevOfNumericAtts": 0.0406795189721022, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.6493541062669266, "MaxStdDevOfNumericAtts": 16.15159497325922, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.7431586254658562, "Quartile3StdDevOfNumericAtts": 3.4775411689742675, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.0480079479768787, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 3.672517747292474, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 6.854029709282557, "Quartile1SkewnessOfNumericAtts": -0.5709520356919644, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.19503202044882734, "AutoCorrelation": 0.36489275362318885, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 1.8242316923536634, "Dimensionality": 0.1994219653179191, "MeanSkewnessOfNumericAtts": 0.5207135665963443, "Quartile2MeansOfNumericAtts": 3.9849002890173413, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 2.0962923471437507, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3736571513264506, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.6004738037271529, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5674123987033249, "MaxKurtosisOfNumericAtts": 20.096123652523595, "MinMeansOfNumericAtts": 0.23088439306358383, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 53.65478612716763, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 6.1003715849782, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.55072463768117, "Quartile3MeansOfNumericAtts": 6.407166184971098, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.4950497904888764, "PercentageOfSymbolicFeatures": 1.4492753623188406, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "68", "type": "numeric", "distinct": "198", "missing": "0", "target": "1", "min": "5", "max": "11", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "346", "missing": "0", "identifier": "1", "distr": [] }, { "name": "SpMin4_Bh.s.", "index": "1", "type": "numeric", "distinct": "234", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1Per", "index": "2", "type": "numeric", "distinct": "312", "missing": "0", "min": "3", "max": "19", "mean": "7", "stdev": "2" }, { "name": "ATSC2p", "index": "3", "type": "numeric", "distinct": "320", "missing": "0", "min": "3", "max": "22", "mean": "7", "stdev": "2" }, { "name": "X1Kup", "index": "4", "type": "numeric", "distinct": "331", "missing": "0", "min": "4", "max": "22", "mean": "9", "stdev": "2" }, { "name": "X1MulPer", "index": "5", "type": "numeric", "distinct": "311", "missing": "0", "min": "4", "max": "22", "mean": "8", "stdev": "2" }, { "name": "ATS4i", "index": "6", "type": "numeric", "distinct": "296", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC1m", "index": "7", "type": "numeric", "distinct": "314", "missing": "0", "min": "0", "max": "35", "mean": "9", "stdev": "5" }, { "name": "SpMin5_Bh.p.", "index": "8", "type": "numeric", "distinct": "241", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.p.", "index": "9", "type": "numeric", "distinct": "230", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "10", "type": "numeric", "distinct": "217", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "11", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SssCH2", "index": "12", "type": "numeric", "distinct": "262", "missing": "0", "min": "0", "max": "37", "mean": "3", "stdev": "4" }, { "name": "ATS2e", "index": "13", "type": "numeric", "distinct": "270", "missing": "0", "min": "4", "max": "6", "mean": "4", "stdev": "0" }, { "name": "Si", "index": "14", "type": "numeric", "distinct": "305", "missing": "0", "min": "25", "max": "159", "mean": "54", "stdev": "16" }, { "name": "ATS1e", "index": "15", "type": "numeric", "distinct": "260", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS1i", "index": "16", "type": "numeric", "distinct": "261", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS3e", "index": "17", "type": "numeric", "distinct": "281", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS3i", "index": "18", "type": "numeric", "distinct": "278", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC3v", "index": "19", "type": "numeric", "distinct": "331", "missing": "0", "min": "2", "max": "42", "mean": "12", "stdev": "5" }, { "name": "nBT", "index": "20", "type": "numeric", "distinct": "62", "missing": "0", "min": "23", "max": "138", "mean": "50", "stdev": "14" }, { "name": "ATSC1p", "index": "21", "type": "numeric", "distinct": "302", "missing": "0", "min": "2", "max": "14", "mean": "4", "stdev": "1" }, { "name": "SpMax6_Bh.v.", "index": "22", "type": "numeric", "distinct": "233", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATS2i", "index": "23", "type": "numeric", "distinct": "275", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "24", "type": "numeric", "distinct": "229", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MSD", "index": "25", "type": "numeric", "distinct": "291", "missing": "0", "min": "4", "max": "14", "mean": "7", "stdev": "2" }, { "name": "ARR", "index": "26", "type": "numeric", "distinct": "100", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC1v", "index": "27", "type": "numeric", "distinct": "303", "missing": "0", "min": "1", "max": "20", "mean": "5", "stdev": "2" }, { "name": "ATSC2v", "index": "28", "type": "numeric", "distinct": "318", "missing": "0", "min": "2", "max": "33", "mean": "9", "stdev": "4" }, { "name": "C.", "index": "29", "type": "numeric", "distinct": "117", "missing": "0", "min": "30", "max": "54", "mean": "42", "stdev": "5" }, { "name": "C.002", "index": "30", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "33", "mean": "2", "stdev": "4" }, { "name": "CIC0", "index": "31", "type": "numeric", "distinct": "274", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "DBI", "index": "32", "type": "numeric", "distinct": "51", "missing": "0", "min": "2", "max": "8", "mean": "4", "stdev": "1" }, { "name": "DLS_07", "index": "33", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eig01_EA.bo.", "index": "34", "type": "numeric", "distinct": "171", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_beta_A", "index": "35", "type": "numeric", "distinct": "204", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "36", "type": "numeric", "distinct": "172", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_C_A", "index": "37", "type": "numeric", "distinct": "262", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eta_FL_A", "index": "38", "type": "numeric", "distinct": "131", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eta_L", "index": "39", "type": "numeric", "distinct": "328", "missing": "0", "min": "3", "max": "22", "mean": "6", "stdev": "2" }, { "name": "Eta_L_A", "index": "40", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1m", "index": "41", "type": "numeric", "distinct": "215", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS1p", "index": "42", "type": "numeric", "distinct": "251", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS1v", "index": "43", "type": "numeric", "distinct": "235", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "GATS2i", "index": "44", "type": "numeric", "distinct": "221", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2p", "index": "45", "type": "numeric", "distinct": "217", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "GATS2v", "index": "46", "type": "numeric", "distinct": "211", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "H.", "index": "47", "type": "numeric", "distinct": "148", "missing": "0", "min": "19", "max": "61", "mean": "42", "stdev": "7" }, { "name": "H.046", "index": "48", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "60", "mean": "4", "stdev": "7" }, { "name": "LOC", "index": "49", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Mp", "index": "50", "type": "numeric", "distinct": "120", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "51", "type": "numeric", "distinct": "136", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NaasC", "index": "52", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "11", "mean": "5", "stdev": "2" }, { "name": "nAB", "index": "53", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "27", "mean": "14", "stdev": "5" }, { "name": "nBM", "index": "54", "type": "numeric", "distinct": "22", "missing": "0", "min": "3", "max": "27", "mean": "16", "stdev": "5" }, { "name": "nCar", "index": "55", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "21", "mean": "12", "stdev": "5" }, { "name": "nCs", "index": "56", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "36", "mean": "3", "stdev": "5" }, { "name": "nCsp3", "index": "57", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "40", "mean": "6", "stdev": "5" }, { "name": "nH", "index": "58", "type": "numeric", "distinct": "37", "missing": "0", "min": "5", "max": "85", "mean": "21", "stdev": "10" }, { "name": "NssCH2", "index": "59", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "35", "mean": "4", "stdev": "5" }, { "name": "ON1V", "index": "60", "type": "numeric", "distinct": "304", "missing": "0", "min": "1", "max": "10", "mean": "3", "stdev": "1" }, { "name": "PCD", "index": "61", "type": "numeric", "distinct": "288", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "PCR", "index": "62", "type": "numeric", "distinct": "196", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "PDI", "index": "63", "type": "numeric", "distinct": "133", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "piPC05", "index": "64", "type": "numeric", "distinct": "263", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC06", "index": "65", "type": "numeric", "distinct": "270", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "piPC07", "index": "66", "type": "numeric", "distinct": "278", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "piPC08", "index": "67", "type": "numeric", "distinct": "294", "missing": "0", "min": "3", "max": "8", "mean": "6", "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 }