{ "data_id": "32716", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1075140", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL1075140", "version": 10, "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: CHEMBL1075140 (TID: 103071), and it has 150 rows and 63 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 10:55:50", "update_comment": null, "last_update": "2016-07-15 10:55:50", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3487920\/data_52529.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-CHEMBL1075140", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL1075140 (TID: 103071), and it has 150 rows and 63 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": 150, "NumberOfFeatures": 65, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 64, "NumberOfSymbolicFeatures": 1, "MaxSkewnessOfNumericAtts": 1.982621999460773, "MinStdDevOfNumericAtts": 0.0033610214703843804, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.628999238740848, "MaxStdDevOfNumericAtts": 91.68359709248287, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.9251197304318038, "Quartile3StdDevOfNumericAtts": 1.0981868121320244, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.533985, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.005697177501567917, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 12.101302604166667, "Quartile1SkewnessOfNumericAtts": 0.00940176120573473, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.081460318128241, "AutoCorrelation": 0.4244161073825503, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.33235612713029106, "Dimensionality": 0.43333333333333335, "MeanSkewnessOfNumericAtts": 0.3503544920424474, "Quartile2MeansOfNumericAtts": 2.035276666666666, "EquivalentNumberOfAtts": null, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 5.646027342734004, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.33258669573050736, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.8048717927670643, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.34177734379650515, "MaxKurtosisOfNumericAtts": 5.08817795563603, "MinMeansOfNumericAtts": -0.15744666666666668, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 124.72939333333333, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.6179366061358041, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.46153846153847, "Quartile3MeansOfNumericAtts": 6.647381666666667, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.34167427612706, "PercentageOfSymbolicFeatures": 1.5384615384615385, "Quartile3MutualInformation": null }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "64", "type": "numeric", "distinct": "118", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "150", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Vindex", "index": "1", "type": "numeric", "distinct": "53", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC6e", "index": "2", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "Xindex", "index": "3", "type": "numeric", "distinct": "73", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "DECC", "index": "4", "type": "numeric", "distinct": "86", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "H.051", "index": "5", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "2" }, { "name": "MATS6i", "index": "6", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS7v", "index": "7", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin7_Bh.v.", "index": "8", "type": "numeric", "distinct": "76", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Yindex", "index": "9", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "JGI5", "index": "10", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpDiam_AEA.ed.", "index": "11", "type": "numeric", "distinct": "55", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "AECC", "index": "12", "type": "numeric", "distinct": "88", "missing": "0", "min": "9", "max": "16", "mean": "12", "stdev": "2" }, { "name": "HVcpx", "index": "13", "type": "numeric", "distinct": "87", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "IDE", "index": "14", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "SpMin7_Bh.p.", "index": "15", "type": "numeric", "distinct": "80", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS5s", "index": "16", "type": "numeric", "distinct": "133", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC2e", "index": "17", "type": "numeric", "distinct": "113", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpDiam_AEA.bo.", "index": "18", "type": "numeric", "distinct": "60", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "ATS5m", "index": "19", "type": "numeric", "distinct": "126", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATSC7e", "index": "20", "type": "numeric", "distinct": "126", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMaxA_AEA.dm.", "index": "21", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS3s", "index": "22", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NaaNH", "index": "23", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SaaNH", "index": "24", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "6", "mean": "2", "stdev": "2" }, { "name": "SpMin6_Bh.e.", "index": "25", "type": "numeric", "distinct": "84", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMax6_Bh.i.", "index": "26", "type": "numeric", "distinct": "78", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "SpMax1_Bh.p.", "index": "27", "type": "numeric", "distinct": "70", "missing": "0", "min": "4", "max": "4", "mean": "4", "stdev": "0" }, { "name": "P_VSA_p_2", "index": "28", "type": "numeric", "distinct": "55", "missing": "0", "min": "37", "max": "180", "mean": "108", "stdev": "31" }, { "name": "P_VSA_v_2", "index": "29", "type": "numeric", "distinct": "67", "missing": "0", "min": "37", "max": "270", "mean": "125", "stdev": "47" }, { "name": "ATS2s", "index": "30", "type": "numeric", "distinct": "126", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATS4m", "index": "31", "type": "numeric", "distinct": "136", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "ATS6s", "index": "32", "type": "numeric", "distinct": "134", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "SpDiam_EA.ed.", "index": "33", "type": "numeric", "distinct": "49", "missing": "0", "min": "15", "max": "26", "mean": "20", "stdev": "2" }, { "name": "SdO", "index": "34", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "51", "mean": "19", "stdev": "13" }, { "name": "P_VSA_MR_2", "index": "35", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "246", "mean": "94", "stdev": "65" }, { "name": "ATSC6s", "index": "36", "type": "numeric", "distinct": "142", "missing": "0", "min": "22", "max": "445", "mean": "102", "stdev": "92" }, { "name": "RDCHI", "index": "37", "type": "numeric", "distinct": "89", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "38", "type": "numeric", "distinct": "91", "missing": "0", "min": "5", "max": "10", "mean": "7", "stdev": "1" }, { "name": "JGI8", "index": "39", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ICR", "index": "40", "type": "numeric", "distinct": "77", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SpMaxA_EA.ed.", "index": "41", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATSC7m", "index": "42", "type": "numeric", "distinct": "142", "missing": "0", "min": "18", "max": "63", "mean": "32", "stdev": "10" }, { "name": "O.", "index": "43", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "8", "mean": "4", "stdev": "2" }, { "name": "MATS8i", "index": "44", "type": "numeric", "distinct": "110", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin6_Bh.i.", "index": "45", "type": "numeric", "distinct": "74", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_5", "index": "46", "type": "numeric", "distinct": "17", "missing": "0", "min": "0", "max": "111", "mean": "55", "stdev": "29" }, { "name": "GATS7s", "index": "47", "type": "numeric", "distinct": "129", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "MATS1m", "index": "48", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X1Per", "index": "49", "type": "numeric", "distinct": "135", "missing": "0", "min": "6", "max": "11", "mean": "8", "stdev": "1" }, { "name": "P_VSA_m_3", "index": "50", "type": "numeric", "distinct": "30", "missing": "0", "min": "0", "max": "197", "mean": "71", "stdev": "45" }, { "name": "GATS7m", "index": "51", "type": "numeric", "distinct": "127", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS8m", "index": "52", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS1s", "index": "53", "type": "numeric", "distinct": "95", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMax3_Bh.s.", "index": "54", "type": "numeric", "distinct": "54", "missing": "0", "min": "4", "max": "8", "mean": "6", "stdev": "1" }, { "name": "MATS3e", "index": "55", "type": "numeric", "distinct": "108", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "MATS7m", "index": "56", "type": "numeric", "distinct": "112", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS6i", "index": "57", "type": "numeric", "distinct": "123", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X1MulPer", "index": "58", "type": "numeric", "distinct": "136", "missing": "0", "min": "7", "max": "13", "mean": "10", "stdev": "1" }, { "name": "SpMin2_Bh.m.", "index": "59", "type": "numeric", "distinct": "63", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SpMax1_Bh.s.", "index": "60", "type": "numeric", "distinct": "37", "missing": "0", "min": "5", "max": "9", "mean": "7", "stdev": "1" }, { "name": "NdO", "index": "61", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "O.058", "index": "62", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "MAXDP", "index": "63", "type": "numeric", "distinct": "135", "missing": "0", "min": "2", "max": "8", "mean": "5", "stdev": "2" } ], "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 }