{"id":"W1850375728","doi":"10.1186/s13321-015-0092-4","title":"Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods","year":2015,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Computer science; Cheminformatics; Interpretability; Quantitative structure–activity relationship; Feature selection; Applicability domain; Visual analytics; Data mining; Machine learning; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Property (philosophy); Software; Feature (linguistics); Process (computing); Generality; Domain (mathematical analysis); Visualization; Bioinformatics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004599899,0.000224034,0.0005149078,0.0004963413,0.00004920826,0.0002575143,0.0008831806,0.0001280088,0.000004114598],"category_scores_gemma":[0.002000207,0.0002015458,0.0002115275,0.0008757816,0.00003704015,0.003166735,0.0001702023,0.000333707,0.000005364156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004581618,"about_ca_system_score_gemma":0.0008286216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000258748,"about_ca_topic_score_gemma":0.000001327642,"domain_scores_codex":[0.997089,0.0000505493,0.001689547,0.0001034287,0.0007138501,0.0003536101],"domain_scores_gemma":[0.996581,0.000822238,0.001006859,0.0002221044,0.001087333,0.0002804465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006408967,0.001181498,0.002669447,0.001797168,0.0006258414,0.00001828233,0.06090997,0.2252506,0.006005872,0.01793501,0.05007359,0.6328918],"study_design_scores_gemma":[0.00162561,0.0002613504,0.0000751764,0.00008154478,0.00003375506,0.0001573436,0.0009791657,0.9356,0.0485418,0.005268021,0.007144367,0.0002318141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03652942,0.00006597223,0.9609706,0.0002119683,0.0005457301,0.0002118919,0.000002240915,0.00002828872,0.001433895],"genre_scores_gemma":[0.03950497,0.00001261581,0.9599023,0.0003187016,0.0001545222,0.000007725563,0.000004681391,0.00001396336,0.0000804607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7103494,"threshold_uncertainty_score":0.8218801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0632942398036562,"score_gpt":0.3859116379978224,"score_spread":0.3226173981941662,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}