{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001641753,0.0007803032,0.0006891225,0.0001552468,0.0005423507,0.000518689,0.003034685,0.000930269,0.000007500112],"category_scores_gemma":[0.002739299,0.0008390874,0.0002792653,0.00007934999,0.0001741588,0.00005462929,0.002915242,0.0008770964,0.000007897276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009463311,"about_ca_system_score_gemma":0.0006720688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004096274,"about_ca_topic_score_gemma":0.000006208321,"domain_scores_codex":[0.9964405,0.0001098247,0.0007182486,0.001547983,0.0003305864,0.0008527981],"domain_scores_gemma":[0.9934074,0.0001030602,0.001120705,0.004490692,0.0006062393,0.0002719003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001785259,0.00008234154,0.002219998,0.002031006,0.0004662203,0.000007731999,0.00001402115,0.005482847,0.9856208,0.001020279,0.002842322,0.00003391876],"study_design_scores_gemma":[0.001732351,0.0003341355,0.0004313638,0.0005852018,0.0003526302,1.748298e-7,0.00000345226,0.5614064,0.1777992,0.00002752709,0.2553102,0.002017431],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1235738,0.003027895,0.8585269,0.0005157933,0.00176939,0.00356322,0.008549336,0.0003987321,0.00007495119],"genre_scores_gemma":[0.7814358,0.0006006879,0.2153905,0.0002122685,0.001237888,0.0005822828,0.0001364978,0.0002967931,0.0001073575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8078216,"threshold_uncertainty_score":0.999406,"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."}}