{"id":"W3003525926","doi":"10.1101/2020.01.30.926923","title":"Semi-supervised segmentation and genome annotation","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Simon Fraser University; Princess Margaret Cancer Centre; University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; Princess Margaret Cancer Foundation; University of Washington","keywords":"Annotation; Computer science; Segmentation; Precision and recall; Genome project; Artificial intelligence; Feature (linguistics); Genome; Metric (unit); Machine learning; Set (abstract data type); Pattern recognition (psychology); Biology; Gene; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004758595,0.001268061,0.001490052,0.002458866,0.001050989,0.001978097,0.003587995,0.002216196,0.002541302],"category_scores_gemma":[0.01100091,0.001018855,0.001710428,0.001983949,0.002577914,0.001884476,0.002996307,0.002133165,0.001598193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366236,"about_ca_system_score_gemma":0.001607329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003495535,"about_ca_topic_score_gemma":0.006250884,"domain_scores_codex":[0.993972,0.002268253,0.0002623278,0.00211504,0.001112661,0.000269694],"domain_scores_gemma":[0.9879786,0.005140162,0.00118041,0.003484089,0.001934272,0.0002825755],"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":[0.00132086,0.0003244146,0.007530505,0.0006392575,0.0005207637,0.0003125451,0.0007584094,0.379365,0.09629828,0.03234964,0.01331219,0.4672682],"study_design_scores_gemma":[0.0000258581,0.00005050638,0.001099325,0.00002528053,0.00001827474,0.00007664492,0.00005375658,0.9447109,0.0276726,0.02290145,0.003332565,0.00003277057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02129901,0.0001444783,0.9721773,0.0001415667,0.00003538699,0.00006583175,0.0005144296,0.00478759,0.0008343835],"genre_scores_gemma":[0.2537406,0.00008927161,0.7384712,0.0002357462,0.00006170775,0.000246928,0.003810324,0.0009026183,0.002441603],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004758595,"threshold_uncertainty_score":0.02516615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009299455110517604,"score_gpt":0.2067531034117766,"score_spread":0.197453648301259,"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."}}