{"id":"W3040054936","doi":"10.1093/molbev/msaa159","title":"Broccoli: Combining Phylogenetic and Network Analyses for Orthology Assignment","year":2020,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Biology; Pipeline (software); Phylogenetic tree; Benchmark (surveying); Computational biology; Scalability; Cluster analysis; Phylogenetics; Gene; Genome; Computer science; Genetics; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001113715,0.0001536219,0.0002002121,0.00001913289,0.0001612014,0.000009533837,0.00006645046,0.0001710924,0.000001535486],"category_scores_gemma":[0.00006434145,0.0001475571,0.00005491456,0.0000546401,0.0001679387,5.453662e-7,0.0001421361,0.0000505652,8.517698e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005872789,"about_ca_system_score_gemma":0.00002463854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007130302,"about_ca_topic_score_gemma":0.000008781818,"domain_scores_codex":[0.999028,0.00008366552,0.0001624007,0.0004124356,0.00002783484,0.0002857221],"domain_scores_gemma":[0.9996692,0.0000178412,0.000065097,0.0001106701,0.00004214199,0.00009507615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001078531,0.00001170792,0.04625253,0.00001631024,0.0001485207,0.000001034703,0.00003757616,0.0005529582,0.9495515,0.002090945,0.0002947974,0.0009343231],"study_design_scores_gemma":[0.009148953,0.01333206,0.5889136,0.00004809368,0.001075095,0.0001634489,0.0007447134,0.007533197,0.2605179,0.04257863,0.07333656,0.00260768],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8797289,0.01419531,0.1050852,0.0005382023,0.00008305049,0.0002427549,0.00001941461,0.000005180013,0.0001019913],"genre_scores_gemma":[0.9948889,0.0004287523,0.003325847,0.001041902,0.0001775679,0.00004987851,0.00005980166,0.00001357056,0.00001378215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6890335,"threshold_uncertainty_score":0.6017205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02310432246976341,"score_gpt":0.2958347641104699,"score_spread":0.2727304416407065,"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."}}