{"id":"W4412850106","doi":"10.1101/2025.07.30.666921","title":"Phyling: phylogenetic inference from annotated genomes","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; U.S. Department of Agriculture; National Institute of Food and Agriculture; National Institutes of Health; National Science Foundation","keywords":"Phylogenetic tree; Inference; Concatenation (mathematics); Computer science; Scalability; Genome; Computational biology; Tree (set theory); Set (abstract data type); Biology; Genomics; Hidden Markov model; Phylogenomics; Gene; Genetics; Artificial intelligence; Clade; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00367077,0.003497431,0.002226962,0.006001661,0.001882412,0.003033075,0.004141643,0.001739202,0.02195283],"category_scores_gemma":[0.0105732,0.0023119,0.002389317,0.00496661,0.001158771,0.00363913,0.003249052,0.003806432,0.01249207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008455834,"about_ca_system_score_gemma":0.001809633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001773187,"about_ca_topic_score_gemma":0.002199096,"domain_scores_codex":[0.9981447,0.0005607556,0.0001254385,0.0006265006,0.0004122902,0.0001303244],"domain_scores_gemma":[0.9972127,0.001560269,0.0002490746,0.0006595357,0.0001761705,0.00014224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003843794,0.0004937237,0.009231054,0.01023723,0.002088089,0.001356764,0.001332797,0.07534049,0.05196745,0.03889661,0.4393562,0.3658558],"study_design_scores_gemma":[0.001174087,0.0003469219,0.005841886,0.0009885165,0.0005425118,0.001774146,0.0005130772,0.5644774,0.04816345,0.1315475,0.2442827,0.0003478113],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0142724,0.001481219,0.6260673,0.0005232636,0.0003569403,0.0003334263,0.1041424,0.2479772,0.004845942],"genre_scores_gemma":[0.07656486,0.001509083,0.660059,0.0003372551,0.0001728351,0.0009056369,0.2317252,0.02617166,0.002554427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02195283,"threshold_uncertainty_score":0.07343954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383034802395939,"score_gpt":0.2302962524512379,"score_spread":0.2164659044272786,"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."}}