{ "data_id": "29035", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3305", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3305", "version": 7, "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: CHEMBL3305 (TID: 12643), and it has 105 rows and 62 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 01:30:32", "update_comment": null, "last_update": "2016-07-15 01:30:32", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3381309\/data_52366.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3305", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3305 (TID: 12643), and it has 105 rows and 62 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": 105, "NumberOfFeatures": 64, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 63, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 58.19241599295448, "MinMeansOfNumericAtts": -4.850190476190476, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 15.607746247348793, "MaxMeansOfNumericAtts": 112.31545714285714, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 15.241514285714286, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.4375, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.8409154161967287, "PercentageOfSymbolicFeatures": 1.5625, "Quartile3SkewnessOfNumericAtts": 3.240795944099771, "MaxSkewnessOfNumericAtts": 6.872760274768878, "MinStdDevOfNumericAtts": 0.002787333989537452, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 7.470843799930971, "MaxStdDevOfNumericAtts": 47.659432604806454, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": 1.3988445568559342, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.7188476190476191, "MeanKurtosisOfNumericAtts": 10.862407091818428, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 18.129401965230535, "Quartile1SkewnessOfNumericAtts": 0.4888274709648921, "AutoCorrelation": -0.7733076923076918, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.10562113508111996, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.6095238095238096, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 5.1497704482909485, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 1.804957895441125, "Quartile2MeansOfNumericAtts": 3.0667714285714287, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 7.798549850226688, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.7801873914901611, "Quartile2StdDevOfNumericAtts": 0.7753056823594806, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.227821261968709, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "63", "type": "numeric", "distinct": "85", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "7", "stdev": "2" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "105", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_p_2", "index": "1", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "281", "mean": "88", "stdev": "37" }, { "name": "BLTA96", "index": "2", "type": "numeric", "distinct": "61", "missing": "0", "min": "-8", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "BLTD48", "index": "3", "type": "numeric", "distinct": "63", "missing": "0", "min": "-8", "max": "0", "mean": "-5", "stdev": "1" }, { "name": "BLTF96", "index": "4", "type": "numeric", "distinct": "60", "missing": "0", "min": "-7", "max": "0", "mean": "-4", "stdev": "1" }, { "name": "MLOGP", "index": "5", "type": "numeric", "distinct": "70", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "MLOGP2", "index": "6", "type": "numeric", "distinct": "70", "missing": "0", "min": "2", "max": "43", "mean": "14", "stdev": "6" }, { "name": "RBF", "index": "7", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "P_VSA_v_2", "index": "8", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "281", "mean": "89", "stdev": "37" }, { "name": "SAacc", "index": "9", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "281", "mean": "89", "stdev": "37" }, { "name": "TPSA.NO.", "index": "10", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "201", "mean": "48", "stdev": "23" }, { "name": "TPSA.Tot.", "index": "11", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "210", "mean": "48", "stdev": "24" }, { "name": "P_VSA_e_5", "index": "12", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "260", "mean": "87", "stdev": "36" }, { "name": "SpMax6_Bh.s.", "index": "13", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "7", "mean": "4", "stdev": "0" }, { "name": "P_VSA_m_3", "index": "14", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "260", "mean": "88", "stdev": "36" }, { "name": "S3K", "index": "15", "type": "numeric", "distinct": "85", "missing": "0", "min": "2", "max": "8", "mean": "2", "stdev": "1" }, { "name": "P_VSA_s_6", "index": "16", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "260", "mean": "94", "stdev": "36" }, { "name": "nHAcc", "index": "17", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "14", "mean": "3", "stdev": "2" }, { "name": "RBN", "index": "18", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "CATS2D_03_LL", "index": "19", "type": "numeric", "distinct": "31", "missing": "0", "min": "4", "max": "45", "mean": "30", "stdev": "10" }, { "name": "Eta_alpha_A", "index": "20", "type": "numeric", "distinct": "28", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "nHet", "index": "21", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "2" }, { "name": "SpMaxA_EA.ed.", "index": "22", "type": "numeric", "distinct": "55", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_MR_2", "index": "23", "type": "numeric", "distinct": "39", "missing": "0", "min": "0", "max": "192", "mean": "77", "stdev": "32" }, { "name": "SpMax5_Bh.s.", "index": "24", "type": "numeric", "distinct": "85", "missing": "0", "min": "4", "max": "7", "mean": "4", "stdev": "1" }, { "name": "D.Dtr06", "index": "25", "type": "numeric", "distinct": "62", "missing": "0", "min": "53", "max": "516", "mean": "112", "stdev": "48" }, { "name": "SAdon", "index": "26", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "171", "mean": "65", "stdev": "31" }, { "name": "SsOH", "index": "27", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "38", "mean": "15", "stdev": "7" }, { "name": "DLS_02", "index": "28", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS2e", "index": "29", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1m", "index": "30", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "O.", "index": "31", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "17", "mean": "5", "stdev": "3" }, { "name": "SpMin1_Bh.e.", "index": "32", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "nO", "index": "33", "type": "numeric", "distinct": "8", "missing": "0", "min": "0", "max": "12", "mean": "3", "stdev": "1" }, { "name": "IDE", "index": "34", "type": "numeric", "distinct": "59", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "ATSC4s", "index": "35", "type": "numeric", "distinct": "98", "missing": "0", "min": "10", "max": "269", "mean": "59", "stdev": "32" }, { "name": "Me", "index": "36", "type": "numeric", "distinct": "37", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Psi_i_t", "index": "37", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax7_Bh.s.", "index": "38", "type": "numeric", "distinct": "81", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "0" }, { "name": "MATS4m", "index": "39", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "LOC", "index": "40", "type": "numeric", "distinct": "41", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "0" }, { "name": "GATS5s", "index": "41", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MSD", "index": "42", "type": "numeric", "distinct": "60", "missing": "0", "min": "4", "max": "10", "mean": "5", "stdev": "1" }, { "name": "NsOH", "index": "43", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "PHI", "index": "44", "type": "numeric", "distinct": "86", "missing": "0", "min": "2", "max": "11", "mean": "4", "stdev": "1" }, { "name": "SpMax4_Bh.s.", "index": "45", "type": "numeric", "distinct": "84", "missing": "0", "min": "4", "max": "7", "mean": "5", "stdev": "1" }, { "name": "ALOGP", "index": "46", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "1" }, { "name": "ALOGP2", "index": "47", "type": "numeric", "distinct": "96", "missing": "0", "min": "1", "max": "49", "mean": "14", "stdev": "7" }, { "name": "GATS5m", "index": "48", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1A", "index": "49", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS5e", "index": "50", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_epsi_A", "index": "51", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS4s", "index": "52", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Psi_e_A", "index": "53", "type": "numeric", "distinct": "84", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "Psi_i_A", "index": "54", "type": "numeric", "distinct": "84", "missing": "0", "min": "2", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATSC2s", "index": "55", "type": "numeric", "distinct": "98", "missing": "0", "min": "6", "max": "180", "mean": "19", "stdev": "18" }, { "name": "HVcpx", "index": "56", "type": "numeric", "distinct": "57", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "nR10", "index": "57", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "SpMax1_Bh.i.", "index": "58", "type": "numeric", "distinct": "52", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "CATS2D_04_LL", "index": "59", "type": "numeric", "distinct": "32", "missing": "0", "min": "2", "max": "43", "mean": "24", "stdev": "9" }, { "name": "MATS4e", "index": "60", "type": "numeric", "distinct": "70", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin2_Bh.i.", "index": "61", "type": "numeric", "distinct": "54", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "S2K", "index": "62", "type": "numeric", "distinct": "88", "missing": "0", "min": "4", "max": "14", "mean": "5", "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 }