{ "data_id": "37775", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2243", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2243", "version": 12, "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: CHEMBL2243 (TID: 11291), and it has 898 rows and 68 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": "2016-07-16 01:49:06", "update_comment": null, "last_update": "2016-07-16 01:49:06", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3621508\/data_53352.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2243", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2243 (TID: 11291), and it has 898 rows and 68 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": 898, "NumberOfFeatures": 70, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 69, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.0779510022271715, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.8743972071432373, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.5855632278736292, "Quartile2MeansOfNumericAtts": 3.9653964365256122, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 260.7143341166049, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.48616153736416173, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.0207004952391243, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.6383764609796613, "MaxKurtosisOfNumericAtts": 15.979588259880948, "MinMeansOfNumericAtts": 0.14579510022271716, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 19467.2011013363, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.181466405819962, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.57142857142858, "Quartile3MeansOfNumericAtts": 28.651092427616927, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.1332817248079996, "PercentageOfSymbolicFeatures": 1.4285714285714286, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.7929815523293433, "MinStdDevOfNumericAtts": 0.049954118284701844, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.2990742702473089, "MaxStdDevOfNumericAtts": 10800.969725420748, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.9787982707510354, "Quartile3StdDevOfNumericAtts": 5.152361624073028, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.7704743875278397, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 3.7020623534261734, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 510.6850054226784, "Quartile1SkewnessOfNumericAtts": -1.7968647959539692, "AutoCorrelation": -0.13804236343366913, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.21850756125692544 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "69", "type": "numeric", "distinct": "478", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "898", "missing": "0", "identifier": "1", "distr": [] }, { "name": "HVcpx", "index": "1", "type": "numeric", "distinct": "432", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "AECC", "index": "2", "type": "numeric", "distinct": "477", "missing": "0", "min": "5", "max": "23", "mean": "13", "stdev": "3" }, { "name": "IDE", "index": "3", "type": "numeric", "distinct": "459", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "RDCHI", "index": "4", "type": "numeric", "distinct": "482", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "UNIP", "index": "5", "type": "numeric", "distinct": "176", "missing": "0", "min": "21", "max": "359", "mean": "124", "stdev": "41" }, { "name": "TIC3", "index": "6", "type": "numeric", "distinct": "644", "missing": "0", "min": "51", "max": "506", "mean": "235", "stdev": "59" }, { "name": "ECC", "index": "7", "type": "numeric", "distinct": "330", "missing": "0", "min": "54", "max": "1037", "mean": "353", "stdev": "121" }, { "name": "TIC4", "index": "8", "type": "numeric", "distinct": "557", "missing": "0", "min": "51", "max": "526", "mean": "247", "stdev": "62" }, { "name": "TIC5", "index": "9", "type": "numeric", "distinct": "523", "missing": "0", "min": "51", "max": "530", "mean": "250", "stdev": "64" }, { "name": "Chi1_EA.ed.", "index": "10", "type": "numeric", "distinct": "529", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SpMin7_Bh.p.", "index": "11", "type": "numeric", "distinct": "380", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "O.060", "index": "12", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Sv", "index": "13", "type": "numeric", "distinct": "611", "missing": "0", "min": "12", "max": "54", "mean": "31", "stdev": "6" }, { "name": "SpMin8_Bh.i.", "index": "14", "type": "numeric", "distinct": "333", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "15", "type": "numeric", "distinct": "388", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax7_Bh.v.", "index": "16", "type": "numeric", "distinct": "390", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "CSI", "index": "17", "type": "numeric", "distinct": "441", "missing": "0", "min": "103", "max": "2259", "mean": "748", "stdev": "264" }, { "name": "MSD", "index": "18", "type": "numeric", "distinct": "546", "missing": "0", "min": "3", "max": "13", "mean": "8", "stdev": "1" }, { "name": "X1Per", "index": "19", "type": "numeric", "distinct": "717", "missing": "0", "min": "2", "max": "13", "mean": "7", "stdev": "1" }, { "name": "SpMin8_Bh.e.", "index": "20", "type": "numeric", "distinct": "353", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax7_Bh.i.", "index": "21", "type": "numeric", "distinct": "381", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Chi0_EA.ed.", "index": "22", "type": "numeric", "distinct": "542", "missing": "0", "min": "4", "max": "19", "mean": "11", "stdev": "2" }, { "name": "X1MulPer", "index": "23", "type": "numeric", "distinct": "709", "missing": "0", "min": "3", "max": "15", "mean": "9", "stdev": "2" }, { "name": "SpMin8_Bh.v.", "index": "24", "type": "numeric", "distinct": "376", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "X1Kup", "index": "25", "type": "numeric", "distinct": "715", "missing": "0", "min": "3", "max": "16", "mean": "9", "stdev": "2" }, { "name": "SpMin3_Bh.v.", "index": "26", "type": "numeric", "distinct": "264", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "MAXDP", "index": "27", "type": "numeric", "distinct": "684", "missing": "0", "min": "1", "max": "7", "mean": "5", "stdev": "1" }, { "name": "P_VSA_LogP_5", "index": "28", "type": "numeric", "distinct": "364", "missing": "0", "min": "0", "max": "99", "mean": "31", "stdev": "19" }, { "name": "SpMin3_Bh.e.", "index": "29", "type": "numeric", "distinct": "312", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax7_Bh.p.", "index": "30", "type": "numeric", "distinct": "396", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "31", "type": "numeric", "distinct": "368", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Yindex", "index": "32", "type": "numeric", "distinct": "343", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS1v", "index": "33", "type": "numeric", "distinct": "450", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin2_Bh.e.", "index": "34", "type": "numeric", "distinct": "220", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin3_Bh.i.", "index": "35", "type": "numeric", "distinct": "330", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax3_Bh.v.", "index": "36", "type": "numeric", "distinct": "340", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "VAR", "index": "37", "type": "numeric", "distinct": "164", "missing": "0", "min": "15", "max": "376", "mean": "121", "stdev": "46" }, { "name": "ATSC8v", "index": "38", "type": "numeric", "distinct": "789", "missing": "0", "min": "0", "max": "29", "mean": "11", "stdev": "4" }, { "name": "IDMT", "index": "39", "type": "numeric", "distinct": "570", "missing": "0", "min": "894", "max": "105334", "mean": "19467", "stdev": "10801" }, { "name": "Xu", "index": "40", "type": "numeric", "distinct": "566", "missing": "0", "min": "11", "max": "42", "mean": "26", "stdev": "4" }, { "name": "TIC2", "index": "41", "type": "numeric", "distinct": "712", "missing": "0", "min": "46", "max": "433", "mean": "204", "stdev": "50" }, { "name": "TIC1", "index": "42", "type": "numeric", "distinct": "680", "missing": "0", "min": "42", "max": "303", "mean": "158", "stdev": "37" }, { "name": "SpMin7_Bh.s.", "index": "43", "type": "numeric", "distinct": "360", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ON1V", "index": "44", "type": "numeric", "distinct": "614", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "IC4", "index": "45", "type": "numeric", "distinct": "454", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "IDET", "index": "46", "type": "numeric", "distinct": "568", "missing": "0", "min": "135", "max": "4631", "mean": "1348", "stdev": "562" }, { "name": "SpMaxA_AEA.dm.", "index": "47", "type": "numeric", "distinct": "171", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CENT", "index": "48", "type": "numeric", "distinct": "496", "missing": "0", "min": "76", "max": "5741", "mean": "1237", "stdev": "630" }, { "name": "Sp", "index": "49", "type": "numeric", "distinct": "588", "missing": "0", "min": "11", "max": "57", "mean": "33", "stdev": "6" }, { "name": "ATS8v", "index": "50", "type": "numeric", "distinct": "581", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "51", "type": "numeric", "distinct": "365", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Vindex", "index": "52", "type": "numeric", "distinct": "219", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "53", "type": "numeric", "distinct": "244", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATS1e", "index": "54", "type": "numeric", "distinct": "425", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ON1", "index": "55", "type": "numeric", "distinct": "179", "missing": "0", "min": "2", "max": "10", "mean": "6", "stdev": "1" }, { "name": "SpMax2_Bh.v.", "index": "56", "type": "numeric", "distinct": "305", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SMTI", "index": "57", "type": "numeric", "distinct": "561", "missing": "0", "min": "649", "max": "47702", "mean": "10050", "stdev": "5072" }, { "name": "SpMaxA_EA.ed.", "index": "58", "type": "numeric", "distinct": "257", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax5_Bh.v.", "index": "59", "type": "numeric", "distinct": "457", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nC", "index": "60", "type": "numeric", "distinct": "28", "missing": "0", "min": "6", "max": "35", "mean": "21", "stdev": "4" }, { "name": "Xindex", "index": "61", "type": "numeric", "distinct": "287", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS1i", "index": "62", "type": "numeric", "distinct": "442", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "IC3", "index": "63", "type": "numeric", "distinct": "512", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM2Kup", "index": "64", "type": "numeric", "distinct": "749", "missing": "0", "min": "94", "max": "686", "mean": "371", "stdev": "108" }, { "name": "SpMax6_Bh.v.", "index": "65", "type": "numeric", "distinct": "409", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig10_EA.ed.", "index": "66", "type": "numeric", "distinct": "391", "missing": "0", "min": "-7", "max": "4", "mean": "2", "stdev": "1" }, { "name": "SM05_AEA.ri.", "index": "67", "type": "numeric", "distinct": "391", "missing": "0", "min": "-7", "max": "4", "mean": "2", "stdev": "1" }, { "name": "Eig10_AEA.ri.", "index": "68", "type": "numeric", "distinct": "438", "missing": "0", "min": "-1", "max": "3", "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 }