{ "data_id": "38962", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4027", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4027", "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: CHEMBL4027 (TID: 10685), and it has 220 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": "2016-07-16 06:09:39", "update_comment": null, "last_update": "2016-07-16 06:09:39", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3658563\/data_53122.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL4027", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL4027 (TID: 10685), and it has 220 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": 220, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.3090909090909091, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.3848908579848085, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.41989006686400643, "Quartile2MeansOfNumericAtts": 3.1859863636363634, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 6.338441900739939, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.3653742151057168, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8443504485102062, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 1.0436883594622703, "MaxKurtosisOfNumericAtts": 20.96852976431761, "MinMeansOfNumericAtts": -2.7824090909090904, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 208.56302727272728, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 1.088612335902567, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 10.758840909090909, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.6492743979705473, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 2.389957294538351, "MinStdDevOfNumericAtts": 0.024181522609204354, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.9976349960357831, "MaxStdDevOfNumericAtts": 106.9212412373514, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9360898063088237, "Quartile3StdDevOfNumericAtts": 2.0935425285198943, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.7363636363636366, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.5187772817156793, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 16.050968113975575, "Quartile1SkewnessOfNumericAtts": -0.23331000938134874, "AutoCorrelation": -0.6936575342465754, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3259504469656814 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "145", "missing": "0", "target": "1", "min": "-8", "max": "10", "mean": "6", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "220", "missing": "0", "identifier": "1", "distr": [] }, { "name": "C.043", "index": "1", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "piPC06", "index": "2", "type": "numeric", "distinct": "163", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "1" }, { "name": "SM09_EA.bo.", "index": "3", "type": "numeric", "distinct": "161", "missing": "0", "min": "11", "max": "15", "mean": "13", "stdev": "1" }, { "name": "SM10_EA.bo.", "index": "4", "type": "numeric", "distinct": "159", "missing": "0", "min": "13", "max": "16", "mean": "15", "stdev": "1" }, { "name": "piPC07", "index": "5", "type": "numeric", "distinct": "164", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "piPC08", "index": "6", "type": "numeric", "distinct": "169", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "piPC10", "index": "7", "type": "numeric", "distinct": "168", "missing": "0", "min": "0", "max": "9", "mean": "7", "stdev": "1" }, { "name": "SM08_EA.bo.", "index": "8", "type": "numeric", "distinct": "160", "missing": "0", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "CATS2D_04_PL", "index": "9", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "piPC05", "index": "10", "type": "numeric", "distinct": "155", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "Eig02_EA.bo.", "index": "11", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SM12_AEA.ri.", "index": "12", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "piPC09", "index": "13", "type": "numeric", "distinct": "169", "missing": "0", "min": "4", "max": "9", "mean": "7", "stdev": "1" }, { "name": "PCR", "index": "14", "type": "numeric", "distinct": "121", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "piID", "index": "15", "type": "numeric", "distinct": "160", "missing": "0", "min": "6", "max": "17", "mean": "11", "stdev": "2" }, { "name": "PCD", "index": "16", "type": "numeric", "distinct": "159", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "SM12_EA.bo.", "index": "17", "type": "numeric", "distinct": "153", "missing": "0", "min": "15", "max": "20", "mean": "18", "stdev": "1" }, { "name": "SM13_EA.bo.", "index": "18", "type": "numeric", "distinct": "156", "missing": "0", "min": "16", "max": "21", "mean": "19", "stdev": "1" }, { "name": "nCbH", "index": "19", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "24", "mean": "10", "stdev": "4" }, { "name": "Eig03_EA.bo.", "index": "20", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SM13_AEA.ri.", "index": "21", "type": "numeric", "distinct": "91", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "NaaaC", "index": "22", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "6", "mean": "1", "stdev": "2" }, { "name": "N.071", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nArNR2", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SM07_EA.bo.", "index": "25", "type": "numeric", "distinct": "155", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "nR.Cs", "index": "26", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "6", "mean": "0", "stdev": "1" }, { "name": "SM11_EA.bo.", "index": "27", "type": "numeric", "distinct": "156", "missing": "0", "min": "14", "max": "18", "mean": "16", "stdev": "1" }, { "name": "SdsCH", "index": "28", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "NaasN", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "1" }, { "name": "nN.", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SaasN", "index": "31", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "2" }, { "name": "GATS2v", "index": "32", "type": "numeric", "distinct": "151", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin1_Bh.p.", "index": "33", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "34", "type": "numeric", "distinct": "79", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "nCconj", "index": "35", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "Psi_e_A", "index": "36", "type": "numeric", "distinct": "172", "missing": "0", "min": "7", "max": "9", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "37", "type": "numeric", "distinct": "172", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "RFD", "index": "38", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SM14_EA.bo.", "index": "39", "type": "numeric", "distinct": "156", "missing": "0", "min": "18", "max": "23", "mean": "20", "stdev": "1" }, { "name": "SM15_EA.bo.", "index": "40", "type": "numeric", "distinct": "148", "missing": "0", "min": "19", "max": "24", "mean": "22", "stdev": "2" }, { "name": "Eig02_AEA.bo.", "index": "41", "type": "numeric", "distinct": "98", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "RCI", "index": "42", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "43", "type": "numeric", "distinct": "188", "missing": "0", "min": "58", "max": "502", "mean": "209", "stdev": "83" }, { "name": "P_VSA_v_3", "index": "44", "type": "numeric", "distinct": "188", "missing": "0", "min": "58", "max": "502", "mean": "209", "stdev": "83" }, { "name": "SRW07", "index": "45", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "6", "mean": "4", "stdev": "2" }, { "name": "SaasC", "index": "46", "type": "numeric", "distinct": "194", "missing": "0", "min": "-3", "max": "6", "mean": "2", "stdev": "2" }, { "name": "Rbrid", "index": "47", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "ARR", "index": "48", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "CATS2D_03_DD", "index": "49", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "3" }, { "name": "CATS2D_03_LL", "index": "50", "type": "numeric", "distinct": "41", "missing": "0", "min": "1", "max": "51", "mean": "16", "stdev": "10" }, { "name": "MLOGP", "index": "51", "type": "numeric", "distinct": "164", "missing": "0", "min": "-7", "max": "7", "mean": "2", "stdev": "3" }, { "name": "BLTA96", "index": "52", "type": "numeric", "distinct": "152", "missing": "0", "min": "-8", "max": "4", "mean": "-3", "stdev": "3" }, { "name": "BLTD48", "index": "53", "type": "numeric", "distinct": "153", "missing": "0", "min": "-8", "max": "3", "mean": "-3", "stdev": "3" }, { "name": "BLTF96", "index": "54", "type": "numeric", "distinct": "153", "missing": "0", "min": "-7", "max": "3", "mean": "-3", "stdev": "3" }, { "name": "Mp", "index": "55", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMAD_EA.bo.", "index": "56", "type": "numeric", "distinct": "133", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ALOGP", "index": "57", "type": "numeric", "distinct": "188", "missing": "0", "min": "-4", "max": "10", "mean": "3", "stdev": "3" }, { "name": "MATS4m", "index": "58", "type": "numeric", "distinct": "133", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_3", "index": "59", "type": "numeric", "distinct": "56", "missing": "0", "min": "38", "max": "332", "mean": "120", "stdev": "49" }, { "name": "SIC0", "index": "60", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_07_AA", "index": "61", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "SpMin1_Bh.v.", "index": "62", "type": "numeric", "distinct": "75", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AAC", "index": "63", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "AECC", "index": "64", "type": "numeric", "distinct": "160", "missing": "0", "min": "6", "max": "32", "mean": "18", "stdev": "8" }, { "name": "ALOGP2", "index": "65", "type": "numeric", "distinct": "189", "missing": "0", "min": "0", "max": "95", "mean": "20", "stdev": "18" }, { "name": "AMR", "index": "66", "type": "numeric", "distinct": "190", "missing": "0", "min": "47", "max": "473", "mean": "205", "stdev": "107" } ], "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 }