{ "data_id": "31695", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3835", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3835", "version": 9, "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: CHEMBL3835 (TID: 30017), and it has 1058 rows and 70 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 08:15:54", "update_comment": null, "last_update": "2016-07-15 08:15:54", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3457107\/data_53642.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3835", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3835 (TID: 30017), and it has 1058 rows and 70 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": 1058, "NumberOfFeatures": 72, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 71, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.4156095703949785, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8707895352349273, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 60.35059318571149, "MinMeansOfNumericAtts": 0.19458506616257087, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 5.308218335454306, "MaxMeansOfNumericAtts": 31434.900756143674, "MinMutualInformation": null, "PercentageOfNumericFeatures": 98.61111111111111, "Quartile3MeansOfNumericAtts": 37.16138941398865, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfSymbolicFeatures": 1.3888888888888888, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0736170807037935, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.5469655376820568, "MaxSkewnessOfNumericAtts": 6.112366143288609, "MinStdDevOfNumericAtts": 0.23908236375563632, "Quartile1KurtosisOfNumericAtts": 0.4425700077068986, "Quartile3StdDevOfNumericAtts": 9.636551271165322, "MaxStdDevOfNumericAtts": 22572.338413000354, "MinorityClassPercentage": null, "Quartile1MeansOfNumericAtts": 2.313133270321361, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MutualInformation": null, "MeanKurtosisOfNumericAtts": 4.609690037889081, "NumberOfBinaryFeatures": 0, "Quartile1SkewnessOfNumericAtts": -1.4080213840039153, "MeanMeansOfNumericAtts": 1327.4375828829309, "Quartile1StdDevOfNumericAtts": 0.49046164300002054, "AutoCorrelation": 0.5232563859981084, "MeanMutualInformation": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2KurtosisOfNumericAtts": 2.0856044086008105, "Dimensionality": 0.06805293005671077, "MeanNominalAttDistinctValues": null, "Quartile2MeansOfNumericAtts": 4.936937618147448, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.027778921965248542, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 970.3634729315935, "Quartile2SkewnessOfNumericAtts": 0.0699971732989749, "MajorityClassSize": null, "MinAttributeEntropy": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "71", "type": "numeric", "distinct": "133", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "5", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "1058", "missing": "0", "identifier": "1", "distr": [] }, { "name": "CATS2D_08_DP", "index": "1", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "8", "mean": "0", "stdev": "1" }, { "name": "Eig07_AEA.bo.", "index": "2", "type": "numeric", "distinct": "606", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_EA.ed.", "index": "3", "type": "numeric", "distinct": "755", "missing": "0", "min": "-5", "max": "7", "mean": "3", "stdev": "2" }, { "name": "SM04_AEA.ri.", "index": "4", "type": "numeric", "distinct": "755", "missing": "0", "min": "-5", "max": "7", "mean": "3", "stdev": "2" }, { "name": "Eig08_EA.ri.", "index": "5", "type": "numeric", "distinct": "649", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "6", "type": "numeric", "distinct": "879", "missing": "0", "min": "0", "max": "54", "mean": "18", "stdev": "8" }, { "name": "Eig08_AEA.bo.", "index": "7", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_AEA.bo.", "index": "8", "type": "numeric", "distinct": "629", "missing": "0", "min": "0", "max": "4", "mean": "3", "stdev": "1" }, { "name": "Eig09_EA", "index": "9", "type": "numeric", "distinct": "594", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM03_AEA.dm.", "index": "10", "type": "numeric", "distinct": "594", "missing": "0", "min": "-2", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig08_AEA.ri.", "index": "11", "type": "numeric", "distinct": "663", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS1m", "index": "12", "type": "numeric", "distinct": "600", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA", "index": "13", "type": "numeric", "distinct": "582", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SM02_AEA.dm.", "index": "14", "type": "numeric", "distinct": "582", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "XMOD", "index": "15", "type": "numeric", "distinct": "993", "missing": "0", "min": "37", "max": "168", "mean": "86", "stdev": "20" }, { "name": "Eig07_AEA.ri.", "index": "16", "type": "numeric", "distinct": "674", "missing": "0", "min": "0", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig07_EA.bo.", "index": "17", "type": "numeric", "distinct": "640", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eta_alpha", "index": "18", "type": "numeric", "distinct": "601", "missing": "0", "min": "5", "max": "26", "mean": "13", "stdev": "3" }, { "name": "Eig09_EA.ri.", "index": "19", "type": "numeric", "distinct": "656", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Eig08_EA.ed.", "index": "20", "type": "numeric", "distinct": "759", "missing": "0", "min": "-4", "max": "8", "mean": "4", "stdev": "1" }, { "name": "SM03_AEA.ri.", "index": "21", "type": "numeric", "distinct": "759", "missing": "0", "min": "-4", "max": "8", "mean": "4", "stdev": "1" }, { "name": "ZM2Mad", "index": "22", "type": "numeric", "distinct": "1006", "missing": "0", "min": "80", "max": "380", "mean": "200", "stdev": "50" }, { "name": "Eig09_AEA.ri.", "index": "23", "type": "numeric", "distinct": "678", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig07_EA", "index": "24", "type": "numeric", "distinct": "598", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM15_AEA.bo.", "index": "25", "type": "numeric", "distinct": "598", "missing": "0", "min": "-1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Eta_F", "index": "26", "type": "numeric", "distinct": "1023", "missing": "0", "min": "6", "max": "73", "mean": "28", "stdev": "10" }, { "name": "ATS2m", "index": "27", "type": "numeric", "distinct": "626", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig08_EA.bo.", "index": "28", "type": "numeric", "distinct": "651", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "X0sol", "index": "29", "type": "numeric", "distinct": "576", "missing": "0", "min": "8", "max": "42", "mean": "19", "stdev": "4" }, { "name": "SMTIV", "index": "30", "type": "numeric", "distinct": "1008", "missing": "0", "min": "1203", "max": "130603", "mean": "17604", "stdev": "12481" }, { "name": "ECC", "index": "31", "type": "numeric", "distinct": "444", "missing": "0", "min": "40", "max": "1281", "mean": "313", "stdev": "152" }, { "name": "Eig09_AEA.ed.", "index": "32", "type": "numeric", "distinct": "647", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "CATS2D_08_DD", "index": "33", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Xu", "index": "34", "type": "numeric", "distinct": "913", "missing": "0", "min": "10", "max": "49", "mean": "26", "stdev": "6" }, { "name": "Eta_beta", "index": "35", "type": "numeric", "distinct": "164", "missing": "0", "min": "14", "max": "69", "mean": "37", "stdev": "9" }, { "name": "IDET", "index": "36", "type": "numeric", "distinct": "928", "missing": "0", "min": "93", "max": "7250", "mean": "1402", "stdev": "826" }, { "name": "LPRS", "index": "37", "type": "numeric", "distinct": "932", "missing": "0", "min": "30", "max": "363", "mean": "137", "stdev": "45" }, { "name": "IDMT", "index": "38", "type": "numeric", "distinct": "930", "missing": "0", "min": "566", "max": "190283", "mean": "20183", "stdev": "16819" }, { "name": "ZM1Mad", "index": "39", "type": "numeric", "distinct": "991", "missing": "0", "min": "70", "max": "546", "mean": "177", "stdev": "46" }, { "name": "CSI", "index": "40", "type": "numeric", "distinct": "627", "missing": "0", "min": "84", "max": "2573", "mean": "677", "stdev": "331" }, { "name": "X2sol", "index": "41", "type": "numeric", "distinct": "872", "missing": "0", "min": "5", "max": "24", "mean": "12", "stdev": "3" }, { "name": "SMTI", "index": "42", "type": "numeric", "distinct": "912", "missing": "0", "min": "505", "max": "73813", "mean": "10207", "stdev": "7387" }, { "name": "Eig08_AEA.ed.", "index": "43", "type": "numeric", "distinct": "666", "missing": "0", "min": "2", "max": "6", "mean": "4", "stdev": "1" }, { "name": "MW", "index": "44", "type": "numeric", "distinct": "910", "missing": "0", "min": "163", "max": "776", "mean": "383", "stdev": "89" }, { "name": "Eig08_AEA.dm.", "index": "45", "type": "numeric", "distinct": "664", "missing": "0", "min": "-1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "MSD", "index": "46", "type": "numeric", "distinct": "859", "missing": "0", "min": "3", "max": "14", "mean": "6", "stdev": "2" }, { "name": "GMTI", "index": "47", "type": "numeric", "distinct": "910", "missing": "0", "min": "453", "max": "73005", "mean": "10711", "stdev": "7864" }, { "name": "UNIP", "index": "48", "type": "numeric", "distinct": "210", "missing": "0", "min": "16", "max": "497", "mean": "111", "stdev": "52" }, { "name": "SpMax7_Bh.i.", "index": "49", "type": "numeric", "distinct": "533", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SM03_AEA.bo.", "index": "50", "type": "numeric", "distinct": "547", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "X1sol", "index": "51", "type": "numeric", "distinct": "791", "missing": "0", "min": "5", "max": "26", "mean": "13", "stdev": "3" }, { "name": "AMR", "index": "52", "type": "numeric", "distinct": "998", "missing": "0", "min": "40", "max": "216", "mean": "105", "stdev": "25" }, { "name": "X4sol", "index": "53", "type": "numeric", "distinct": "876", "missing": "0", "min": "3", "max": "19", "mean": "9", "stdev": "2" }, { "name": "X3sol", "index": "54", "type": "numeric", "distinct": "882", "missing": "0", "min": "4", "max": "20", "mean": "10", "stdev": "2" }, { "name": "Eig09_EA.bo.", "index": "55", "type": "numeric", "distinct": "660", "missing": "0", "min": "-2", "max": "3", "mean": "2", "stdev": "1" }, { "name": "ON1", "index": "56", "type": "numeric", "distinct": "266", "missing": "0", "min": "2", "max": "13", "mean": "6", "stdev": "1" }, { "name": "ATS1s", "index": "57", "type": "numeric", "distinct": "614", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "GMTIV", "index": "58", "type": "numeric", "distinct": "1019", "missing": "0", "min": "2266", "max": "227651", "mean": "31435", "stdev": "22572" }, { "name": "X1", "index": "59", "type": "numeric", "distinct": "716", "missing": "0", "min": "5", "max": "26", "mean": "13", "stdev": "3" }, { "name": "Eig13_EA.bo.", "index": "60", "type": "numeric", "distinct": "689", "missing": "0", "min": "-3", "max": "2", "mean": "0", "stdev": "1" }, { "name": "SpMax6_Bh.m.", "index": "61", "type": "numeric", "distinct": "582", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Pol", "index": "62", "type": "numeric", "distinct": "69", "missing": "0", "min": "11", "max": "103", "mean": "43", "stdev": "12" }, { "name": "SM02_AEA.bo.", "index": "63", "type": "numeric", "distinct": "395", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "IDE", "index": "64", "type": "numeric", "distinct": "676", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Chi0_EA.ed.", "index": "65", "type": "numeric", "distinct": "878", "missing": "0", "min": "4", "max": "22", "mean": "11", "stdev": "3" }, { "name": "Chi0_EA.ri.", "index": "66", "type": "numeric", "distinct": "979", "missing": "0", "min": "7", "max": "37", "mean": "19", "stdev": "5" }, { "name": "P_VSA_e_2", "index": "67", "type": "numeric", "distinct": "972", "missing": "0", "min": "25", "max": "242", "mean": "129", "stdev": "37" }, { "name": "IDDM", "index": "68", "type": "numeric", "distinct": "341", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "CID", "index": "69", "type": "numeric", "distinct": "498", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig14_AEA.bo.", "index": "70", "type": "numeric", "distinct": "661", "missing": "0", "min": "-1", "max": "3", "mean": "1", "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 }