{ "data_id": "35630", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5398", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5398", "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: CHEMBL5398 (TID: 101173), and it has 108 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 18:34:10", "update_comment": null, "last_update": "2016-07-15 18:34:10", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3563887\/data_53145.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL5398", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL5398 (TID: 101173), and it has 108 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": 108, "NumberOfFeatures": 68, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 67, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.6296296296296297, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.9031061746535198, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.008163772505210921, "Quartile2MeansOfNumericAtts": 3.1915, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 13.546091449809106, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.06109343467246777, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2209252768124932, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.33009844485958917, "MaxKurtosisOfNumericAtts": 28.03732199452194, "MinMeansOfNumericAtts": -0.09552777777777778, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 258.40580555555556, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.6735457052690523, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.52941176470588, "Quartile3MeansOfNumericAtts": 14.165462962962962, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.668173527568722, "PercentageOfSymbolicFeatures": 1.4705882352941175, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.2849682952311734, "MinStdDevOfNumericAtts": 0.01179774679134607, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.6722965156584095, "MaxStdDevOfNumericAtts": 97.2986156189956, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.44839273802724566, "Quartile3StdDevOfNumericAtts": 6.518661248616356, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.1079166666666667, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 2.2907602500681765, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 37.61142647871752, "Quartile1SkewnessOfNumericAtts": -0.9774862633314828, "AutoCorrelation": 0.7559813084112151, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.1700354703593907 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "67", "type": "numeric", "distinct": "54", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "108", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_MR_1", "index": "1", "type": "numeric", "distinct": "34", "missing": "0", "min": "47", "max": "506", "mean": "225", "stdev": "83" }, { "name": "ATSC1v", "index": "2", "type": "numeric", "distinct": "103", "missing": "0", "min": "2", "max": "12", "mean": "6", "stdev": "2" }, { "name": "ATSC3v", "index": "3", "type": "numeric", "distinct": "105", "missing": "0", "min": "3", "max": "31", "mean": "13", "stdev": "5" }, { "name": "ATSC4v", "index": "4", "type": "numeric", "distinct": "104", "missing": "0", "min": "4", "max": "42", "mean": "15", "stdev": "7" }, { "name": "Mi", "index": "5", "type": "numeric", "distinct": "40", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "6", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "7", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "C.", "index": "8", "type": "numeric", "distinct": "67", "missing": "0", "min": "29", "max": "54", "mean": "42", "stdev": "5" }, { "name": "GATS1v", "index": "9", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "CIC0", "index": "10", "type": "numeric", "distinct": "98", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMin5_Bh.s.", "index": "11", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Mv", "index": "12", "type": "numeric", "distinct": "78", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.s.", "index": "13", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.s.", "index": "14", "type": "numeric", "distinct": "75", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC1i", "index": "15", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC5v", "index": "16", "type": "numeric", "distinct": "106", "missing": "0", "min": "2", "max": "46", "mean": "14", "stdev": "7" }, { "name": "SpMAD_EA.ri.", "index": "17", "type": "numeric", "distinct": "87", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "18", "type": "numeric", "distinct": "88", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMin6_Bh.e.", "index": "19", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.i.", "index": "20", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin6_Bh.v.", "index": "21", "type": "numeric", "distinct": "85", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "DLS_05", "index": "22", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "nH", "index": "23", "type": "numeric", "distinct": "30", "missing": "0", "min": "7", "max": "47", "mean": "23", "stdev": "8" }, { "name": "P_VSA_e_1", "index": "24", "type": "numeric", "distinct": "32", "missing": "0", "min": "47", "max": "541", "mean": "256", "stdev": "97" }, { "name": "P_VSA_m_1", "index": "25", "type": "numeric", "distinct": "32", "missing": "0", "min": "47", "max": "541", "mean": "256", "stdev": "97" }, { "name": "P_VSA_p_1", "index": "26", "type": "numeric", "distinct": "40", "missing": "0", "min": "47", "max": "541", "mean": "258", "stdev": "97" }, { "name": "P_VSA_s_2", "index": "27", "type": "numeric", "distinct": "35", "missing": "0", "min": "47", "max": "541", "mean": "256", "stdev": "97" }, { "name": "P_VSA_v_1", "index": "28", "type": "numeric", "distinct": "32", "missing": "0", "min": "47", "max": "541", "mean": "256", "stdev": "97" }, { "name": "P_VSA_LogP_2", "index": "29", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "78", "mean": "22", "stdev": "16" }, { "name": "P_VSA_m_2", "index": "30", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "345", "mean": "155", "stdev": "56" }, { "name": "PHI", "index": "31", "type": "numeric", "distinct": "103", "missing": "0", "min": "2", "max": "16", "mean": "6", "stdev": "2" }, { "name": "S3K", "index": "32", "type": "numeric", "distinct": "104", "missing": "0", "min": "1", "max": "13", "mean": "5", "stdev": "2" }, { "name": "SpMax3_Bh.i.", "index": "33", "type": "numeric", "distinct": "96", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.e.", "index": "34", "type": "numeric", "distinct": "87", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMin7_Bh.i.", "index": "35", "type": "numeric", "distinct": "82", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "nCsp3", "index": "36", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "24", "mean": "7", "stdev": "5" }, { "name": "Eta_FL_A", "index": "37", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS4i", "index": "38", "type": "numeric", "distinct": "99", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC1e", "index": "39", "type": "numeric", "distinct": "78", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "RCI", "index": "40", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X3Av", "index": "41", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS1i", "index": "42", "type": "numeric", "distinct": "90", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "43", "type": "numeric", "distinct": "86", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eta_beta_A", "index": "44", "type": "numeric", "distinct": "95", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "SpMax5_Bh.v.", "index": "45", "type": "numeric", "distinct": "92", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "MATS2m", "index": "46", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATS8m", "index": "47", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "ATS8v", "index": "48", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "1" }, { "name": "MSD", "index": "49", "type": "numeric", "distinct": "100", "missing": "0", "min": "3", "max": "11", "mean": "6", "stdev": "1" }, { "name": "P_VSA_MR_5", "index": "50", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "213", "mean": "42", "stdev": "32" }, { "name": "SpMAD_EA.bo.", "index": "51", "type": "numeric", "distinct": "86", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax6_Bh.e.", "index": "52", "type": "numeric", "distinct": "87", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.i.", "index": "53", "type": "numeric", "distinct": "82", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax8_Bh.m.", "index": "54", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMin2_Bh.m.", "index": "55", "type": "numeric", "distinct": "83", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin2_Bh.s.", "index": "56", "type": "numeric", "distinct": "88", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC1s", "index": "57", "type": "numeric", "distinct": "105", "missing": "0", "min": "2", "max": "79", "mean": "13", "stdev": "12" }, { "name": "X2Av", "index": "58", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1i", "index": "59", "type": "numeric", "distinct": "89", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_e_2", "index": "60", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "278", "mean": "138", "stdev": "40" }, { "name": "P_VSA_i_2", "index": "61", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "272", "mean": "128", "stdev": "38" }, { "name": "ATS8s", "index": "62", "type": "numeric", "distinct": "105", "missing": "0", "min": "1", "max": "7", "mean": "6", "stdev": "1" }, { "name": "ATS5s", "index": "63", "type": "numeric", "distinct": "103", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "P_VSA_p_3", "index": "64", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "278", "mean": "149", "stdev": "44" }, { "name": "P_VSA_v_3", "index": "65", "type": "numeric", "distinct": "104", "missing": "0", "min": "8", "max": "278", "mean": "149", "stdev": "44" }, { "name": "AAC", "index": "66", "type": "numeric", "distinct": "93", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" } ], "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 }