{ "data_id": "27687", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304401", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304401", "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: CHEMBL2304401 (TID: 105564), and it has 68 rows and 57 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": "2016-07-14 22:09:51", "update_comment": null, "last_update": "2016-07-14 22:09:51", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3337579\/data_51500.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL2304401", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL2304401 (TID: 105564), and it has 68 rows and 57 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": 68, "NumberOfFeatures": 59, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 58, "NumberOfSymbolicFeatures": 1, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.3382352941176472, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 1.1315651121204469, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 39.77810826572008, "Quartile1SkewnessOfNumericAtts": -0.05064144299167801, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.3661508339298991, "AutoCorrelation": 0.6783582089552239, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "ClassEntropy": null, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": -0.587708885864973, "Dimensionality": 0.8676470588235294, "MeanSkewnessOfNumericAtts": 0.18511152504165837, "Quartile2MeansOfNumericAtts": 4.334992647058823, "EquivalentNumberOfAtts": null, "MeanStdDevOfNumericAtts": 10.026779818592953, "Quartile2MutualInformation": null, "MajorityClassPercentage": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.0634145882188362, "MajorityClassSize": null, "MinKurtosisOfNumericAtts": -1.7843054871300437, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.5734936623346898, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 30.179231463945584, "MinMeansOfNumericAtts": -1.2699264705882354, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 385.20176470588234, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.15940209551782614, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.30508474576271, "Quartile3MeansOfNumericAtts": 53.665191176470586, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -5.517096159598814, "PercentageOfSymbolicFeatures": 1.694915254237288, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 3.4629766639916664, "MinStdDevOfNumericAtts": 0.022864696305392736, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.35426457440601944, "MaxStdDevOfNumericAtts": 72.56462837270774, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -1.0741018049696947, "Quartile3StdDevOfNumericAtts": 17.257875727420465 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "58", "type": "numeric", "distinct": "28", "missing": "0", "target": "1", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "68", "missing": "0", "identifier": "1", "distr": [] }, { "name": "P_VSA_MR_2", "index": "1", "type": "numeric", "distinct": "11", "missing": "0", "min": "70", "max": "184", "mean": "130", "stdev": "37" }, { "name": "ATSC3e", "index": "2", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "GGI10", "index": "3", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Psi_i_s", "index": "4", "type": "numeric", "distinct": "44", "missing": "0", "min": "44", "max": "91", "mean": "73", "stdev": "11" }, { "name": "Eig04_AEA.dm.", "index": "5", "type": "numeric", "distinct": "43", "missing": "0", "min": "2", "max": "3", "mean": "3", "stdev": "0" }, { "name": "Eig03_AEA.dm.", "index": "6", "type": "numeric", "distinct": "40", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "CATS2D_02_NL", "index": "7", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax6_Bh.s.", "index": "8", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "C.040", "index": "9", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_AN", "index": "10", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_01_DN", "index": "11", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "CATS2D_02_DA", "index": "12", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "NdssC", "index": "13", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "nROH", "index": "14", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "O.058", "index": "15", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "P_VSA_e_5", "index": "16", "type": "numeric", "distinct": "7", "missing": "0", "min": "25", "max": "172", "mean": "117", "stdev": "38" }, { "name": "P_VSA_LogP_4", "index": "17", "type": "numeric", "distinct": "5", "missing": "0", "min": "30", "max": "168", "mean": "121", "stdev": "38" }, { "name": "P_VSA_m_3", "index": "18", "type": "numeric", "distinct": "9", "missing": "0", "min": "25", "max": "172", "mean": "118", "stdev": "36" }, { "name": "P_VSA_p_2", "index": "19", "type": "numeric", "distinct": "8", "missing": "0", "min": "25", "max": "174", "mean": "120", "stdev": "36" }, { "name": "P_VSA_s_6", "index": "20", "type": "numeric", "distinct": "10", "missing": "0", "min": "25", "max": "172", "mean": "120", "stdev": "36" }, { "name": "P_VSA_v_2", "index": "21", "type": "numeric", "distinct": "9", "missing": "0", "min": "61", "max": "174", "mean": "121", "stdev": "34" }, { "name": "SAacc", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "61", "max": "172", "mean": "119", "stdev": "34" }, { "name": "Eig04_EA", "index": "23", "type": "numeric", "distinct": "54", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SM12_AEA.bo.", "index": "24", "type": "numeric", "distinct": "54", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SdO", "index": "25", "type": "numeric", "distinct": "67", "missing": "0", "min": "11", "max": "47", "mean": "28", "stdev": "7" }, { "name": "SdssC", "index": "26", "type": "numeric", "distinct": "64", "missing": "0", "min": "-3", "max": "0", "mean": "-1", "stdev": "1" }, { "name": "ATSC4s", "index": "27", "type": "numeric", "distinct": "67", "missing": "0", "min": "27", "max": "76", "mean": "51", "stdev": "10" }, { "name": "ATSC3s", "index": "28", "type": "numeric", "distinct": "67", "missing": "0", "min": "30", "max": "150", "mean": "52", "stdev": "17" }, { "name": "NsOH", "index": "29", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "O.057", "index": "30", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SAdon", "index": "31", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "85", "mean": "58", "stdev": "22" }, { "name": "SpMax7_Bh.s.", "index": "32", "type": "numeric", "distinct": "38", "missing": "0", "min": "4", "max": "5", "mean": "4", "stdev": "0" }, { "name": "DELS", "index": "33", "type": "numeric", "distinct": "67", "missing": "0", "min": "13", "max": "51", "mean": "35", "stdev": "8" }, { "name": "Eig03_EA.dm.", "index": "34", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "1" }, { "name": "NdO", "index": "35", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "nHAcc", "index": "36", "type": "numeric", "distinct": "4", "missing": "0", "min": "3", "max": "6", "mean": "4", "stdev": "1" }, { "name": "nHet", "index": "37", "type": "numeric", "distinct": "5", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "nO", "index": "38", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "6", "mean": "4", "stdev": "1" }, { "name": "SpMax5_Bh.s.", "index": "39", "type": "numeric", "distinct": "34", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "1" }, { "name": "TPSA.NO.", "index": "40", "type": "numeric", "distinct": "8", "missing": "0", "min": "17", "max": "106", "mean": "74", "stdev": "20" }, { "name": "TPSA.Tot.", "index": "41", "type": "numeric", "distinct": "8", "missing": "0", "min": "17", "max": "106", "mean": "74", "stdev": "20" }, { "name": "GGI9", "index": "42", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "ATSC2e", "index": "43", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS2s", "index": "44", "type": "numeric", "distinct": "52", "missing": "0", "min": "5", "max": "6", "mean": "6", "stdev": "0" }, { "name": "IC5", "index": "45", "type": "numeric", "distinct": "53", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ZM1MulPer", "index": "46", "type": "numeric", "distinct": "65", "missing": "0", "min": "177", "max": "526", "mean": "385", "stdev": "73" }, { "name": "Eig04_AEA.ri.", "index": "47", "type": "numeric", "distinct": "53", "missing": "0", "min": "3", "max": "3", "mean": "3", "stdev": "0" }, { "name": "ZM1V", "index": "48", "type": "numeric", "distinct": "38", "missing": "0", "min": "166", "max": "488", "mean": "357", "stdev": "67" }, { "name": "IC4", "index": "49", "type": "numeric", "distinct": "57", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SpMax2_Bh.s.", "index": "50", "type": "numeric", "distinct": "8", "missing": "0", "min": "4", "max": "8", "mean": "7", "stdev": "1" }, { "name": "Eig05_EA.ed.", "index": "51", "type": "numeric", "distinct": "54", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "SM14_AEA.dm.", "index": "52", "type": "numeric", "distinct": "54", "missing": "0", "min": "3", "max": "7", "mean": "5", "stdev": "1" }, { "name": "Eig02_EA.dm.", "index": "53", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig04_EA.ri.", "index": "54", "type": "numeric", "distinct": "45", "missing": "0", "min": "2", "max": "2", "mean": "2", "stdev": "0" }, { "name": "ATSC2s", "index": "55", "type": "numeric", "distinct": "64", "missing": "0", "min": "18", "max": "142", "mean": "51", "stdev": "18" }, { "name": "MATS1e", "index": "56", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "nDB", "index": "57", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "2", "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 }