{"id":"W2779844278","doi":"10.1101/217802","title":"WeSeqMiner: A Weka package for building machine-learning models for sequence data","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Workbench; Computer science; Workflow; Sequence (biology); Artificial intelligence; Data mining; Machine learning; Database; Visualization","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006361496,0.005042809,0.003225431,0.007568096,0.00183273,0.003936581,0.006055883,0.002293562,0.04216148],"category_scores_gemma":[0.02894444,0.004228683,0.007815301,0.004736506,0.0008032937,0.003175287,0.002882688,0.006131606,0.04149183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386285,"about_ca_system_score_gemma":0.004678768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00592098,"about_ca_topic_score_gemma":0.007859573,"domain_scores_codex":[0.9963419,0.001010507,0.0007100539,0.0009318482,0.0008456189,0.0001600458],"domain_scores_gemma":[0.9894605,0.007242285,0.0007697276,0.001363477,0.001006994,0.0001570768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009071473,0.0003296508,0.00957186,0.009246181,0.003695083,0.001565779,0.0007968638,0.06672869,0.0174554,0.01903978,0.6935077,0.1771559],"study_design_scores_gemma":[0.0006751269,0.0001997863,0.005368606,0.001126717,0.001426861,0.0009727526,0.000259044,0.357848,0.03691273,0.1097661,0.4849207,0.0005234866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.002889293,0.0007363372,0.5754979,0.0006308394,0.0002300075,0.0005898306,0.08966253,0.3276438,0.002119427],"genre_scores_gemma":[0.0187845,0.0009996332,0.8171989,0.0007588529,0.0001181891,0.003648265,0.1085391,0.04666341,0.003289157],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04216148,"threshold_uncertainty_score":0.1410441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05009955651760598,"score_gpt":0.2929193196621664,"score_spread":0.2428197631445604,"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."}}