{"id":"W3087379575","doi":"10.1101/2020.09.17.302307","title":"MetaFusion: A high-confidence metacaller for filtering and prioritizing RNA-seq gene fusion candidates","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Ontario Genomics; Genome Canada","keywords":"Computer science; Benchmarking; Precision and recall; Data mining; Graph; Fusion; Information retrieval; Machine learning; Theoretical computer science","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":[0.008704674,0.002474361,0.001774627,0.004997414,0.001932844,0.003631417,0.002469377,0.001957089,0.01880307],"category_scores_gemma":[0.01830341,0.001517448,0.002644377,0.002365497,0.0006671234,0.002507735,0.003185161,0.002175366,0.01002781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009638237,"about_ca_system_score_gemma":0.001856385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001754776,"about_ca_topic_score_gemma":0.004568867,"domain_scores_codex":[0.9953517,0.0007764076,0.0003561175,0.001445115,0.001744213,0.0003264827],"domain_scores_gemma":[0.9929718,0.003987526,0.0006926697,0.001149247,0.000811749,0.0003868765],"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":[0.003805301,0.0003131314,0.05535279,0.003449496,0.001580972,0.001327949,0.001389091,0.02082688,0.347761,0.01164374,0.2046121,0.3479376],"study_design_scores_gemma":[0.0005307339,0.000590626,0.0393814,0.0006077639,0.0008803201,0.002614489,0.0005238928,0.3928079,0.4090927,0.02274049,0.1294734,0.0007562265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06147269,0.001591057,0.6177034,0.0006111493,0.0004316063,0.0005068918,0.05207603,0.2578759,0.007731423],"genre_scores_gemma":[0.1603734,0.0003996392,0.7455049,0.0009843948,0.0001836008,0.001083349,0.05252066,0.03430671,0.004643239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01880307,"threshold_uncertainty_score":0.06290251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01709354582161221,"score_gpt":0.2239702655376559,"score_spread":0.2068767197160437,"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."}}