{ "data_id": "32753", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1903", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1903", "version": 8, "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: CHEMBL1903 (TID: 113), and it has 95 rows and 60 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 11:01:24", "update_comment": null, "last_update": "2016-07-15 11:01:24", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3488841\/data_52038.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-CHEMBL1903", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1903 (TID: 113), and it has 95 rows and 60 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": 95, "NumberOfFeatures": 62, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 61, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 7.133799419715069, "MinStdDevOfNumericAtts": 0.011516364519053843, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.44687125102388137, "MaxStdDevOfNumericAtts": 122.12179110886647, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 0.9084644326692626, "Quartile3StdDevOfNumericAtts": 4.85912308035323, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.4037052631578948, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 7.468271965467268, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 27.759084555651423, "Quartile1SkewnessOfNumericAtts": -2.8064739704635175, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.24703979796372214, "AutoCorrelation": 0.19461702127659572, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 2.9259475613238872, "Dimensionality": 0.6526315789473685, "MeanSkewnessOfNumericAtts": -0.6789200989884702, "Quartile2MeansOfNumericAtts": 4.804042105263158, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.74069690611933, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.19002433618987952, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.6099487386190534, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5686613596801537, "MaxKurtosisOfNumericAtts": 61.24545891743325, "MinMeansOfNumericAtts": -0.18632631578947387, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 526.755747368421, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 12.949527531493684, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.38709677419355, "Quartile3MeansOfNumericAtts": 15.017857894736842, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -3.9260162109458836, "PercentageOfSymbolicFeatures": 1.6129032258064515, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "61", "type": "numeric", "distinct": "77", "missing": "0", "target": "1", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "95", "missing": "0", "identifier": "1", "distr": [] }, { "name": "ATS2p", "index": "1", "type": "numeric", "distinct": "64", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "X5sol", "index": "2", "type": "numeric", "distinct": "50", "missing": "0", "min": "0", "max": "13", "mean": "7", "stdev": "2" }, { "name": "H.051", "index": "3", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "2" }, { "name": "ATSC2p", "index": "4", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "17", "mean": "10", "stdev": "3" }, { "name": "GATS2v", "index": "5", "type": "numeric", "distinct": "58", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATS1p", "index": "6", "type": "numeric", "distinct": "54", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "TPSA.Tot.", "index": "7", "type": "numeric", "distinct": "17", "missing": "0", "min": "12", "max": "115", "mean": "66", "stdev": "32" }, { "name": "MATS1m", "index": "8", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "CATS2D_05_NL", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC2m", "index": "10", "type": "numeric", "distinct": "66", "missing": "0", "min": "6", "max": "43", "mean": "24", "stdev": "7" }, { "name": "ATSC5p", "index": "11", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "24", "mean": "15", "stdev": "5" }, { "name": "MATS5i", "index": "12", "type": "numeric", "distinct": "63", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin8_Bh.m.", "index": "13", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS4p", "index": "14", "type": "numeric", "distinct": "65", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eig15_EA.ed.", "index": "15", "type": "numeric", "distinct": "47", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "2" }, { "name": "SM10_AEA.ri.", "index": "16", "type": "numeric", "distinct": "47", "missing": "0", "min": "-3", "max": "3", "mean": "0", "stdev": "2" }, { "name": "ATS3p", "index": "17", "type": "numeric", "distinct": "67", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS5p", "index": "18", "type": "numeric", "distinct": "73", "missing": "0", "min": "1", "max": "5", "mean": "4", "stdev": "1" }, { "name": "X3A", "index": "19", "type": "numeric", "distinct": "27", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4A", "index": "20", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC3p", "index": "21", "type": "numeric", "distinct": "74", "missing": "0", "min": "2", "max": "22", "mean": "13", "stdev": "3" }, { "name": "ZM2Mad", "index": "22", "type": "numeric", "distinct": "70", "missing": "0", "min": "25", "max": "354", "mean": "200", "stdev": "58" }, { "name": "ATS2i", "index": "23", "type": "numeric", "distinct": "63", "missing": "0", "min": "3", "max": "5", "mean": "5", "stdev": "0" }, { "name": "X5A", "index": "24", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MWC07", "index": "25", "type": "numeric", "distinct": "58", "missing": "0", "min": "6", "max": "10", "mean": "9", "stdev": "0" }, { "name": "SpMin2_Bh.p.", "index": "26", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Rperim", "index": "27", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "36", "mean": "19", "stdev": "6" }, { "name": "GATS4p", "index": "28", "type": "numeric", "distinct": "63", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "ATSC8m", "index": "29", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "75", "mean": "37", "stdev": "16" }, { "name": "Chi1_EA.dm.", "index": "30", "type": "numeric", "distinct": "61", "missing": "0", "min": "4", "max": "39", "mean": "19", "stdev": "8" }, { "name": "SpDiam_EA.bo.", "index": "31", "type": "numeric", "distinct": "36", "missing": "0", "min": "5", "max": "8", "mean": "7", "stdev": "0" }, { "name": "GATS5e", "index": "32", "type": "numeric", "distinct": "72", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "TWC", "index": "33", "type": "numeric", "distinct": "57", "missing": "0", "min": "9", "max": "13", "mean": "12", "stdev": "1" }, { "name": "ATSC3m", "index": "34", "type": "numeric", "distinct": "75", "missing": "0", "min": "8", "max": "60", "mean": "34", "stdev": "8" }, { "name": "CATS2D_08_NL", "index": "35", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "CATS2D_09_DL", "index": "36", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nR06", "index": "37", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Sp", "index": "38", "type": "numeric", "distinct": "57", "missing": "0", "min": "9", "max": "60", "mean": "38", "stdev": "9" }, { "name": "X0v", "index": "39", "type": "numeric", "distinct": "58", "missing": "0", "min": "4", "max": "28", "mean": "17", "stdev": "4" }, { "name": "X1sol", "index": "40", "type": "numeric", "distinct": "41", "missing": "0", "min": "3", "max": "24", "mean": "14", "stdev": "4" }, { "name": "ATS4v", "index": "41", "type": "numeric", "distinct": "77", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.e.", "index": "42", "type": "numeric", "distinct": "41", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMax4_Bh.i.", "index": "43", "type": "numeric", "distinct": "48", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MWC08", "index": "44", "type": "numeric", "distinct": "58", "missing": "0", "min": "7", "max": "11", "mean": "10", "stdev": "1" }, { "name": "MWC09", "index": "45", "type": "numeric", "distinct": "58", "missing": "0", "min": "8", "max": "12", "mean": "11", "stdev": "1" }, { "name": "SRW10", "index": "46", "type": "numeric", "distinct": "57", "missing": "0", "min": "7", "max": "11", "mean": "10", "stdev": "0" }, { "name": "SpMin1_Bh.s.", "index": "47", "type": "numeric", "distinct": "22", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin4_Bh.m.", "index": "48", "type": "numeric", "distinct": "48", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMin4_Bh.v.", "index": "49", "type": "numeric", "distinct": "46", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "GATS3e", "index": "50", "type": "numeric", "distinct": "68", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "C.024", "index": "51", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "16", "mean": "8", "stdev": "4" }, { "name": "Eta_betaP", "index": "52", "type": "numeric", "distinct": "16", "missing": "0", "min": "2", "max": "32", "mean": "15", "stdev": "5" }, { "name": "NaaCH", "index": "53", "type": "numeric", "distinct": "12", "missing": "0", "min": "0", "max": "18", "mean": "8", "stdev": "4" }, { "name": "nCar", "index": "54", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "28", "mean": "12", "stdev": "5" }, { "name": "nCsp2", "index": "55", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "31", "mean": "15", "stdev": "5" }, { "name": "P_VSA_MR_6", "index": "56", "type": "numeric", "distinct": "43", "missing": "0", "min": "1", "max": "201", "mean": "99", "stdev": "44" }, { "name": "P_VSA_e_2", "index": "57", "type": "numeric", "distinct": "63", "missing": "0", "min": "8", "max": "296", "mean": "151", "stdev": "50" }, { "name": "SpMin5_Bh.s.", "index": "58", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "VvdwMG", "index": "59", "type": "numeric", "distinct": "57", "missing": "0", "min": "61", "max": "341", "mean": "219", "stdev": "50" }, { "name": "Vx", "index": "60", "type": "numeric", "distinct": "57", "missing": "0", "min": "141", "max": "824", "mean": "527", "stdev": "122" } ], "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 }